Learning quadrupedal locomotion over challenging terrain

Cited 420 time in webofscience Cited 170 time in scopus
  • Hit : 634
  • Download : 173
Legged locomotion can extend the operational domain of robots to some of the most challenging environments on Earth. However, conventional controllers for legged locomotion are based on elaborate state machines that explicitly trigger the execution of motion primitives and reflexes. These designs have increased in complexity but fallen short of the generality and robustness of animal locomotion. Here, we present a robust controller for blind quadrupedal locomotion in challenging natural environments. Our approach incorporates proprioceptive feedback in locomotion control and demonstrates zero-shot generalization from simulation to natural environments. The controller is trained by reinforcement learning in simulation. The controller is driven by a neural network policy that acts on a stream of proprioceptive signals. The controller retains its robustness under conditions that were never encountered during training: deformable terrains such as mud and snow, dynamic footholds such as rubble, and overground impediments such as thick vegetation and gushing water. The presented work indicates that robust locomotion in natural environments can be achieved by training in simple domains.
Publisher
AMER ASSOC ADVANCEMENT SCIENCE
Issue Date
2020-10
Language
English
Article Type
Article
Citation

SCIENCE ROBOTICS, v.5, no.47

ISSN
2470-9476
DOI
10.1126/scirobotics.abc5986
URI
http://hdl.handle.net/10203/278216
Appears in Collection
ME-Journal Papers(저널논문)
Files in This Item
000581106800002.pdf(2.5 MB)Download
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 420 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0