REVIEW 3 cited by
Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots. Our approach builds upon previous work on imitating human or dog Motion Capture (MoCap) data to learn a movement skill module. Once learned, this skill module can be reused for complex downstream tasks. Importantly, due to the prior imposed by the MoCap data, our approach does not require extensive reward engineering to produce sensible and natural looking behavior at the time of reuse. This makes it easy to create well-regularized, task-oriented controllers that are suitable for deployment on real robots. We demonstrate how our skill module can be used for imitation, and train controllable walking and ball dribbling policies for both the ANYmal quadruped and OP3 humanoid. These policies are then deployed on hardware via zero-shot simulation-to-reality transfer. Accompanying videos are available at https://bit.ly/robot-npmp.
Forward citations
Cited by 3 Pith papers
-
Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
A single onboard policy trained with 2D trajectory-optimization priors, transformer latent actions, and reinforcement learning enables a quadruped to autonomously select gaits and traverse unstructured terrain at up to 6 m/s.
-
Phase-Based Multi-Gait Learning for a Salamander-Like Robot
A phase-velocity RL controller with a coverage reward and symmetry augmentation lets a salamander-type robot acquire 22 omnidirectional gaits — including lateral, diagonal, and in-place rotation — without reference motions.
-
The embodied brain: Bridging the brain, body, and behavior with biorealistic neuromechanical models
Neuromechanical digital twins—simulated bodies with artificial neural controllers—are maturing into tools that can infer unmeasurable physiological variables, test hypotheses, and link neuroscience with robotics and r...
Discussion (0). Continue with ORCID to comment.