GRASP: Gradient-Guided Sampling for Contact-Rich Physics-Based Motion Retargeting
cs.RO
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/google-deepmind/mujoco_warp
Project page: https://computationalrobotics.seas.harvard.edu/GRASP
Terminology
Sources
- Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking
- HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos
- On the Convergence of Adaptive Sequential Monte Carlo Methods
- Expressive Whole-Body Control for Humanoid Robots
- Accelerating Asymptotically Exact MCMC for Computationally Intensive Models via Local Approximations
- DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization
- Shooting for Contact: Contact-Implicit Multiple Shooting for Dynamic Motion Retargeting
- Towards Tight Convex Relaxations for Contact-Rich Manipulation
- Robust Motion In-betweening
- Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation
- ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
- Stein Variational Guided Model Predictive Path Integral Control: Proposal and Experiments with Fast Maneuvering Vehicles
- Global Contact-Rich Planning with Sparsity-Rich Semidefinite Relaxations
- Object Motion Guided Human Motion Synthesis
- AMASS: Archive of Motion Capture as Surface Shapes
- Do as I Do: Dexterous Manipulation Data from Everyday Human Videos
- SPIDER: Scalable Physics-Informed Dexterous Retargeting
- DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
- Bundled Gradients through Contact via Randomized Smoothing
- Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation