Collective Intelligence for 2D Push Manipulations with Mobile Robots

TL;DR

This paper presents a novel multi-robot system for 2D push manipulation that leverages a neural network distilled from a physics-based planner, enabling better performance, generalization, and adaptability to environmental changes.

Contribution

It introduces a new approach combining differentiable physics simulation with attention-based neural networks for adaptive multi-robot push manipulation.

Findings

Outperforms baseline methods in push manipulation tasks

Generalizes to unseen configurations

Adapts to environmental changes and turbulence

Abstract

While natural systems often present collective intelligence that allows them to self-organize and adapt to changes, the equivalent is missing in most artificial systems. We explore the possibility of such a system in the context of cooperative 2D push manipulations using mobile robots. Although conventional works demonstrate potential solutions for the problem in restricted settings, they have computational and learning difficulties. More importantly, these systems do not possess the ability to adapt when facing environmental changes. In this work, we show that by distilling a planner derived from a differentiable soft-body physics simulator into an attention-based neural network, our multi-robot push manipulation system achieves better performance than baselines. In addition, our system also generalizes to configurations not seen during training and is able to adapt toward task completions when external turbulence and environmental changes are applied. Supplementary videos can be found on our project website: https://sites.google.com/view/ciom/home