Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: We introduce SoftMimic, a framework for learning compliant whole-body control
policies for humanoid robots from example motions. Imitating human motions with
reinforcement learning allows humanoids to quickly learn new skills, but
existing methods incentivize stiff control that aggressively corrects
deviations from a reference motion, leading to brittle and unsafe behavior when
the robot encounters unexpected contacts. In contrast, SoftMimic enables robots
to respond compliantly to external forces while maintaining balance and
posture. Our approach leverages an inverse kinematics solver to generate an
augmented dataset of feasible compliant motions, which we use to train a
reinforcement learning policy. By rewarding the policy for matching compliant
responses rather than rigidly tracking the reference motion, SoftMimic learns
to absorb disturbances and generalize to varied tasks from a single motion
clip. We validate our method through simulations and real-world experiments,
demonstrating safe and effective interaction with the environment.
Authors (4)
Gabriel B. Margolis
Michelle Wang
Nolan Fey
Pulkit Agrawal
Submitted
October 20, 2025
Key Contributions
Introduces SoftMimic, a framework for learning compliant whole-body control policies for humanoid robots from example motions. It uses an inverse kinematics solver to generate augmented data, enabling RL policies to learn compliant responses to external forces while maintaining balance, leading to safer and more robust behavior than rigid imitation methods.
Business Value
Enables the development of safer, more adaptable humanoid robots capable of interacting with complex, unpredictable environments, crucial for applications in logistics, manufacturing, and assistance.