news    views    podcast    learn    |    about    contribute     republish    

Fabio Bonsignorio



Fabio Bonsignorio is currently a Professor at the Biorobotics Institute of the Scuola Superiore Sant’Anna in Pisa. He has been professor in the Department of System Engineering and Automation of the University Carlos III of Madrid until 2014. In 2009 he was awarded the Santander Chair of Excellence in Robotics at the same university. He is founder and CEO of Heron Robots (advanced robotic solutions), see www.heronrobots.com. He has been working in the R&D departments of several major Italian and American companies for more than 20 years. He is a Founding Director of euRobotics aisbl, the private part of SPARC, the Eu Robotics PPP. He is currently a member of the Research Board of Directors of SPARC. He coordinated and has been the main teacher of the ShanghAI Lectures 2013, 2014, 2015 (www.shanghailectures.org), edition an advanced network MOOC teaching initiated several years ago by Rolf Pfeifer. He is currently coordinating the 2016 edition. His preferred research topics are in advanced robotics: cognition, control, modeling, software architectures, epistemological issues in robotics, performance evaluation and foundational issues like ’morphological computation’. He has pioneered and introduced the topic of Reproducible Research and Benchmarking in Robotics and AI, where is one of the leading experts. He is an Associate Editor of the IEEE Robotics and Automation Magazine. He is author or co-author of about 140 publications in the areas of robotics, cognition and manufacturing systems in the last few years since he became an almost full-time researcher. He coordinated the EURON Special Interest Group on Good Experimental Methodology and Benchmarking in Robotics, is cochair of the IEEE RAS TC-Pebras and has been a board member of EURON III. He is a member of the Euron Training Board (the GeorgeGiralt PhD Award jury). He has been reviewer for several conferences and journals inside and outside IEEE. He is project reviewer for Ecsel and has been for FP7. He was a member of the joint Europ-Euron-other experts restricted team preparing the Robotics Public Private Partnership in Horizon 2020, the successor program at EU level of FP7. He contributed together with other 9 leading European experts in robotics to the Echord report on the state of robotics in USA and Asia. He is the coordinator of the euRobotics Topic Group on Experiment Replication, Benchmarking, Challenges and Competitions and is co-chair of the IEEE TC-Pebras. He has participated to design and launch the new euCognition society, he is now a member of the euCogniton society steering commitee. He has been publication chair in the 2014 IEEE RAS Humanoids 2014 conference. He has been general co-chair of the IEEE RAS 2015 Summer School on Replicable and Measurable Robotics Research. He has been the corresponding and more active editor of the Special Issue on Replicable and Measurable Robotics Research on IEEE Robotics and Automation Magazine, appeared in September 2015. This special issue is the very first example of a higher impact archival robotics journal issue with replicable and measurable results pioneering Reproducible Research in RAS and to a certain extent IEEE at large.



As highlighted in a previous post, despite the fact that robotics is increasingly regarded as a ‘Science’, as shown by the launch of new journals such as Science Robotics, reproducibility of experiments is still difficult or entirely lacking.

by   -   February 20, 2017

Fabio Bonsignorio discusses how perception of robotics, reproducibility and measureable research still presents issues for the robotics community.

by   -   September 30, 2016

robot-and-scientist

In general, as any robotics and/or AI PhD student knows very well, replicating the research results of other labs is quite difficult. The information you can customary find in a reputed journal paper is usually not enough to reproduce the experimental results claimed by the authors, let alone to make comparisons of the strengths and weaknesses of the different methods proposed in the literature in term of performances.

This week we publish the tenth and last of the ShanghAI Lectures 2013 Edition on Robohub. We have been releasing  a new lecture from this series on Monday for several weeks and this is the last one. Please use the comments section below to send us your questions, and we will do our best to respond! You can learn more about the ShanghAI lectures here. Stay tuned for the 2014 Edition! And more later…on RoboHub!

Lecture09SlidesFabsShEyesjpg

Lecture 9: Towards a theory of intelligence

This lecture, which I hosted at the the University Carlos III (Madrid, Spain), suggests principles and design guidelines for the development of embodied intelligent systems that are more similar to animal-like intelligence than what has been proposed so far. How to build a self-organizing embodied intelligence?

Lecture 8-II: Education and Industry Session

This lecture hosted by Prof. Samia Nefti-Meziani from the University of Salford, Manchester, UK, is about higher education and industrial impact of the ‘ShanghAI paradigm’. You should not be surprised to see early glimpses of the next industrial revolution enabled by intelligent machines in Manchester – this was the iconic example of industrial city during the very first industrial revolution.

“ITN Marie Curie Network SMART-E: Advanced Robotics for Sustainable Manufacturing in Europe” by  Samia Nefti-Meziani

Lecture 8-I: Ontogenetic development: From locomotion to cognition

8ILecture08SlidesFabVS

In this lecture, hosted at the University Carlos III of Madrid in Spain, I show how it is possible to ground ‘understanding’ on data streams coming from the physical interaction of an agent in the environment, and discuss the many open issues that remain. For example, setting information theory in an embodied framework is challenging, but the road ahead looks promising. So, what’s the link between locomotion to cognition? Is there one?

by   -   March 3, 2014

This week we publish the seventh of the ShanghAI Lectures 2013 Edition on Robohub. You can learn more about the ShanghAI lectures here.

Lecture 7 – Design principles of intelligent systems

Lecture07SlidesFabShortsucfailjpgThis lecture, which I hosted at the University Carlos III of Madrid, Spain, looks at the foundational issues and the successes and failures of AI from a critical perspective.

by   -   February 24, 2014

Lecture 6 – Soft Robotics and Bioinspiration II

In this second lecture hosted by the Scuola Superiore S. Anna, Matteo Cianchetti builds on the previous lecture to talk about building soft actuators for soft robots. In Matteo’s lecture, titled “Soft actuator design methods“,  he explains that the devil is in the details, but that it’s possible to build soft actuators by insightfully exploiting the properties of Shape Memory Alloy (SMA). Want to learn how?

by   -   February 17, 2014

Lecture 5 – Soft Robotics and Bioinspiration I

Hosted by Prof. Cecilia Laschi from the Scuola Superiore S. Anna in Pisa, Italy, this ShanghAI episode puts together contrasting approaches to ‘embodied intelligence’ and ‘embodied cognition’ in her lecture titled How an octopus can help build a robot”.

This week we publish the fourth of the ShanghAI Lectures 2013 Edition on Robohub — we will release a new lecture from this series every Monday until the series is complete. Please use the comments section below to send us your questions, and we will do our best to respond! You can learn more about the ShanghAI lectures here.

Lecture 4 – Evolution: Cognition from scratch

EvoTimeScales

If you believe that it’s too difficult to develop the mathematical models required to arrive at a new concept of embodied AI and robotics, this lecture will offer you hope. In her talk, Prof. Verena Hafner, from Humboldt University in Berlin, discusses the concept of ‘body maps’ from an embodied intelligence perspective, and shows how they can emerge from sensorimotor flow, through information distances in the data flow and/or an internal simulation.

This week we publish the third of the ShanghAI Lectures 2013 Edition on Robohub — we will release a new lecture from this series every Monday until the series is complete. Please use the comments section below to send us your questions, and we will do our best to respond! You can learn more about the ShanghAI lectures here.

Lecture 3 – Cognition and embodiment – Language learning in children and robots: A developmental robotics approach 

This week’s lecture discusses an important problem: how ‘symbols’ and language emerge and are ‘grounded’ from the flow of sensory-motor data. In this lecture, Angelo Cangelosi, Director of the Centre for Robotics and Neural Systems at the University of Plymouth, explains the developmental approach to robotics (and psychology) and offers a remarkable example of ‘synthetic methodology’  for the study of children’s intellectual development.  Cangelosi, who’s original background is in psychology, is a leading researcher in developmental robotics.

by   -   January 21, 2014

ShanghAIGlobeColorThis week we publish the second of the ShanghAI Lectures 2013 Edition on Robohub — we will release a new lecture from this series every Monday until the series is complete. Please use the comments section below to send us your questions, and we will do our best to respond! You can learn more about the ShanghAI lectures here.

Lecture 2 – Embodied Intelligence

“Evolution embodies information in every part of every organism. This information doesn’t have to be copied into the brain at all. It doesn’t have to be “represented” in “data structures” in the nervous system. It can be exploited by the nervous system, however, which is designed to rely on, or exploit, the information in the hormonal systems just as it is designed to rely on, or exploit, the information embodied in your limbs and eyes.” – D.Dennett, Kind of Minds, 1996

by   -   January 13, 2014

ShanghAIGlobeColor

This week marks the launch of the ShanghAI Lectures 2013 Edition on Robohub — we will release a new lecture from this series every Monday until the series is complete. Please use the comments section below to send us your questions, and we will do our best to respond! You can learn more about the ShanghAI lectures here.

Lecture 1 – Intelligence: Things can be seen differently

If you are not interested in precisely predicting the motion of a handful of ‘anomalous’ stars (nowadays known as planets), then there is no reason to assume that the earth is not sitting at the center of the universe. Ptolemaic astronomy was good astronomy, after all. And if you were an astronomer of the XVI century you may have had good reason to think that ‘solving astronomy’ was simply a matter of adding the ‘right’ epicycles ;-). Many did. Why worry about just five stars that do not model correctly when there are several thousand stars that are perfectly predictable?

by   -   December 18, 2013

ShanghAIGlobeColorIf you have been following the ShanghAI Lectures, you will not want to miss the live webcast of the final 2013 lecture this Thursday starting at 9:30 CET. Rolf Pfeifer (University of Zurich) will explain why a mind needs a body, Manuela Veloso (Carnegie Mellon University) will explain how humans may help robots for mutual benefit, and W. Chen, Shanghai Jiao Tong, Vincent Mueller (ATC and University of Oxford), Rolf Pfeifer, Manuela Veloso  and Vera Zabotkina (Russian State University for the Humanities) will discuss if embodiment is really a must for AI and the future of education on natural and artificial intelligence (we think you should study them together, actually).

In the next coming weeks we will release all the lectures of the 2013 Edition, including remarks and insights. Don’t miss them!

Watch Thursday’s live stream here …