In 2016, the European Union co-funded 17 new robotics projects from the Horizon 2020 Framework Programme for research and innovation. 16 of these resulted from the robotics work programme, and 1 project resulted from the Societal Challenges part of Horizon 2020. The robotics work programme implements the robotics strategy developed by SPARC, the Public-Private Partnership for Robotics in Europe (see the Strategic Research Agenda). 

Every week, euRobotics will publish a video interview with a project, so that you can find out more about their activities. This week features Co4Robots: Achieving Complex Collaborative Missions via Decentralized Control and Coordination of Interacting Robots.

Objectives

Recent applications necessitate coordination of different robots. Current practice is mainly based on offline, centralized planning and tasks are fulfilled in a predefined manner. Co4Robots’ goal is to build a systematic methodology to:

• accomplish complex task specifications given to a team of potentially heterogeneous robots;
• develop control schemes appropriate for mobility and manipulation capabilities of the robots;
• achieve perceptual capabilities that enable robots to localize themselves and estimate the dynamic environment state;
• integrate all in a decentralized framework.

Expected impact

1. The envisioned scenarios involve multi-robot services in e.g. office environments. Although public facilities are in some degree pre-structured, the need for the Co4Robots’ framework is evident since:
2. it will lead to an improved use of resources and a faster accomplishment of tasks inside workspaces with high social activity;
3. it will contribute towards the vision of more flexible multi-robot applications in both professional and domestic environments, also in view of the “Industry 4.0” vision and the general need to deploy such systems in everyday life scenarios.

Partners

KTH ROYAL INSTITUTE OF TECHNOLOGY
BOSCH
NATIONAL TECHNICAL UNIVERSITY OF ATHENS
PAL ROBOTICS
FOUNDATION FOR RESEARCH AND TECHNOLOGY HELLAS
UNIVERSITY OF GOTHENBURG

Coordinator:Prof. Dimos Dimarogonas
dimos@kth.se
www.facebook.com/co4robots

Project website: www.co4robots.eu

Watch all EU-projects videos

If you enjoyed reading this article, you may also want to read:

• New Horizon 2020 robotics projects, 2016: An.Dy
• New Horizon 2020 robotics projects, 2016: BADGER
• Two Horizon 2020 projects researching EU Digital Industrial Platform for Robotics
• EU’s Horizon 2020 has funded $179 million in robotics PPPs

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

In 2016, the European Union co-funded 17 new robotics projects from the Horizon 2020 Framework Programme for research and innovation. 16 of these resulted from the robotics work programme, and 1 project resulted from the Societal Challenges part of Horizon 2020. The robotics work programme implements the robotics strategy developed by SPARC, the Public-Private Partnership for Robotics in Europe (see the Strategic Research Agenda). 

Every week, euRobotics will publish a video interview with a project, so that you can find out more about their activities. This week features BADGER, a Robot for Autonomous Underground Trenchless Operations, Mapping and Navigation.

Objectives

The goal of the proposed project is the design and development of an integrated underground robotic system capable for autonomous construction of subterranean small-diameter, highly curved tunnel networks and for localization, mapping and autonomous navigation during its operation. The proposed robotic system will enable the execution of tasks in different application domains of high societal and economic impact including trenchless constructions (cabling and piping) installations, etc., search and rescue operations, remote science and exploration applications.

Expected impact

The expected strategic impact of BADGER project focuses in:

1. Introduce advanced robotics technologies, including intelligent control and cognition capabilities, to significantly increase the European competitiveness,
2. Drastically reduce the traffic congestion and pollution in the European urban environments increasing, in this way, the quality of life of people,

Enabling technologies for new potential applications: search and rescue, mining and quarrying, civil applications, mapping, etc.

Partners

UNIVERSITY CARLOS III OF MADRID (ES) 
UNIVERSITY OF GLASGOW (UK)
CENTRE FOR RESEARCH AND TECHNOLOGY HELLAS (GR) 
IDS GEORADAR (I)
SINGULARLOGIC (GR)
TRACTO-TECHNIK (D)
ROBOTNIK (ES) 
UNIVERSITY CARLOS III OF MADRID (ES)

Coordinator: Prof. Carlos Balaguer
balaguer@ing.uc3m.es
Twitter: @badger_project

Project website: www.badger-robotics.eu

If you enjoyed reading this article, you may also want to read:

• New Horizon 2020 robotics projects, 2016: An.Dy
• New Horizon 2020 robotics projects – 2016 presented at #ERF2017
• Two Horizon 2020 projects researching EU Digital Industrial Platform for Robotics
• EU’s Horizon 2020 has funded $179 million in robotics PPPs

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

In 2016, the European Union co-funded 17 new robotics projects from the Horizon 2020 Framework Programme for research and innovation. 16 of these resulted from the robotics work programme, and 1 project resulted from the Societal Challenges part of Horizon 2020. The robotics work programme implements the robotics strategy developed by SPARC, the Public-Private Partnership for Robotics in Europe (see the Strategic Research Agenda). Every week, euRobotics will publish a video interview with a project, so that you can find out more about their activities.

A wide variety of research and innovation themes are represented in the new projects: from healthcare via transportation, industrial- and logistics robotics to events media production using drones. Some deal with complex safety matters on the frontier where robots meet people, to ensure that no one comes to harm. Others will create a sustainable ecosystem in the robotics community, setting up common platforms supporting robotics development. One project deals exclusively with the potentially radical changes facing society with the rise of new autonomous technologies. The projects are either helping humans in their daily lives at home or at work, collaborating with humans to help them with difficult, strenuous tasks, or taking care of dangerous tasks, reducing the risk to humans.

The research and innovation projects focus on a wide variety of Robotics and Autonomous Systems and capabilities, such as navigation, human-robot interaction, recognition, cognition and handling. Many of these abilities can be transferable to other fields as well.

Advancing Anticipatory Behaviors in Dyadic Human-Robot Collaboration: An.Dy

Objective

Obj1. ANDY will develop the ANDYSUIT, a wearable technology for monitoring humans involved in whole-body physical interaction tasks.  Obj2. Based on the ANDYSUIT, ANDY will generate ANDYDATASET, a collection of motion and force captures of humans involved in and collaboration tasks. Obj3. From ANDYDATASET, ANDY will develop ANDYMODEL, a set of models to describe human and robot behaviour when engaged in collaborative tasks. Obj4. With ANDYSUIT and ANDYMODEL, ANDY will develop ANDYCONTROL, a reactive and predictive control strategy for human-robot physical collaboration.

Expected impact

Impact on manufacturing domain: ANDY technologies support this objective in two ways: (1) by increasing productivity through more effective production and service processes in which the strength of humans and robots are optimally combined, and (2) by maintaining workers health until the age of retirement including reduced costs for health care and compensation. Impact on healthcare: the ANDYSUIT will open a completely new field for methodological analysis with the possibility of monitoring patients also outside the clinics.

Partners

FONDAZIONE ISTITUTO ITALIANO DI TECNOLOGIA
INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE
INŠTITUT JOŽEF ŠTEFAN
DEUTSCHES ZENTRUM FÜR LUFT- UND RAUMFAHRT
XSENS TECHNOLOGIES BV
IMK AUTOMOTIVE GMBH
OTTO BOCK HEALTHCARE GMBH
ANYBODY TECHNOLOGY A/S

Coordinator: Francesco Nori
francesco.nori@iit.it
http://iron76.github.io
Instituto Italiano di Tecnologia – iCub Facility
Via Morego, 30
16163 Genova, Italy
Phone: (+39) 010 71 781 420
Fax: +39 010 71 70 817
Twitter: @AnDy_H2020

Project website: www.andy-project.eu

In 2016, the European Union co-funded 17 new robotics projects from the Horizon 2020 Framework Programme for research and innovation. 16 of these resulted from the robotics work programme, and one project resulted from the Societal Challenges part of Horizon 2020. The robotics work programme implements the robotics strategy developed by SPARC, the Public-Private Partnership for Robotics in Europe (see the Strategic Research Agenda).

A wide variety of research and innovation themes are represented in the new projects: from healthcare via transportation, industrial- and logistics robotics to events media production using drones. Some deal with complex safety matters on the frontier where robots meet people, to ensure that no one comes to harm. Others will create a sustainable ecosystem in the robotics community, setting up common platforms supporting robotics development. One project deals exclusively with the potentially radical changes facing society with the rise of new autonomous technologies. The projects are either helping humans in their daily lives at home or at work, collaborating with humans to help them with difficult, strenuous tasks, or taking care of dangerous tasks, reducing the risk to humans.

The research and innovation projects focus on a wide variety of Robotics and Autonomous Systems and capabilities, such as navigation, human-robot interaction, recognition, cognition and handling. Many of these abilities can be transferable to other fields as well.

At the European Robotics Forum 2017, on 22-24 March 2017, Edinburgh, Scotland, UK, all projects presented themselves during a dedicated workshop.

Watch the video with all Horizon2020 projects presentations:

Watch the video with FP7 projects results:

Every week, euRobotics will publish a video interview with each project, so that you can find out more about their activities.

We are looking forward to following these new projects and accompanying them to bring benefits to Europe’s citizens and economy.

Horizon 2020 RobMoSys

Market pull for better factory automation and the ever-increasing relevance of software in every domain are triggering a rethink in how we develop software for robotics. Techniques such as Model Driven Engineering (MDE), proven effective in businesses like automotive and aerospace, can be used to this end. Practices such as collaborative development through Open-Source Software (OSS) can also be used. Two projects funded by the European Horizon 2020 research and innovation programme are exploring these opportunities, in a common foundational effort for an EU Digital Industrial Platform for Robotics.

HORIZON 2020 ROSIN project.

RobMoSys, coordinated by the French Alternative Energies and Atomic Energy Commission, envisions a composition-oriented approach to system-of-system integration which is independent of the current code-centric robotic platforms, yet can build on top of them. ROSIN, led by the Delft University of Technology, aims to exploit the current momentum of the open-source Robot Operating System (ROS) and make it better, more accessible, and more relevant to industrial applications. Both projects foresee active involvement of the robotics community, as they make available through Open Calls significant parts of their budgets for third-party technical development.

RobMoSys: Composable Models for Robotics Systems

In the realm of advanced software engineering methods and tools, model-driven engineering demonstrated to be a key driver to manage system complexity in many engineering domains. RobMoSys brings to the robotics software community a model-driven support, specifically targeting the autonomous nature of robotics systems and their validation. To this end, RobMoSys adopts a composition-oriented approach that manages, maintains and assures system-level properties, while preserving modularity and independence of existing robotics frameworks and code bases.

RobMosys will engage the robotics community in this endeavour, thanks to two rounds of Open Calls. Expected results include improved tools, interoperable tool-chains and better software for an open and sustainable European robotics software ecosystem of professional quality and scope.

The RobMoSys project is coordinated by the Commissariat à l’énergie atomique et aux énergies alternatives (France). Further partners include COMAU (Italy), Eclipse Foundation Europe (Germany), EUnited AISBL (Belgium), Hochschule Ulm (Germany), KU Leuven (Belgium), PAL ROBOTICS (Spain), SIEMENS (Germany) and Technical University of Munich (Germany).

ROSIN: ROS-Industrial quality-assured robot software components

Open-Source Software for robots is a de-facto practice in academia, and its advantages can benefit industrial applications as well. The worldwide ROS-Industrial initiative has been using ROS, the Robot Operating System, to this end. In order to consolidate Europe’s dominance in advanced manufacturing, the H2020 project ROSIN will push the role of the EU within ROS-Industrial to a leading position.

It will achieve this goal through three main actions on ROS. The first one is to ensure industrial-grade software quality. Secondly, the project partners will promote new business-relevant applications. More industrial tools and components will be created and existing ones will be improved. This will be performed by making 50% of the ROSIN budget available to collaborating European users and developers for so-called Focused Technical Projects (FTPs). The third action is to support educational activities for students and industry professionals. Interested entities are welcome to apply for participation.

The ROSIN project is coordinated by TU Delft (the Netherlands), and further partners include Fraunhofer IPA (Germany), IT University of Copenhagen (Denmark), FH Aachen University of Applied Sciences (Germany), Fundacion Tecnalia Research & Innovation (Spain) and ABB AB (Sweden).

Duration: January 1^st 2017 to December 31^st 2020

Funding: These projects received funding from the European Horizon 2020 research and innovation programme under grant agreements No 732410 (RobMoSys) and 732287 (ROSIN).

 RobMoSys

Website: www.robmosys.eu
Project partners: Commissariat à l’énergie atomique et aux énergies alternatives (France, coordinator), COMAU (Italy), Eclipse Foundation Europe (Germany), EUnited AISBL (Belgium), Hochschule Ulm (Germany), KU Leuven (Belgium), PAL ROBOTICS (Spain), SIEMENS (Germany), Technical University of Munich (Germany)

 ROSIN

Website: www.rosin-project.eu
Project partners: Delft University of Technology (The Netherlands, coordinator), Fraunhofer Institute for Manufacturing Engineering and Automation IPA (Germany), IT University of Copenhagen (Denmark), Fachhochschule Aachen University of Applied Sciences (Germany), Fundacion Tecnalia Research and Innovation (Spain), ABB AB (Sweden)

Teams participating in the ERL Service Robots local tournament at certified Leon@Home Test bed. Copyright: Universidad de León.

The European Robotics League has closed a successful first season. Funded by the European Union’s Horizon 2020 Programme for research, the ERL brings a common framework for two indoor robotics competitions, ERL Industrial Robots and ERL Service Robots and one outdoor robotics competition, ERL Emergency Robots.  The three competitions are designed to target three clear objectives: the European societal challenge of an aging population, the strengthening of the European robotics industry and the use of autonomous systems for emergency response.

The last tournament of the ERL season 2016/17 took place at the Leon@Home Test bed located at the Módulo de Investigación en Cibernética of the Universidad de León, Spain. The ERL Service Robots local competition organised by Dr Vicente Matellan and the Leon Robotics Group was held from the 13-17 March and consisted of several trials, which mainly took place on the last day.

Caption: (Left) Leon@Home Test bed. (Right) Módulo de Investigación en Cibernética (MIC). Copyright: Universidad de León

The teams competed in different Task Benchmarks (TBM) and Functionality Benchmarks (FBM), comprising “TBM1: Getting to know my home”, “TBM4: Visit My Home”, “FBM2: Navigation Functionality” and “FBM3: Speech Recognition”. Robots were required to generate a map of their environment, detect random changes in the location of furniture and other items, interact effectively with humans and demonstrate different behaviors when dealing with known and unknown people, and help them with general tasks throughout the day.

The three teams that participated in the local tournament were SPQReL, University of Rome (Italy) and University of Lincoln (UK), Outsider Bots, Universidad Rey Juan Carlos (Spain) and University of Luxemburg (Luxembourg), and Leonbot, Universidad de León (Spain).

Caption: (Left) Example of a  semantic Map of the environment. (Right) Objects used in TBM1. Copyright: Universidad de León

The final score for each team was calculated as the MEDIAN of the best performance in each TBM and FBM trials. The teams’ scoring and standings for the season 2016/2017 are available on the ERL Service Robots and ERL Industrial Robots web page.

The ERL Service and ERL Industrial Awards (Season 2016/17), sponsored by Texas Instruments University Program, were handed to the winning teams during the euRobotics Awards Ceremony held on 23 March, at the National Museum of Scotland, in Edinburgh.

ERL Tournaments dates (Season 2017/18)

The European Robotics League has announced the tournament dates for the new season. The local and major tournaments are based in Europe and are open to international participation from Universities, Research labs, Industry and/or end-users. The events are open to the public and anyone interested is welcome to contact the local organisers and attend as a spectator.

There are eight tournaments already confirmed for this season 2017-2018 and new ones are expected to be confirmed in the next months.

ERL Service Robots

Major Tournament

• 28-31 August 2017: as part of the IEEE RO-MAN 2017 event held in Lisbon, Portugal

Local Tournament

• 26-30 June 2017: BRL Anchor Personalised Assisted Living Studio, Bristol Robotics Laboratory, Bristol, UK
• 11-15 September 2017: Leon@Home test bed, Universidad de Leon, Leon, Spain
• ERW 2017, 20-26 November 2017: PAL Robotics, Barcelona, Spain.
• 4-7 December 2017: ECHORD++ RIF Peccioli test bed, Peccioli, Italy.

ERL Industrial Robots

Local Tournament

• 11-15 September 2017: b-it-bots@Work Test Bed, Bonn-Rhein-Sieg University of Applied Science, Sankt Augustin, Germany
• ERW 2017, 21-25 November 2017: Politecnico di Milano, Milan, Italy

ERL Emergency Robots

Major Tournament

• 15-23 September 2017: Piombino, Italy. (Download ERL Emergency 2017 brochure)

ERL Emergency 2017 promo video:

This season 2017/18, Worthington Sharpe Ltd., silver sponsor of ERL Emergency Robots 2017,  will provide one Wing Ground Control Station (GCS) for loan to a selected applicant team. Teams wishing to borrow the Wing GCS must apply to the ERL consortium, following the application procedure set on ERL Emergency web page. Applications received will be evaluated by the consortium and Worthington Sharpe Ltd. to select the team who will be granted the loan equipment.

PAL Robotics, a platinum sponsor of ERL Service Robots, announced at the ERL Awards ceremony that the company will offer on a very affordable rental scheme limited units of TIAGo robots for different teams to use in the competition.

Companies and academic institutions interested in sponsoring ERL events can contact Dr Fausto Ferreira for information on the sponsorship and exhibitor packages.

To find out more about the European Robotics League, please visit www.robotics-league.eu.

 ERL History

The ERL is the natural evolution of a series of highly successful previous competitions that were established via FP7 funded projects: RoCKIn, euRathlon and EuRoC.  All three projects aimed to foster scientific progress and innovation in cognitive systems and robotics through the design and implementation of new competitions.

The European Robotics League is funded by the European Union’s Horizon 2020 Programme for research, technological development and demonstration under grant agreement n° 688441

Watch the European Robotics League promo video:

www.robotics-league.eu

About euRobotics and SPARC

euRobotics is a non-profit organisation based in Brussels with the objective to make robotics beneficial for Europe’s economy and society.  With more than 250 member organisations, euRobotics also provides the European Robotics Community with a legal entity to engage in a public/private partnership with the European Commission, named SPARC.

SPARC, the public-private partnership (PPP) between the European Commission and euRobotics, is a European initiative to maintain and extend Europe’s leadership in civilian robotics. Its aim is to strategically position European robotics in the world thereby securing major benefits for the European economy and the society at large.

SPARC is the largest research and innovation programme in civilian robotics in the world, with 700 million euro in funding from the European Commission between 2014 to 2020, which is tripled by European industry to yield a total investment of 2.1 billion euro. SPARC will stimulate an ever more vibrant and effective robotics community that collaborates in the successful development of technical transfer and commercial exploitation.

www.eu-robotics.net

www.eu-robotics.net/sparc

SoMa is a collaborative research project between the Technische Universität Berlin (TUB), Università di Pisa, Istituto Italiano di Tecnologia, Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), the Institute of Science and Technology Austria, Ocado Technology, and Disney Research Zurich.

One of the main challenges of robotic manipulation has been the handling of easily damageable and unpredictably shaped objects such as fruit and vegetable groceries. These products have unique shapes and should be handled in a way that does not cause damage or bruising. To avoid damaging sensitive items, the project uses a compliant gripper (i.e. one that possesses spring-like properties) in conjunction with an industrial robot arm.

The variation in shape of the target objects imposes another set of constraints on the design of a suitable gripper. The gripper must be sufficiently versatile to pick a wide variety of products, including Ocado’s current range which includes over 48,000 hypermarket items.

How RBO softhand could help address these challenges

The SoMa project (EU Horizon 2020 GA 645599) aims to design compliant robotic hands that are suitable for handling fragile objects without much detailed knowledge of an item’s shape; in addition, the robotic arms should also be capable of exploiting environmental constraints (physical constraints imposed by the environment). The goal is to develop versatile, robust, cost-effective, and safe robotic grasping and manipulation capabilities.

An example of a compliant gripper is the RBO Hand 2 developed by the Technische Universität Berlin (TUB). The gripper uses flexible rubber materials and pressurized air for passively adapting grasps which allows for safe and damage-free picking of objects. With seven individually controllable air chambers, the anthropomorphic design enables versatile grasping strategies.

Due to its compliant design, the robotic hand is highly under-actuated: only the air pressure is controlled, while the fingers, palm, and thumb adjust their shape to the given object geometry (morphological computation). This simplifies control and enables effective exploitation of the environment.

Integrating the RBO Hand 2 with an industrial manipulator and testing with a standard object set

The Ocado Technology robotics team replicated a production warehouse scenario in order to evaluate the performance of the RBO Hand 2 for Ocado’s use case. The team mounted the soft hand on two different robot arms, a Staubli RX160L and a KUKA LBR iiwa14. Both of these arms can operate in the standard position controlled mode; in addition to this, the KUKA provides the capability of demonstrating a certain amount of software controlled compliance in the arm.

Ocado designed a set of experiments to evaluate grasping performance on an example set of artificial fruit stored in an IFCO (International Fruit Container) tray. The adopted strategies attempted to exploit environmental constraints (e.g. the walls and the bottom of the tray) to perform the gripping tasks successfully.

The experiments started with the simple scenario of grasping a single object from the example set using only the bottom of the tray. Initial results showed that the hand is able to successfully grasp a variety of shapes and the results suggested the chance of success increased when environmental constraints are being used effectively to restrict the movement of the object.

In the coming months, Ocado plans to explore more complex scenarios, adding more objects in the IFCO, and introducing additional environmental constraints that could be exploited by a grasping strategy.

If you liked this article, you may also enjoy these:

• NAIST OpenHand M2S released
• Five applications for craft beer robots
• NPR podcasts discuss automation and the future of work
• Automatica’s exhibitors were trumpeting Industry 4.0. Is this the turning point for robotics?
• Advanced Robotics Manufacturing Institute in planning for USA

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Source: vinbot.eu

The list of the new H2020 project in robotics from Call 3 2016 and the call under Societal Challenges 2016 is ready. The 17 robotics projects funded under Horizon 2020 will work with a wide variety of research and innovation themes: health robotics, autonomous cars, industrial robotics and logistics to events media productions.

An.Dy: Safety certified robots with the ability to react to unintentional contacts (co-bots).

Badger: Autonomous underground robotic system that can drill, manoeuvre, localise, map and navigate in the underground space.

Co4Robots: Different multi-tasking robots with varying capabilities deployed to provide services such as object handling/transportation, or pickup and delivery operations.

CYBERLEGs Plus Plus: powered robotic ortho-prosthesis to help restore mobility allowing amputees to perform physical activity.

Dreams4Cars: Focusing on rare events, such as near miss car accidents the robots can develop safe behaviours for hypothetical/unexperienced situations.

HEPHAESTUS: Cable-robots using 3D to help with high risk and critical construction tasks such as prefab wall installation.

ILIAD: Flexible and rock-solid reliable intra-logistic systems, which can be quickly deployed and integrated in current warehouse facilities, in particular in the food sector, yet guaranteeing safe operation in environments shared with humans.

IMAGINE: The project seeks to enable robots to understand the structure of their environment and how it is affected by its actions.

MoveCare: A multi-actor platform to supports the independent living of the elderly at home by monitoring, assist and promoting activities to counteract decline and social exclusion

MULTIDRONE: multi-drone platform for media production to cover outdoor events with improved robustness, security and safety mechanisms.

REELER: Tackling major societal concerns the project will formulate guidelines in the REELER Roadmap for distributed responsibility among roboticists, users/affected stakeholders and policy-makers by closing the current gap between these.

REFILLS: A robotic systems able to address the in-store logistics needs of the retail market.

RobMoSys: The project proposes composable models and software for robotics systems building an open and sustainable, agile and multi-domain European robotics software ecosystem.

ROSIN: The project aims to create a step change in the availability of high-quality intelligent robot software components for the European industry by building on the existing open-source “Robot Operating System” (ROS) framework and leveraging its worldwide community.

ROPOD: Cost-effective and human-friendly automated guided vehicles (AGVs) for logistic tasks.

SMARTsurg: Smart wearable robotic tele operated surgery focusing on real-world surgical scenarios of urology, vascular surgery, and soft tissue orthopaedic surgery.

VERSATILE: Flexible robotic cells with dual robot arms that can adapt automatically to the high number of different products in industries such as automotive, aerospace and handling and packaging.

You can read more about each project chosen for funding here.

Europe’s roadmap for robotics released its latest version on 2 December. The MAR is updated annually as priorities, technologies and strategic developments shape European research development and innovation. This version of the MAR relates to the Horizon 2020 robotics work programme defined for the 2017 call in ICT25, ICT 27 & ICT-28.

If you liked this article, you may want to also read more about Horizon 2020:

• Horizon 2020 earmarks € 98M for new wave of European robotics
• Robohub Focus on European Robotics
• #ERF2016 webcam: Horizon2020 project pitches
• 2 agricultural robotics projects funded under latest Horizon 2020
• EU’s Horizon 2020 has funded $179 million in robotics PPPs

Horizon 2020 projects on Robohub

• Future robots will learn through curiosity and self-generated goals
• XoSoft: Intelligent trousers designed to assist people with limited mobility
• Surveying flooded mines with UNEXMIN: Interview with Norbert Zajzon
• Space for the masses as helium balloons and remote control planes reach through the stratosphere

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Helium balloons are being used to carry people, experiments and satellite launchers into near space. Image courtesy of Zero2Infinity

Space will soon be within the grasp of everyday people, small countries, researchers or start-up companies thanks to a fleet of low-cost launch vehicles under development across Europe.

From remote control drones that can fire rockets into orbit from the edge of space, to giant helium balloons that could carry tourists, science experiments or satellite launchers into the stratosphere, small-scale start-ups are stepping into the control room and embarking on a new low-cost space race.

It represents an exciting new wave of space travel, following in the vapour trails of private companies such as Elon Musk’s SpaceX or Richard Branson’s Virgin Galactic.

The Issue

The EU is aiming to encourage private companies to develop low-cost launch systems as part of its Space Strategy for Europe announced in October this year.

The objective of EU funding for research into space technologies is to enable Europe to access space independently and affordably, and strengthen the capability of European scientists and engineers.

Between 2014 and 2020, it plans to spend over EUR 12 billion on three space programmes – satellite navigation, earth observation and space research.

Where once only global superpowers with vast budgets could go, Europe’s entrepreneurs and innovators will soon be travelling for a fraction of the cost.

One of these innovators is Zero 2 Infinity, a Spanish start-up working on helium balloon-borne spacecraft.

‘It’s the cheaper way because it’s more efficient, you need fewer engineers to build it,’ explained Jose Mariano Lopez-Urdiales, chief executive.

Near space

The idea is that the balloon would carry a passenger pod into what is known as near space, somewhere between 20 km and 100 km above the earth’s surface, or carry its small rocket-powered Bloostar spacecraft which it could then launch much higher into low-earth orbit.

Zero 2 Infinity customers are already balloon launching satellites for short periods of high-altitude testing, and the company has EUR 140 million in expressions of interest for full satellite launches.

It was the leader of the EU-backed HELIUM project, which developed the concept for a near-space European laboratory that allows orbiting research at 36 km, and the life support system for the two pilots in the initial six-hour flights.

Although space tourists could soon be using the balloon launch system to take selfies in near space, the first passengers are likely to be scientists, according to Lopez-Urdiales.

Aiming higher than the balloon satellite launcher’s range of 600 km, Europe’s ALTAIR project is readying the blueprints for a remote-controlled aircraft which would use a rocket launch module to blast sub-200 kilogramme satellite payloads into orbit and take off in 2020 at the earliest.

Runway

ALTAIR’s launch system — similar to Virgin Galactic’s piloted White Knight 2 space tourism aircraft in appearance and general function — would take off from a runway, before ferrying satellites up to an altitude of 12-15 km and igniting its rocket payload.

But the similarities end there. ALTAIR project manager Nicolas Bérend says the project is focused on affordable, remote-controlled launches, calling on the experience of French space centres CNES and Onera, creators of the Eole automated launch aircraft demonstrator which is the project’s precursor.

By the end of the EU-funded program in 2018, the six-country collaboration will have a final concept for the unmanned aircraft, its hybrid propulsion engine rocket launcher and ground operations, and will demonstrate its launch technology by doing suborbital tests using a scale model.

By removing the human pilot and designing a facility geared towards a high launch frequency and minimal staffing, they hope to bring down the costs enough to make the project economically viable.

‘It is essential to the project’s success to restrict launch costs to around EUR 4 million, a price the team’s market analysts consider to be a competitive launch price,’ said Bérend.

That should give them access to a growing market for small satellite launches, often in the form of so-called CubeSats, nanosatellites normally no more than 10 centimetres wide, a market where Europe is lagging behind at the moment.

Even though Europe covers large-to-medium launches with its Ariane 6 and Vega rockets, and suborbital rockets from the Andøya launch site in Norway, it has no small-satellite solution.

‘The small satellites are all launched outside of Europe with Russian or Indian launchers,’ said Bertil Oving, of the Netherlands Aerospace Centre. ‘There is a small-satellite market, it’s booming and if Europe does not take the chance now, then we may lose this possibility.’

He is the coordinator of SMILE, an EU-funded project designing a small-scale launcher for satellites of up to 50 kg.

SMILE will design and start component testing of a standard-format rocket, along with the necessary upgrades to the Andøya facility, by 2019, keeping costs below EUR 50 000 per kilogramme launched, and hopefully cutting the expensive wait for satellites to be able to piggyback on one of the larger rockets.

3D printing

Larger rockets benefit from an economy of scale, and SMILE’s competitiveness would come from advances in reusable components, automated composite manufacturing, 3D printing and also high-volume production.

‘The payload versus the total mass becomes smaller when the launcher is smaller, so it’s a cost aspect challenge,’ said Oving.

He said SMILE is pushing advances in reusable liquid-fuelled engines and its automated manufacturing advances would have automotive and aviation industry uses, but he thinks the biggest implications of low-cost, low-orbit access will be for consumers.

‘The idea for small satellites like CubeSats is to approach them like FedEx & DHL,’ he said. ‘We will simply bring it to where you want to have it.’

European organisations may soon make it easier to get equipment into near space and low-earth orbit.

If you enjoyed this article, you may also want to read these Horizon related articles:

• EU’s Horizon 2020 has funded $179 million in robotics PPPs
• Keeping a robotic eye on pollution
• Protecting European wine: Vinbot rover optimises harvest and quality
• A helping hand for high-tech firms

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

The iCub robot (by ITT, Genoa) exploring an object. Credit: Technische Universitaet Darmstadt

Imagine a friend asking for help to tidy up her room that is full of objects and furniture. Now imagine for some reason your friend will not be there to help (we are all lazy) and she just describes, showing photos, the way she would like the room to look. Although it may be a boring task, everyone could handle this with ease. As little kids, we discovered new objects and learned to recognise them and developed new skills to manipulate these objects. Guided by our curiosity, we progressively developed visual, attentional, and sensorimotor knowledge that allows us, as adults, to manipulate our physical environment as desired.

Current robots are ill-suited for these challenges. Imagine a humanoid robot helping to clean a room. Assume you have shown the robot the room in its normal tidy state, but once it is messy you tell the robot to make it tidy, as it was before. In such conditions, it would be tedious to teach the robot where to allocate attention and show how each object has to be manipulated to put it in its desired place and orientation, or how to sequence the different actions to do so.

Although new sophisticated robots and powerful algorithms are developed each year, carrying out complex duties and finding unknown solutions to different tasks still require tedious programming of low-level motor control details. In the best case, robots are able to learn a small set of inflexible behaviours. If we compare current artificial agents to biological ones, we find that artificial ones still present relevant limitations in terms of autonomy and versatility.

Future robots, instead, should be able to learn how to truly “master” their environments autonomously, i.e. to self-generate goals and autonomously and efficiently learn the skills to accomplish them based on the progressive acquisition, modification, generalisation, and recombination of previously learned skills and knowledge. This will allow them, with little additional learning, to change an environment from its current state to a wide range of potential goal states desired by the user. The question is: how can we create future robots that are able to face this challenge?

The GOAL-Robots project

Addressing this question and having central importance for applications and artificial intelligence, is the start of a new European project led by the Laboratory of Computational Embodied Neuroscience (LOCEN), an Italian research group based in Rome at the Institute of Cognitive Sciences and Technologies of the Italian National Research Council (ISTC-CNR).

“GOAL-Robots – Goal-based Open-ended Autonomous Learning Robots” project ranked #1 among all 11 projects funded out of the 800 participants to the April 2016 EU FET-OPEN call (Future Emergent Technologies), and is part of the Horizon 2020 EU research program. LOCEN and its Principal Investigator, Gianluca Baldassarre, will coordinate the project consortium also involving other three important European research groups:

1. the Laboratoire Psychologie de la Perception (LPP, France), headed by Kevin O’Regan and based in Paris at the Institut Paris Descartes de Neurosciences et Cognition, that will carry out experiments on the learning of goals and skills in children;
2. the Frankfurt Institute of Advanced Studies (FIAS, Germany), headed by Jochen Triesch, focussed on the development of bio-inspired visual and attention systems and motor synergies; and
3. the group of roboticists directed by Jan Peters, based at the Technische Universitaet Darmstadt (TUDa, Germany), which will lead the challenging robotic demonstrators of the project.

GOAL-Robots follows a previous European project, IM-CLeVeR (“Intrinsically Motivated Cumulative Learning Versatile Robots,” where LOCEN and its former project partners investigated the role of intrinsic motivations (IMs) in fostering autonomous learning both in biological agents and robots. The scientific investigation of IMs began by observing how children, driven by curiosity, explore and interact with the world, acquiring knowledge of how things work and an ample repertoire of sensorimotor skills to act on it.

A robot exploring the effects it can produce on a “mechatronic board”. Credit: Laboratory of Computational Embodied Neuroscience.

If curiosity and IMs are at the basis of human versatility and adaptability then endowing artificial agents with architectures and algorithms mimicking IMs might help the needed “motivational engine” to drive robots through an “open-ended” autonomous learning process without the need for continuous programming and training by human experts.

GOAL-Robots also adds a new critical component for the development of open-ended learning in robots: goals. A goal is an agent’s internal representation of a world or body state or event, or a set of them, having two important properties. Firstly, the agent can activate this representation even in the absence of the perception of the corresponding world state or event. Secondly, this activation has “motivational effects”, i.e. it can contribute to select and focus the agent’s attention and behaviour, and guide its learning processes, towards the accomplishment of the goal. The possibility of creating motivating goals at will, even abstract ones, and use them to guide actions and learning is a key element of the behavioural flexibility and learning power of biological agents. The bet of GOAL Robots is that endowing robots with suitable mechanisms to form and exploit goals for learning will drastically increase their autonomous learning potential.

An example of robot controller able to discover goals inspired by surprise mechanisms in brain. Credit: Laboratory of Computational Embodied Neuroscience, Institute of Cognitive Sciences and Technologies, Italian National Research Council.

The possibility of creating and motivating goals at will, even abstract ones, and use them to guide actions and learning is a key element of the behavioural flexibility and learning power of biological agents. GOAL-Robots bets that endowing robots with suitable mechanisms to form and use goals will drastically increase their autonomous learning potential.

Challenges and ideas

The challenging idea of GOAL-Robots is to combine the mechanisms related to IMs with the power of goals. IMs will in particular guide robots in the autonomous discovery of new interesting events in the world caused by its own action. The robots will thus be driven to explore the environment by their curiosity and to self-generate increasingly complex goals, using them to learn numerous skills in an open-ended fashion.

A simulated robot investigating some spheres that can turn on when touched. Credit: Laboratory of Computational Embodied Neuroscience, Institute of Cognitive Sciences and Technologies, Italian National Research Council.

The open-ended process of competence acquisition requires sophisticated mechanisms and the integration of different architectural components. In particular, the robots will need to acquire new skills without impairing previously learned ones and, at the same time, to re-use previously acquired skills to speed up the acquisition of skills for new goals (knowledge transfer). Moreover, they will need to be able to compose previously acquired skills to form increasingly complex skills. These issues represent some of the most important current challenges of artificial intelligence. To face them, the project will use state-of-the-art algorithms to face both the processing of sensory information (e.g., on the basis of deep neural networks) and the organisation and exploitation of knowledge related to motor control (e.g., using dynamic movement primitives and echo-state neural networks).

Moreover, all the mechanisms related to the different components of the learning process will need to be integrated within a single architecture controlling the robots: the high-level goal-formation processes will be connected to motivational layers where, on the basis of IMs, the robot will form and select goals to focus on; goals will be gradually connected to the low-levels of the controllers so that the robot will be able to recall the learned skills to accomplish desired goals or to form more complex skills by composing them; knowledge transfer between different skills will be integrated with the avoidance of their interference, and so on. These mechanisms will be useful not only for the autonomous learning phase but also to allow an external user to exploit the knowledge and competence acquired by the robots.

Robotic hand tries to put object in the holes of a toy. Credits: Technische Universitaet Darmstadt

Each year the project will present a complex “robotic demonstrator” where sophisticated robotic platforms (such as iCub or Kuka robots) will be guided by the architectures developed by the project to solve increasingly challenging tasks. These demonstrators will not only show the advancements of the project but also aims to become general benchmarks for open-ended learning in autonomous robots.

The final demonstrator will aim to tackle the “futuristic” challenge that we posed at the beginning of this article: is it possible for a robot to show a versatility and adaptability similar to those of humans interacting with real world scenarios? In particular, the robots will be requested to: (a) observe an ordered scenario formed by several objects located in containers and shelves on a working plane, and (b) reproduce such state of the environment after a user misplaces and mixes the objects.

If GOAL-Robots maintains its promise, you won’t have to worry anymore about lazy friends: when they ask for your help, you will simply ask your artificial friends to help them for you!

Robothespian welcomes visitors to Bristol Robotics Lab during #ERW2015. Image: RIF@Bristol

Bridging the gap between cutting-edge research in academia and the vibrant robotics startup ecosystem is no easy task. This Wednesday in the UK city of Bristol, a free public event titled “From Imagination to Market” — the centre piece of European Robotics Week 2015 — took on that challenge by bringing together leading innovators, researchers, startups and strategists. Below are the key moments and insights from the event.

Organised by euRobotics AISBL (which represents robotics stakeholders in Europe) and the Bristol Robotics Laboratory (BRL — one of the largest facilities of its kind in Europe), this event was packed insight, stories and advice.

The day kicked off with an introduction to robots in science fiction by Michael Szollosy and a look at the field of RoboLaw by Andrea Bertolini, before taking a deep dive into the BRL’s state-of-the art research on swarms, human-robot interaction and soft robotics. Then we heard from up-and-coming startups Open Bionics and Reach Robotics, we got an overview of the UK robotics landscape, followed up by inside info from two of the UK’s most successful corporations: Dyson and Ocado. In the middle of all this, we were whisked off to BRL to meet real-life robots before being brought back for a rousing panel discussion to bring all that freshly gained knowledge together.

There was more: the day finished with a robot build-a-thon, where kids aged 5-14 years helped researchers build 100 robots to ‘treat’ artificial cancer cells. Robot stations were also placed throughout Bristol’s Science Museum, showcasing a swarm of 200 coin-sized robots, Thymio and TiddlyBot robots to program, the latest robots from the Robogals team, and students from Digimakers.

Here is a taste of what we learned in just one day:

What could be going from imagination to market in the future

Control in human-robot interaction can take four forms, BRL’s Angelika Peer told us. First is bilateral control, where transparency, task performance, telepresence, robust stability and conflicting requirements need to be taken into account. Then we have shared control — the kind found in robotic assistive walking devices, or in the automation of assembly and transportation tasks, which can be performed either collaboratively with a human operator, or learned from humans by imitation. For the third category — supervisory control — Peer outlined the EU-funded project, VERE, which stands for Virtual Embodiment and Robotic Re-embodiment. Autonomous control makes up the fourth category, and this can be sequential, parallel, or parallel and symmetric.

Sabine Hauert speaking at ERW2015

Taking swarming into the real world through the simulation of basic rules forms the basis for Sabine Hauert’s research at the BRL. Her interest in robot swarms inspired her research in nanoparticles to cure cancer. The challenge is to design the behaviour of the nanoparticles. How do you synchronise them? How sticky should they be to deal effectively with cancer cells? Hauert’s research also translates to robot swarms that work in the thousands, and we’re just now reaching that stage. Watch her TEDx talk here.

BRL’s Jonathan Rossiter has just received a £2.5m UK grant to make trousers out of soft robotics — a futuristic aide to enable those with mobility issues. The limitations of rigid robots have inspired his research, which forms part of the EU’s Robosoft action. With applications in everything from mobile phones to alleviating deep vein thrombosis, soft robotics is really taking off. While it took 15 years to develop adequate motors, Rossiter believes work on materials will move much faster.

So when can we buy this stuff?

“It’s just starting,” said euRobotics road-mapping expert David Bisset. “We tend to use the phrase ‘on the cusp.’ There are a lot of products out there, but long way to go.” The UK landscape, he said, is composed of four different areas: manufacturing and agricultural goods, healthcare and consumer, transport and cities and energy, and utilities and the environment. The drivers are economic, societal (such as the crisis in care for the elderly), markets (which are concerned with efficiency) and, finally, getting robots to do things we don’t want to, such as vacuuming. But, crucially, the infrastructure needs to be in place for robots to become a valued part of activity. The biggest market is healthcare, with a value of £323bn. But it’s not the value of the robots themselves, it’s their impact that’s important, and for this we need strategy, assets, skills clusters and challenges — landing a UAV at Heathrow, mapping out North Sea pipelines, and driving though a town, for instance. Here, SMEs are a very important part of the mix.

Coming soon to a market near you are cutting-edge robotic technologies from two of these SMEs: Open Bionics and Reach Robotics, both originating from the BRL incubator.

Open Bionics is the first company to use 3D scanning and printing to fit a prosthetic limb. The startups’ CEO, Joel Gibbard, relayed how a handheld device that cost a couple of hundred pounds now makes it possible to customise every device, remotely and cost-effectively. The company took time to ask amputees what they wanted, and it turned out they would rather have a prosthetic that is comfortable, light weight, and that helps them celebrate their limb difference over a prosthetic that offers high functionality. To this end, Open Bionics focused on fashion and design, creating a Swarovski crystal-encrusted prosthetic arm, and partnering with Disney for Ironman, Elsa and Star Wars hands that light up (which produces additional benefits). Plus there’s a subscription model in the works so that children can have the size of their prosthetic adjusted as they grow.

Reach Robotics CEO Silas Adekunle at ERW2015

Reach Robotics CEO Silas Adekunle sees a future where video game characters will leap out of the screen into our world. Their robot, MekaMon, can do battle in both the real and virtual worlds, can be customised, and has its very own universe complete with epic battles. The company recently had its first round of VC funding, from Qualcomm and Techstars, among others. “When creating, startups are in the sausage-making business,” he said, “It’s lovely in front but a mess in the back.” Team members have left and been replaced, and there have been 17 grants and 24 product iterations, said Adekunle. MekaMon is on track and due on the market for Christmas 2016.

The startup ecosystem

Support for startups, how to raise the funding, and what infrastructure is needed to allow startups to be successful were covered by the next two speakers, BRL’s Farid Dailami and Renaud Champion of Robolution Capital.

“I’m looking for products that will solve a problem but not to replace someone,” said Champion, speaking of his investment policies.  “What I’m looking for is a bicycle for the mind, and project linked to robotics to solve any kind of issue: ethical, legal or societal.” He had further advice for would-be entrepreneurs:

• Know what’s at the core of your product, not just the IP. What is the service you give to users? What is your competitive advantage?
• Don’t confuse getting feedback with convincing people.
• Be able to name failure in your product development.
• A low [financial] burn rate does not mean you have time to waste.
• Don’t validate your customer hypothesis with investors.
• Start off with Indiegogo and Kickstarter rather than VCs; it’s a question of strategy.

Meanwhile, for those ready to develop and test products, services or processes, Farid Dailami outlined the facilities available at BRL’s Robotics Innovation Facility (RIF).

Robots in the real world

Next up were two success stories from industry. Note that neither Dyson nor Ocado are companies that have previously worked with robots. The former is best known for vacuum cleaners and the latter is an online grocer. Their stories were inspiring because they show the power of robotics when it enters everyday life.

“The only way you are going to get something to work in the real world is by putting it in the real world,” said Dyson’s Mike Aldred. His key take away message was “test test test.” Dyson’s 360 Eye robot vacuum cleaner was 16 years in development and went through 110,000 trials in real homes over more than eight years. Two person-years were spent just in creating a test tool that identifies outliers and anomalies. But Aldred was keen to point out that, since it went on sale in Japan four weeks ago, the 360 Eye has already saved customers 250,000 hours that they could spend doing something else. However, for a robot be taken up, it has to perform better than a human, he said. His advice for would-be innovators was: “Always try to do something that can never possibly work. Innovation comes from thinking broadly and thinking differently.”

Thinking very differently from the average grocer is what got online supermarket Ocado interested in robotics. The company’s robotics research team leader Graham Deacon outlined the two major projects the company is involved with (in collaboration with European research institutes): Secondhands and SoMa, both funded via Horizon 2020 grants. SoMa is about using compliant robotic mechanisms to handle deformable products without conventional geometry, and Secondhands is seeking to develop a humanoid robot to assist maintenance technicians in routine and preventative maintenance. It’s a hugely ambitious exercise in collaborative robotics to develop a safe robot that can work shoulder to shoulder with a human.

Bringing it back to the table

Panel roundup at ERW2015

During the panel discussion that followed, three of the speakers were joined by the BRL’s Innovation Manager Jill Burnet, and there was some final advice on bringing imagination to market.

Researching and manufacturing robotics can be hugely expensive. Dyson spent  £28m on research for the 360 Eye, and manufacturing ran into eight figures, said Mike Aldred. But although this amount of investment is a barrier to many SMEs, Jill Burnet pointed out that incubators, such as the one at BRL, can tackle niche market problems.

Champion’s advice was to identify the core of the product, which might lead you to rethink your manufacturing. If it’s not linked to manufacturing, the SME should sub-contract.

And their top advice?

Mike Aldred: The best person to follow your idea is you. Own your own idea.

Jill Burnet: Find a community to work in, with like minded people, as we’ve done at BRL.

Renaud Champion: It’s a matter of having an idea, but the difference is in having and implementing. You don’t have to the go to the US to develop, Europe is a great place to start your business.

Graham Deacon: The companies I know that continue have passion – so it’s about sticking to it.

Check out the first videos below and stay tuned for the rest of the series. You can also read about all the approved projects here.

Flourish
Title: Aerial Data Collection and Analysis, and Automated Ground Intervention for Precision Farming
Duration (months): 42
Presenter: Roland Siegwart, ETHZ
Partners: Eidgenoessische Technische Hochschule Zurich, CH | Rheinische Friedrich-Wilhelms-Universitat Bonn, DE | Albert-ludwigs-universitaet Freiburg, DE | Robert Bosch Gmbh, DE | Centre National De La Recherche Scientifique, FR | Universita Degli Studi Di Roma La Sapienza, IT | Agenzia Servizi Settore Agroalimentare Delle Marche, IT

Centauro
Title: Robust Mobility and Dexterous Manipulation in Disaster Response by Fullbody Telepresence in a Centaur-like Robot
Duration (months): 42
Presenter: Sven Behnke, Rheinische Friedrich-Wilhelms-Universitat Bonn, DE
Partners: Rheinische Friedrich-Wilhelms-Universitat Bonn, DE | Fondazione Istituto Italiano Di Tecnologia, IT | Scuola Superiore Di Studi Universitari E, IT | Perfezionamento Sant’anna, IT | Kungliga Tekniska Hoegskolan, SE | Linkopings Universitet, SE | Rheinisch-westfaelische Technische Hochschule Aachen, DE | Progenox Gmbh De, DE | Kerntechnische Hilfsdienst Gmbh, DE

AEROWORKS
Title: Collaborative Aerial Robotic Workers
Duration (months): 36
Presenter: Margarita Chli, University of Edinburgh, UK, Kostas Alexis, ETHZ, CH
Partners: Lulea Tekniska Universitet, SE | Eidgenoessische Technische Hochschule Zurich, CH | Kungliga Tekniska Hoegskolan, SE | Universiteit Twente, NL | The University Of Edinburgh, UK |University Of Patras, EL |Ascending Technologies Gmbh, DE | Skybotix Ag, CH |Alstom Inspection Robotics Ag, CH | Skelleftea Kraft Ab, SE

CogIMon
Title: Cognitive Interaction in Motion
Duration (months): 48
Presenter: Jochen Steil, University of Bielefeld, DE
Partners: Universitaet Bielefeld, DE | Ecole Polytechnique Federale De Lausanne, CH | Fondazione Istituto Italiano Di Tecnologia, IT | The University Of Birmingham, UK | Fondazione Santa Lucia, IT | Imperial College Of Science, Technology And Medicine, UK | Eberhard Karls Universitaet Tuebingen, DE

Smokebot
Title: Mobile Robots with Novel Environmental Sensors for Inspection of Disaster Sites with Low Visibility
Duration (months): 42
Presenter: Achim Lilienthal, Orebro University, SE
Partners: Orebro University, SE | Gottfried Wilhelm Leibniz Universitaet Hannover, DE | Fraunhofer-gesellschaft Zur Foerderung, DE | Angewandten Forschung E.v, DE | The University Of Warwick, UK | Taurob Gmbh, AT | Stadt Dortmund, DE

Flourish, which has been funded at just over €3.5 Million for 42 months, will be managed by Cyrill Stachniss of the University of Bonn, Germany. It is described both in the H2020 document and on the university’s website as follows:

To feed a growing world population with the given amount of available farm land, we must develop new methods of sustainable farming that increase yield while reducing reliance on herbicides and pesticides. Precision agricultural techniques seek to address this challenge by monitoring key indicators of crop health and targeting treatment only to plants that need it. This is a time consuming and expensive activity and while there has been great progress on autonomous farm robots, most systems have been developed to solve only specialized tasks. This lack of flexibility poses a high risk of no return on investment for farmers. The goal of the Flourish project is to bridge the gap between the current and desired capabilities of agricultural robots by developing an adaptable robotic solution for precision farming. By combining the aerial survey capabilities of a small autonomous multi-copter Unmanned Aerial Vehicle (UAV) with a multi-purpose agricultural Unmanned Ground Vehicle, the system will be able to survey a field from the air, perform targeted intervention on the ground, and provide detailed information for decision support, all with minimal user intervention. The system can be adapted to a wide range of crops by choosing different sensors and ground treatment packages. This development requires improvements in technological abilities for safe accurate navigation within farms, coordinated multi-robot mission planning that enables large field survey even with short UAV flight times, multispectral three-dimensional mapping with high temporal and spatial resolution, ground intervention tools and techniques, data analysis tools for crop monitoring and weed detection, and user interface design to support agricultural decision making. As these aspects are addressed in Flourish, the project will unlock new prospects for commercial agricultural robotics in the near future.

SWEEPER, which has been funded at just over €4 Million for 36 months, will be managed by Jan Bontsema of Wageningen UR, Netherlands. It is described in the H2020 document as follows:

In modern greenhouses there is a high demand to automate labour. The availability of a skilled workforce that accepts repetitive tasks in the harsh climate conditions of a greenhouse is decreasing rapidly. The resulting increase in labour costs and reduced capacity puts major pressure on the competitiveness of the European greenhouse sector. Present robotization of this labour has entered a high level of technological readiness. However, a gap remains which halts the transition from science to economic and societal impact; the so called ‘Technological Innovation Gap’. In the EU-FP7-project CROPS, extensive research has been performed on agricultural robotics. One of the applications was a sweet pepper harvesting robot. It was shown that such a robot is economically and technically viable. The proven hardware and software modules (TRL: 6) developed in CROPS will be used as the groundwork. The successful CROPS software modules based on the Robotic-Operating-System (ROS) will be maintained and expanded in SWEEPER. Also the gripper end-effector will be retained. This patent pending module is able to grasp the sweet pepper without the need of an accurate measurement of the position and orientation of the fruit. In several experiments, it turned out that different growers use different cropping systems ranging in crop density. In SWEEPER, the cropping system itself will be optimized to facilitate robotic harvesting. In CROPS it was concluded that instead of a 9DOF, a 4DOF robot arm is sufficient, greatly reducing costs. To improve the level of robotic cognitive abilities, plant models will be applied to approximate location of sweet peppers. This “model-based vision” will increase and speed up fruit detection. Based on the insights of CROPS, sensors will be placed onto the gripper only. Also a LightField sensor will be introduced, which is able to record both colour and 3D information simultaneously.

The “CROPS” referred to above is Clever Robots for Crops, a program of the 7th Framework, which preceded H2020.

The first H2020 call for proposals was issued last year as a follow up to the EU’s Seventh Framework Programme for Research (FP7), and includes over 100 collaborative robotics projects under the Digital Agenda framework. To learn more about the other robotics projects funded under H2020, see this post by Frank Tobe.

A downside, however, is that European Commission President Jean-Claude Juncker recently proposed shifting the overall Horizon 2020 program to reduce the research aspect and use the saved funds to pay for general economic stimulus. The results of his push are, at present, unknown.

Here are the 17 robotics-related projects, whose funding was started in 2014 and will continue to 2018:

• AEROARMS – developing an aerial robotic system with multiple arms and advanced manipulation capabilities for application in industrial inspection and maintenance. Corporate partners: Elektra UAS, Alstom Inspection, Sensima Inspection.
• AEROWORKS – developing an aerial robotic team to autonomously conduct infrastructure inspection and maintenance tasks, while additionally providing intuitive and user-friendly interfaces to human-operators. Corporate partners: Ascending Technologies, Skybotix, Alstom Inspection, Skelleftea Kraft.
• COMANOID – investigates the deployment of robotic solutions in well-identified Airbus airliner assembly operations that are laborious or tedious for human workers and for which access is impossible for wheeled or rail-ported robotic platforms. Corporate partners: European Aeronautic Defence & Space (EADS).
• CENTAURO – developing a human-robot symbiotic system, where a human operator is tele-present with its whole body in a Centaur-like robot, which is capable of robust locomotion and dexterous manipulation in the rough terrains of various disaster situations. Corporate partners: ProgenoX, Kermtechnische Hilfsdienst.
• CogIMon – This Cognitive Interactive in Motion research aims at human-robot interaction with systemic integration of teams of humans and compliant robots. Corporate partners: none.
• EurEyeCase – Large numbers of patients suffer from various types of vitreo-retinal eye diseases and the majority of these intra−ocular interventions lie on or even beyond the boundaries of human skills in terms of manipulation and positioning precision. Hence the need for robotic technology to augment surgeons’ skills. Corporate partners: Medical Robotic Technologies, ACMIT, Optomedical Technologies, Medizinisches Laserzentrum Lubeck.
• FLOBOT – developing a floor washing robot for professional users. The project integrates existing solutions to produce a professional floor washing robot for a wide area of industrial, civil and commercial premises. Corporate partners: FIMAP, Robosoft Services, 7 Manutencoop Facility Management, Groupe Services France.
• Flourish – to bridge the gap between the current and desired capabilities of agricultural robots by developing an adaptable robotic solution for precision farming. The system will be able to survey a field from the air, perform targeted intervention on the ground, and provide detailed information for decision support. Corporate partners: Robert Bosch, Agenzia Servizi Settore Agroalimentare delle Marche.
• RETRAINER – to tune and validate advanced robot-based technologies to facilitate recovery of arm and hand function in stroke survivors. Will allow the users to use their own arm and hand as much and as soon as possible after the trauma so to achieve the best outcomes in rehabilitation. Corporate partners: Robert Bosch, Agenzia Servizi Settore Agroalimentare delle Marche. 
• RobDREAM – improve industrial mobile manipulators’ perception, navigation, manipulation and grasping capabilities by automatic optimization of parameters, strategies and selection of tools within a portfolio of key algorithms. Corporate partners: KUKA, Convergent Information Technologies.
• RoMaNS – This (Robotic Manipulation for Nuclear Sort and Segregation) project will solve an urgent market and societal need cleaning up the past half century of nuclear waste. Corporate partners: National Nuclear Lab.
• SARAFun – a project to enable a non-expert user to train/integrate a new bi-manual assembly task on an ABB YuMi robot in less than a day. The robot will be equipped with sensory and cognitive abilities as well as reasoning abilities required to plan and execute any assembly task in a human like manner. Corporate partners: ABB.
• SecondHands – a robot assistant that is trained to understand maintenance tasks so that it can either pro-actively or as a result of prompting, offer assistance to maintenance technicians performing routine and preventative maintenance. Corporate partners: OCADO Group.
• Smokebot – a project to develop and equip mobile robots with novel environmental sensors for inspection of disaster sites with low visibility. Corporate partners: Taurob GmbH.
• SoMa – a plan to provide soft, uncertain interactions between robotic manipulation and the environment. Corporate partners: OCADO Group and The Walt Disney Company.
• Sweeper – using modules from the FP7 CROPS project, this new project is to detect, grasp and harvest sweet peppers under various growing situations. Corporate partners: de Tuindershoek, Irmato Group.
• WiMUST – a Widely scalable Mobile Underwater Sonar Technology project to expand and improve the functionalities of current cooperative marine robotic systems, effectively enabling distributed acoustic array technologies for geophysical surveying with a view to exploration and geotechnical surveying for civil and commercial applications. Corporate partners: Graal Tech, Evo Logics, CGG Veritas Services, Geo Marine Survey Systems, GeoSurveys.

If you liked this article, you may also be interested in:

• Japan’s new robotics push: Funding and deregulation
• National Science Foundation and federal partners award $31.5M to advance co-robots in US
• Governmental funding of strategic robotic projects
• China takes long view in funding robotics, innovation
• South Korean private-public partnership to invest $2.6B in robot industry by 2018

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.