DisCo: Distributed Contact-Rich Trajectory Optimization for Forceful Multi-Robot Collaboration

TL;DR

DisCo is a distributed contact-implicit trajectory optimization algorithm enabling multi-robot collaboration in contact-rich tasks, improving efficiency and privacy by decentralizing computation and communication.

Contribution

We introduce DisCo, a novel distributed algorithm based on ADMM for contact-rich multi-robot trajectory optimization, enhancing scalability and privacy compared to centralized methods.

Findings

Achieves 3x higher success rates in simulations

Operates 2.5x to 5x faster than centralized approaches

Successfully demonstrated on hardware with modular robots

Abstract

We present DisCo, a distributed algorithm for contact-rich, multi-robot tasks. DisCo is a distributed contact-implicit trajectory optimization algorithm, which allows a group of robots to optimize a time sequence of forces to objects and to their environment to accomplish tasks such as collaborative manipulation, robot team sports, and modular robot locomotion. We build our algorithm on a variant of the Alternating Direction Method of Multipliers (ADMM), where each robot computes its own contact forces and contact-switching events from a smaller single-robot, contact-implicit trajectory optimization problem, while cooperating with other robots through dual variables, enforcing constraints between robots. Each robot iterates between solving its local problem, and communicating over a wireless mesh network to enforce these consistency constraints with its neighbors, ultimately converging to a coordinated plan for the group. The local problems solved by each robot are significantly less challenging than a centralized problem with all robots' contact forces and switching events, improving the computational efficiency, while also preserving the privacy of some aspects of each robot's operation. We demonstrate the effectiveness of our algorithm in simulations of collaborative manipulation, multi-robot team sports scenarios, and in modular robot locomotion, where DisCo achieves $3$x higher success rates with a 2.5x to 5x faster computation time. Further, we provide results of hardware experiments on a modular truss robot, with three collaborating truss nodes planning individually while working together to produce a punctuated rolling-gate motion of the composite structure. Videos are available on the project page: https://disco-opt.github.io.