Object-Informed Model Predictive Path Integral Control for Non-Prehensile Robot Manipulation

2026-05-28

AI Summary

This work addresses the challenge of long-horizon planning in non-prehensile robotic manipulation, where underactuation and discontinuous interactions complicate control. To this end, the authors propose an object-guided hierarchical Model Predictive Path Integral (MPPI) control framework. The approach first generates a desired trajectory for the object and then embeds this trajectory as a reference within a joint robot–object dynamics optimization, enabling efficient and forward-looking decision-making. By integrating a simplified object-centric direct dynamics model with high-fidelity joint simulation, the method achieves a 40% improvement in task success rate and a 26% increase in control frequency in simulation. Real-world experiments demonstrate a 20% gain in success rate with computational overhead comparable to standard MPPI, substantially enhancing the robustness and efficiency of non-prehensile manipulation.

Abstract

Long-horizon planning for non-prehensile robot manipulation is challenging due to underactuated and discontinuous interactions. We propose a hierarchical formulation of model predictive path integral (MPPI) control that guides robot-level planning with a separately computed object-level plan to achieve efficient long-horizon prediction. We first solve a simplified object-only problem, assuming the object can be actuated directly, and use the planned object trajectory as a reference in solving the joint robot-object planning problem. We evaluate our method in both simulation and hardware using a 6-DoF xArm6 manipulator to perform object pushing tasks in which the target object must reach a goal while avoiding static obstacles, necessitating non-myopic reasoning. Our object-informed MPPI increases task success by 40\% with a 26\% faster control frequency in simulation, and by 20\% in real experiments with similar computation as regular MPPI.

Problem

• non-prehensile manipulation
• long-horizon planning
• underactuated systems
• discontinuous interactions
• robotic manipulation

Innovation

• Model Predictive Path Integral Control
• Non-Prehensile Manipulation
• Hierarchical Planning
• Object-Informed Control
• Long-Horizon Planning