A survey on embedding physics priors in robot learning, covering how physical constraints like contact mechanics, rigid-flexible coupling, and multibody dynamics improve sample efficiency and reliability of learned policies.
See LICENSE filerobot learningphysics priorsmultibody dynamics
Proposes AffordanceWAM, an affordance-aware generative World Action Model that leverages both action-labeled robot videos and egocentric human videos for generalizable robot manipulation.
See LICENSE filerobot manipulationaffordance learningworld model
This paper investigates physical diagnosis for robots facing unfamiliar conditions, defining six ordered empirical conditions required for behavior improvement, and validates the chain in controlled and public environments.
See LICENSE filerobot diagnosisphysical adaptationtest-time inference
ForceTwin learns joint physical properties including inertia, friction, and spring mechanisms from human interaction data to build physics-informed digital twins that predict robotic manipulation actions.
See LICENSE filedigital twinrobotic manipulationphysics-informed
A robot arm manipulation dataset collected using the LeRobot framework, containing 51 episodes and 29803 frames of video data for robot manipulation policy learning.
