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

• URL: http://arxiv.org/abs/2604.27175v1
• Date: Wed, 29 Apr 2026 20:24:41 GMT
• Title: Global Sampling-Based Trajectory Optimization for Contact-Rich Manipulation via KernelSOS
• Abstract summary: We introduce Global-MPPI, a unified optimization framework that integrates global exploration and local solution space.<n>We evaluate a graduated nonity based strategy to evaluate on logsumexp smoothing, which transitions the optimization landscape from a smoothed surrogate to the original nonsmooth objective refinement.<n> Experimental results demonstrate that our approach robustly uncovers high-quality solutions, achieving faster convergence and lower final costs compared to existing baseline methods.
• Score: 2.964978357715084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hybrid Augmented Lagrangian Method for General Constrained Optimization via Evolutionary Algorithms [0.0]
  We propose a Hybrid Augmented Lagrangian (HyAL) method that integrates the AL framework's constraint-handling strengths with the exploratory power of population-based search.<n>Our approach employs evolutionary techniques to solve subproblems within the AL iterations, promoting exploration and aiding in the escape from local optima.<n>Our results show that HyAL consistently produces high-quality solutions across the benchmark suite.
  arXiv  Detail & Related papers  (2026-07-18T16:29:06Z)
• Domain Knowledge Guided Bayesian Optimization For Autonomous Alignment Of Complex Scientific Instruments [0.44654729785785796]
  We propose a domain knowledge guided Bayesian Optimization approach, which leverages physical insight to simplify the search problem.<n>We demonstrate this approach's efficacy on a challenging 12-dimensional, 6-crystal Split-and-Delay optical system.<n>Our results demonstrate a generalizable paradigm: leveraging physical insight to transform high-dimensional, coupled optimization problems into simpler representations can enable rapid and robust automated tuning.
  arXiv  Detail & Related papers  (2026-02-11T09:15:20Z)
• Anytime Metaheuristic Framework for Global Route Optimization in Expected-Time Mobile Search [0.6187780920448871]
  Expected-time mobile search (ETS) is a robotics task where a mobile sensor navigates an environment to minimize the expected time required to locate a hidden object.<n>This paper builds on and significantly extends the latter by introducing Milaps, a model-based solution framework for ETS.
  arXiv  Detail & Related papers  (2025-12-23T19:19:27Z)
• Efficient Global-Local Fusion Sampling for Physics-Informed Neural Networks [5.257115841810259]
  We propose a Global-Local Fusion (GLF) Sampling Strategy that combines the strengths of both approaches.<n>New collocation points are generated by perturbing training points with Gaussian noise scaled inversely to the residual.<n>To further reduce computational overhead, a lightweight linear surrogate is introduced to approximate the global residual-based distribution.
  arXiv  Detail & Related papers  (2025-10-28T03:10:54Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• SPGD: Steepest Perturbed Gradient Descent Optimization [0.0]
  This paper presents the Steepest Perturbed Gradient Descent (SPGD) algorithm.<n>It is designed to generate a set of candidate solutions and select the one exhibiting the steepest loss difference.<n>Preliminary results show a substantial improvement over four established methods.
  arXiv  Detail & Related papers  (2024-11-07T18:23:30Z)
• Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles [83.85151306138007]
  Multi-level Actor-Critic (MAC) framework incorporates a Multi-level Monte-Carlo (MLMC) estimator. We demonstrate that MAC outperforms the existing state-of-the-art policy gradient-based method for average reward settings.
  arXiv  Detail & Related papers  (2024-03-18T16:23:47Z)
• Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape [59.841889495864386]
  In federated learning (FL), a cluster of local clients are chaired under the coordination of a global server. Clients are prone to overfit into their own optima, which extremely deviates from the global objective. ttfamily FedSMOO adopts a dynamic regularizer to guarantee the local optima towards the global objective. Our theoretical analysis indicates that ttfamily FedSMOO achieves fast $mathcalO (1/T)$ convergence rate with low bound generalization.
  arXiv  Detail & Related papers  (2023-05-19T10:47:44Z)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• Fighting the curse of dimensionality: A machine learning approach to finding global optima [77.34726150561087]
  This paper shows how to find global optima in structural optimization problems. By exploiting certain cost functions we either obtain the global at best or obtain superior results at worst when compared to established optimization procedures.
  arXiv  Detail & Related papers  (2021-10-28T09:50:29Z)
• Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming [41.30044824711509]
  We focus on the case that the global reward is a sum of local rewards, the joint policy factorizes into agents' marginals, and full state observability. We develop multi-agent extensions, whereby agents solve their local saddle point problems and then perform local weighted averaging. We establish that the sample complexity to obtain near-globally optimal solutions matches tight dependencies on the cardinality of the state and action spaces.
  arXiv  Detail & Related papers  (2021-10-22T03:48:41Z)
• Localized active learning of Gaussian process state space models [63.97366815968177]
  A globally accurate model is not required to achieve good performance in many common control applications. We propose an active learning strategy for Gaussian process state space models that aims to obtain an accurate model on a bounded subset of the state-action space. By employing model predictive control, the proposed technique integrates information collected during exploration and adaptively improves its exploration strategy.
  arXiv  Detail & Related papers  (2020-05-04T05:35:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.