Adding a physical feasibility reward derived from inverse kinematics to a unified whole-body RL policy improves loco-manipulation accuracy and prevents the policy from abandoning arm coordination during locomotion training.
Versatile multicontact planning and control for legged loco-manipulation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Efficient Learning of A Unified Policy For Whole-body Manipulation and Locomotion Skills
Adding a physical feasibility reward derived from inverse kinematics to a unified whole-body RL policy improves loco-manipulation accuracy and prevents the policy from abandoning arm coordination during locomotion training.