DaXBench: Benchmarking Deformable Object Manipulation with Differentiable Physics

TL;DR

DaXBench is a comprehensive differentiable physics-based benchmark for deformable object manipulation, covering diverse objects and tasks, enabling systematic evaluation of various algorithms and highlighting current limitations.

Contribution

The paper introduces DaXBench, a new benchmark with nine high-fidelity tasks for deformable object manipulation using differentiable physics, facilitating cross-task performance comparison.

Findings

Differentiable physics-based methods show promising results across tasks.

Current algorithms face limitations in generalization and complexity handling.

DaXBench enables systematic evaluation and comparison of DOM algorithms.

Abstract

Deformable Object Manipulation (DOM) is of significant importance to both daily and industrial applications. Recent successes in differentiable physics simulators allow learning algorithms to train a policy with analytic gradients through environment dynamics, which significantly facilitates the development of DOM algorithms. However, existing DOM benchmarks are either single-object-based or non-differentiable. This leaves the questions of 1) how a task-specific algorithm performs on other tasks and 2) how a differentiable-physics-based algorithm compares with the non-differentiable ones in general. In this work, we present DaXBench, a differentiable DOM benchmark with a wide object and task coverage. DaXBench includes 9 challenging high-fidelity simulated tasks, covering rope, cloth, and liquid manipulation with various difficulty levels. To better understand the performance of general algorithms on different DOM tasks, we conduct comprehensive experiments over representative DOM methods, ranging from planning to imitation learning and reinforcement learning. In addition, we provide careful empirical studies of existing decision-making algorithms based on differentiable physics, and discuss their limitations, as well as potential future directions.