Event
DSMS: Contact-Implicit Multiple Shooting for Dynamic Motion Retargeting
1 reports · 1 sources
Sergio A. Esteban and co-authors propose DSMS, a contact-implicit, direct-simulation-based multiple shooting framework that converts kinematically feasible reference motions into dynamically feasible whole-body trajectories. The framework embeds a differentiable simulator into a nonlinear program, handling contact, friction, collisions, and joint limits internally, without requiring pre-specified contact timing or the introduction of explicit contact constraints. The authors report that, compared with existing retargeting methods, DSMS accelerates motion-imitation reinforcement learning training, yielding policies with high success rates and low tracking error; and on the Unitree G1 it achieves zero-shot sim-to-real transfer, completing commanded walking, jogging, contact-rich crawling, and a 180-degree jumping turn.
Report timeline
- DSMS: Contact-Implicit Multiple Shooting for Dynamic Motion Retargeting
The study proposes DSMS, a contact-implicit, direct-simulation-based multiple shooting framework that converts kinematically feasible reference motions into dynamically feasible whole-body trajectories. It handles contact, friction, collision, and joint limits within a nonlinear program without presetting a contact schedule. Compared with existing retargeting methods, DSMS accelerates motion-imitation reinforcement learning training and yields policies with high success rates and low tracking error. The authors achieved zero-shot sim-to-real transfer on the Unitree G1, completing walking, jogging, contact-rich crawling, and a 180-degree jump-turn.
arXiv cs.RO ·