Sampling-Based Optimization with Parallelized Physics Simulator for Bimanual Manipulation

TL;DR

This paper introduces a GPU-accelerated, sampling-based optimization framework using a physics simulator for complex bimanual manipulation tasks, demonstrating real-time performance and effective sim-to-real transfer in cluttered environments.

Contribution

A novel GPU-accelerated, sampling-based optimization method with a customized MPPI algorithm for efficient bimanual manipulation in cluttered settings.

Findings

Successfully solves complex bimanual tasks with static obstacles.

Achieves real-time performance on commodity GPUs.

Demonstrates effective sim-to-real transfer.

Abstract

In recent years, dual-arm manipulation has become an area of strong interest in robotics, with end-to-end learning emerging as the predominant strategy for solving bimanual tasks. A critical limitation of such learning-based approaches, however, is their difficulty in generalizing to novel scenarios, especially within cluttered environments. This paper presents an alternative paradigm: a sampling-based optimization framework that utilizes a GPU-accelerated physics simulator as its world model. We demonstrate that this approach can solve complex bimanual manipulation tasks in the presence of static obstacles. Our contribution is a customized Model Predictive Path Integral Control (MPPI) algorithm, \textbf{guided by carefully designed task-specific cost functions,} that uses GPU-accelerated MuJoCo for efficiently evaluating robot-object interaction. We apply this method to solve significantly more challenging versions of tasks from the PerAct$^{2}$ benchmark, such as requiring the point-to-point transfer of a ball through an obstacle course. Furthermore, we establish that our method achieves real-time performance on commodity GPUs and facilitates successful sim-to-real transfer by leveraging unique features within MuJoCo. The paper concludes with a statistical analysis of the sample complexity and robustness, quantifying the performance of our approach. The project website is available at: https://sites.google.com/view/bimanualakslabunitartu .