Journal
IEEE ROBOTICS AND AUTOMATION LETTERS
Volume 5, Issue 2, Pages 3699-3706Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2020.2979660
Keywords
Planning; Foot; Legged locomotion; Optimization; Machine learning; Dynamics; Legged robots; deep learning in robotics and automation; motion and path planning
Categories
Funding
- Intel Labs
- Swiss National Science Foundation (SNSF) [166232, 188596]
- National Centre of Competence in Research Robotics (NCCR Robotics)
- European Union's Horizon 2020 research and innovation program [780883]
- ANYmal Research, a community to advance legged robotics
Ask authors/readers for more resources
This letter addresses the problem of legged locomotion in non-flat terrain. As legged robots such as quadrupeds are to be deployed in terrains with geometries which are difficult to model and predict, the need arises to equip them with the capability to generalize well to unforeseen situations. In this work, we propose a novel technique for training neural-network policies for terrain-aware locomotion, which combines state-of-the-art methods for model-based motion planning and reinforcement learning. Our approach is centered on formulating Markov decision processes using the evaluation of dynamic feasibility criteria in place of physical simulation. We thus employ policy-gradient methods to independently train policies which respectively plan and execute foothold and base motions in 3D environments using both proprioceptive and exteroceptive measurements. We apply our method within a challenging suite of simulated terrain scenarios which contain features such as narrow bridges, gaps and stepping-stones, and train policies which succeed in locomoting effectively in all cases.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available