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

• URL: http://arxiv.org/abs/2606.20712v1
• Date: Tue, 16 Jun 2026 12:24:05 GMT
• Title: Real-World Deployment of Massively Parallel Sampling-Based MPC for Contact-Rich Manipulation
• Abstract summary: We present an MPC framework that leverages JAX for large-scale parallelization and efficient computation.<n>We deploy it on a Franka Research 3 executing the Push-T manipulation task through a complete real-to-sim-to-real pipeline.<n>These findings highlight key challenges for sampling-based MPC in contact-rich manipulation-contact sensitivity, tight compute budgets, and the difficulty of obtaining informative domain-randomization signals in real time.
• Score: 21.501604407170273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 simplified dynamics or remains confined to simulation. We present an MPC framework that leverages JAX for large-scale parallelization and efficient computation, coupled with the high-fidelity MuJoCo MJX simulator, and deploy it on a Franka Research 3 executing the Push-T manipulation task through a complete real-to-sim-to-real pipeline. The MTP variant with structured global sampling outperforms unimodal baselines such as CEM, MPPI, and PS across tasks that require mode switching, both in simulation and on hardware. Furthermore, we evaluate online domain randomization within the MPC sample budget, showing that contact-initiation parameters yield interpretable adaptation signals, whereas global physics parameters provide feedback that is too weak for reliable exploitation at typical replanning frequencies. These findings highlight key challenges for sampling-based MPC in contact-rich manipulation-contact sensitivity, tight compute budgets, and the difficulty of obtaining informative domain-randomization signals in real time.

Related papers

• PRISM: Projection-Integrated Sampling-Based MPC with Bayesian Cost Tuning for Bimanual Manipulation [1.9669271611151167]
  Bimanual manipulation in cluttered, contact-rich environments requires coordinated motion generation, interaction-aware planning, and reliable execution under tight kinematic constraints.<n>We present PRISM, a projection-integrated sampling-based Model Predictive Control framework that uses a GPU-accelerated physics simulator as an online world model for complex dual-arm manipulation.
  arXiv  Detail & Related papers  (2026-08-26T11:47:12Z)
• Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control [19.515987245507013]
  This paper shows that the optimal sampling proposal distribution can be realized by sampling with an optimized feedback policy.<n>In diverse contact-rich control tasks like humanoid loco-manipulation and dexterous manipulation, we show that FS-MPC successfully tackles dynamically unstable tasks.
  arXiv  Detail & Related papers  (2026-08-19T20:56:18Z)
• Fine-Tuning of Neural Network Approximate MPC without Retraining via Bayesian Optimization [81.35990332700389]
  Approximate model-predictive control (AMPC) aims to imitate an MPC's behavior with a neural network.<n>During deployment, the parameters of the underlying MPC must usually be fine-tuned.<n>Recent work addresses this problem by adapting AMPC without retraining using approximated sensitivities of the MPC's optimization problem.
  arXiv  Detail & Related papers  (2025-12-16T12:24:08Z)
• Simulating Environments with Reasoning Models for Agent Training [55.98861707136674]
  Building bespoke environments for training is heavy, brittle, and limits progress.<n>We propose two frameworks: Simia-SFT and Simia-RL.<n>Simia-SFT and Simia-RL enable scalable agent training without environment engineering.
  arXiv  Detail & Related papers  (2025-11-03T18:29:57Z)
• Feedback-MPPI: Fast Sampling-Based MPC via Rollout Differentiation -- Adios low-level controllers [0.9674641730446749]
  Model Predictive Path Integral control is a powerful sampling-based approach suitable for complex robotic tasks.<n>This paper introduces robust feedback gains derived from sensitivity used in gradient-based MPC.<n>We demonstrate the effectiveness of F-MPPI in simulations through real-world experiments on two robotic platforms.
  arXiv  Detail & Related papers  (2025-06-17T07:47:33Z)
• G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration [48.948187359727996]
  G-Sim is a hybrid framework that automates simulator construction with rigorous empirical calibration.<n>It produces reliable, causally-informed simulators, mitigating data-inefficiency and enabling robust system-level interventions.
  arXiv  Detail & Related papers  (2025-06-10T22:14:34Z)
• An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfer with Differentiable Simulation [13.15220962477623]
  This paper introduces a novel Real-Sim-Real loop framework to address the gap between simulation and real-world conditions.<n>A key contribution of our work is the design of an informative cost function that encourages the collection of diverse and representative real-world data.<n>Our approach is implemented on the versatile Mujoco MJX platform, and our framework is compatible with a wide range of robotic systems.
  arXiv  Detail & Related papers  (2025-03-13T07:27:05Z)
• Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations [5.394255369988441]
  This paper presents a novel federated reinforcement learning (Fed-RL) approach to tackle (a) model complexities, unknown dynamical behaviors of IBR devices, (b) privacy issues regarding data sharing in multi-party-owned networked grids, and (2) transfers learned controls from simulation to hardware-in-the-loop test-bed. Experiments show that the simulator-trained RL controllers produce convincing results with the real-time test-bed set-up, validating the minimization of sim-to-real gap.
  arXiv  Detail & Related papers  (2023-11-21T00:59:27Z)
• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration [87.53543137162488]
  We propose an easy-to-implement online reinforcement learning (online RL) framework called textttMEX. textttMEX integrates estimation and planning components while balancing exploration exploitation automatically. It can outperform baselines by a stable margin in various MuJoCo environments with sparse rewards.
  arXiv  Detail & Related papers  (2023-05-29T17:25:26Z)
• Auto-Tuned Sim-to-Real Transfer [143.44593793640814]
  Policies trained in simulation often fail when transferred to the real world. Current approaches to tackle this problem, such as domain randomization, require prior knowledge and engineering. We propose a method for automatically tuning simulator system parameters to match the real world.
  arXiv  Detail & Related papers  (2021-04-15T17:59:55Z)
• Reinforcement Learning for Adaptive Mesh Refinement [63.7867809197671]
  We propose a novel formulation of AMR as a Markov decision process and apply deep reinforcement learning to train refinement policies directly from simulation. The model sizes of these policy architectures are independent of the mesh size and hence scale to arbitrarily large and complex simulations.
  arXiv  Detail & Related papers  (2021-03-01T22:55:48Z)

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.