Spectral Decomposition of Inverse Dynamics for Fast Exploration in Model-Based Manipulation

TL;DR

This paper introduces a spectral decomposition approach to inverse dynamics for efficient exploration in long-horizon robotic manipulation planning, enabling real-time, long-duration contact-rich trajectories.

Contribution

It presents a novel spectral decomposition method for inverse dynamics that improves long-horizon manipulation planning by enabling fast, feasible trajectory generation.

Findings

Achieves 45-second, multi-contact plans in 15 seconds of computation.

Performs comparably to existing methods on short-horizon tasks.

Successfully plans long-duration manipulation sequences with real-time efficiency.

Abstract

Planning long duration robotic manipulation sequences is challenging because of the complexity of exploring feasible trajectories through nonlinear contact dynamics and many contact modes. Moreover, this complexity grows with the problem's horizon length. We propose a search tree method that generates trajectories using the spectral decomposition of the inverse dynamics equation. This equation maps actuator displacement to object displacement, and its spectrum is efficient for exploration because its components are orthogonal and they approximate the reachable set of the object while remaining dynamically feasible. These trajectories can be combined with any search based method, such as Rapidly-Exploring Random Trees (RRT), for long-horizon planning. Our method performs similarly to recent work in model-based planning for short-horizon tasks, and differentiates itself with its ability to solve long-horizon tasks: whereas existing methods fail, ours can generate 45 second duration, 10+ contact mode plans using 15 seconds of computation, demonstrating real-time capability in highly complex domains.