Robohub.org
 

Autonomous exploration planning using aerial robots

by and
23 May 2016



share this:
aerial-robot-robotics

Autonomous exploration of unknown environments corresponds to a critical ability and a major challenge for aerial robots. In many cases, we would like to rely on the ability of an intelligent flying system to completely and efficiently explore the previously unknown world and derive a consistent map of it. On top of this basic skill, one can then work on several tasks such as infrastructure inspection, hazard detection, and more.

Source: Kostas Alexis, UNR

Source: Dr Kostas Alexis, UNR

Our algorithm “Receding Horizon Next-Best-View Path Planning” is a recent contribution towards enabling the key goal of autonomous exploration. It achieves this by sampling finite-depth candidate paths within the environment, selecting the one that maximizes the amount of new space to be explored, and executes only the first step while then repeating the whole process in a receding horizon fashion. By performing multiple iterative steps of this process the space is fully and efficiently explored, and a volumetric representation is derived. Finally, one can afterwards launch a second mission for higher-fidelity surface inspection and more accurate 3D reconstruction of the environment.

The algorithm has been experimentally verified with aerial robotic platforms equipped with a stereo visual-inertial system, as shown in our video:

Finally, to enable further developments, research collaboration and consistent comparison, we have released an open source version of our exploration planner, experimental datasets and interfaces to established simulation tools, including demo scenarios. To get the code, please visit: https://github.com/ethz-asl/nbvplanner/

This research was conducted at the Autonomous Systems Lab, ETH Zurich and the University of Nevada, Reno.


Reference:

  1. Bircher, M. Kamel, K. Alexis, H. Oleynikova, R. Siegwart, “Receding Horizon “Next-Best-View” Planner for 3D Exploration”, IEEE International Conference on Robotics and Automation 2016 (ICRA 2016), Stockholm, Sweden. Open-Source Git Repo: https://github.com/ethz-asl/nbvplanner


tags: , , , ,


Kostas Alexis is an assistant professor at Computer Science & Engineering of the University of Nevada, Reno
Kostas Alexis is an assistant professor at Computer Science & Engineering of the University of Nevada, Reno

Andreas Bircher is a research engineer at WingTra.
Andreas Bircher is a research engineer at WingTra.





Related posts :



Robot Talk Episode 55 – Sara Adela Abad Guaman

In the first episode of the new season, Claire chatted to Dr. Sara Adela Abad Guaman from University College London about adaptable robots inspired by nature.
30 September 2023, by

A short guide to Multidisciplinary Research

How and Why would I consider colliding two opposite disciplines in my research.
27 September 2023, by

Robo-Insight #5

In this fifth edition, we are excited to feature robot progress in human-robot interaction, agile movement, enhanced training methods, soft robotics, brain surgery, medical navigation, and ecological research. 
25 September 2023, by

Soft robotic tool provides new ‘eyes’ in endovascular surgery

The magnetic device can help visualise and navigate complex and narrow spaces.

‘Brainless’ robot can navigate complex obstacles

Researchers who created a soft robot that could navigate simple mazes without human or computer direction have now built on that work, creating a “brainless” soft robot that can navigate more complex and dynamic environments.
21 September 2023, by

Battery-free origami microfliers from UW researchers offer a new bio-inspired future of flying machines

Researchers at the University of Washington present battery-free microfliers that can change shape in mid-air to vary their dispersal distance.





©2021 - ROBOTS Association


 












©2021 - ROBOTS Association