Global Sampling-Based Trajectory Optimization for Contact-Rich Manipulation via KernelSOS

2026-04-29 · Zhongqi Wei, Frederike Dümbgen arxiv

Contact-rich manipulation is challenging due to its high dimensionality, the requirement for long time horizons, and the presence of hybrid contact dynamics. Sampling-based methods have become a popular approach for this class of problems, but without explicit mechanisms for global exploration, they are susceptible to converging to poor local minima. In this paper, we introduce Global-MPPI, a unified trajectory optimization framework that integrates global exploration and local refinement. At the global level, we leverage kernel sum-of-squares optimization to identify globally promising regions of the solution space. To enable reliable performance for the non-smooth landscapes inherent to contact-rich manipulation, we introduce a graduated non-convexity strategy based on log-sum-exp smoothing, which transitions the optimization landscape from a smoothed surrogate to the original non-smooth objective. Finally, we employ the model-predictive path integral method to locally refine the solution. We evaluate Global-MPPI on high-dimensional, long-horizon contact-rich tasks, including the PushT task and dexterous in-hand manipulation. Experimental results demonstrate that our approach robustly uncovers high-quality solutions, achieving faster convergence and lower final costs compared to existing baseline methods.

📄 PDF Abstract BibTeX arXiv:2604.27175

Code (0)

등록된 구현이 없습니다.

Assembly robots with optimized control stiffness through reinforcement learning

2020-02-27 · Masahide Oikawa, Kyo Kutsuzawa, Sho Sakaino, Toshiaki Tsuji

There is an increased demand for task automation in robots. Contact-rich tasks, wherein multiple contact transitions occur in a series of operations, are extensively being studied to realize high accuracy. In this study,…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Trajectory Planning

Real-World Deployment of Massively Parallel Sampling-Based MPC for Contact-Rich Manipulation

2026-06-16 · Magnus Dierking, Joao Carvalho, An Thai Le, Georgia Chalvatzaki 외 arxiv

Sampling-based Model Predictive Control (SMPC) is a promising strategy for contact-rich robotic manipulation, combining gradient-free optimization with massively parallel GPU simulation. Yet, most prior work relies on si…

IMPACT: An Implicit Active-Set Augmented Lagrangian for Fast Contact-Implicit Trajectory Optimization

2026-05-09 · Jiayun Li, Dejian Gong, Georgia Chalvatzaki arxiv

Contact-implicit trajectory optimization (CITO) has attracted growing attention as a unified framework for planning and control in contact-rich robotic tasks. Recent approaches have demonstrated promising results in mani…

Diffusing Trajectory Optimization Problems for Recovery During Multi-Finger Manipulation

2025-10-08 · Abhinav Kumar, Fan Yang, Sergio Aguilera Marinovic, Soshi Iba 외 arxiv

Multi-fingered hands are emerging as powerful platforms for performing fine manipulation tasks, including tool use. However, environmental perturbations or execution errors can impede task performance, motivating the use…

Out-of-Distribution Detection Reinforcement Learning

FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation

2026-07-30 · Lifeng Zhuo, Wendi Chen, Han Xue, Shirun Tang 외 arxiv

In contact-rich manipulation, action multimodality and reactivity dominate different stages of a single episode. Before contact, multiple trajectories might be equally valid, making it important to preserve diverse actio…