analiza aiqbench
This research introduces a contact-implicit multiple shooting framework that embeds differentiable simulators directly into nonlinear programs to generate dynamically feasible whole-body trajectories. By resolving friction, impacts, and joint limits internally without explicit contact schedules, the method significantly accelerates reinforcement learning training for complex robotic behaviors like dynamic jumping and crawling on Unitree G1 robots. The approach demonstrates successful zero-shot transfer from simulation to reality, addressing a critical bottleneck in deploying AI policies for physically grounded agents.
Shooting for Contact: Contact-Implicit Multiple Shooting for Dynamic Motion Retargeting
arXiv:2608.03116v1 Announce Type: new Abstract: Motion retargeting approaches often prioritize kinematic similarity over whole-body dynamics, contact consistency, and actuation limits, yielding references that are difficult for reinforcement learning (RL) policies to reproduce, particularly for contact-rich behaviors. We present a contact-implicit, direct simulation-based multiple shooting (DSMS) framework that transforms kinematically feasible references into dynamically feasible whole-body trajectories. By embedding a differentiable simulator within a nonlinear program, DSMS resolves contact, friction, impacts, self-collision, and joint limits internally while enforcing tracking, actuation, and task constraints without prescribing a contact schedule or introducing explicit contact constraints. Compared with existing retargeting methods, DSMS accelerates motion-imitation RL training and yields policies with high success rates and low tracking error. We further demonstrate zero-shot sim-to-real transfer on the Unitree G1 through command-conditioned contact-rich crawling and a highly dynamic 180-degree jump-turn.
Abstract:Motion retargeting approaches often prioritize kinematic similarity over whole-body dynamics, contact consistency, and actuation limits, yielding references that are difficult for reinforcement learning (RL) policies to reproduce, particularly for contact-rich behaviors. We present a contact-implicit, direct simulation-based multiple shooting (DSMS) framework that transforms kinematically feasible references into dynamically feasible whole-body trajectories. By embedding a differentiable simulator within a nonlinear program, DSMS resolves contact, friction, impacts, self-collision, and joint limits internally while enforcing tracking, actuation, and task constraints without prescribing a contact schedule or introducing explicit contact constraints. Compared with existing retargeting methods, DSMS accelerates motion-imitation RL training and yields policies with high success rates and low tracking error. We further demonstrate zero-shot sim-to-real transfer on the Unitree G1 through command-conditioned contact-rich crawling and a highly dynamic 180-degree jump-turn.
Robotics (cs.RO); Systems and Control (eess.SY)
arXiv:2608.03116 [cs.RO]
(or arXiv:2608.03116v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.03116 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 225 cuvinte
Subiecte conexe
The State of Simulation for Physical AI: An Overview
Hugging Face · 21 iul. 2026
Task-Space Motion-Force Nonlinear Model Predictive Control for Precise and Compliant Control under Uncertainties
arXiv · 14 oct. 2026
ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids
arXiv · 15 sept. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026