REVIEW 2 cited by
Learning Multiple Gaits within Latent Space for Quadruped Robots
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
Learning multiple gaits is non-trivial for legged robots, especially when encountering different terrains and velocity commands. In this work, we present an end-to-end training framework for learning multiple gaits for quadruped robots, tailored to the needs of robust locomotion, agile locomotion, and user's commands. A latent space is constructed concurrently by a gait encoder and a gait generator, which helps the agent to reuse multiple gait skills to achieve adaptive gait behaviors. To learn natural behaviors for multiple gaits, we design gait-dependent rewards that are constructed explicitly from gait parameters and implicitly from conditional adversarial motion priors (CAMP). We demonstrate such multiple gaits control on a quadruped robot Go1 with only proprioceptive sensors.
Forward citations
Cited by 2 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.
-
Integrating Diffusion-based Multi-task Learning with Online Reinforcement Learning for Robust Quadruped Robot Control
A diffusion policy pretrained on offline gait data and then finetuned with PPO achieves robust language-conditioned quadruped control with 50 Hz onboard inference.
Discussion (0). Continue with ORCID to comment.