Evolving Modular Soft Robots without Explicit Inter-Module Communication using Local Self-Attention

Abstract

Modularity in robotics holds great potential. In principle, modular robots can be disassembled and reassembled in different robots, and possibly perform new tasks. Nevertheless, actually exploiting modularity is yet an unsolved problem: controllers usually rely on inter-module communication, a practical requirement that makes modules not perfectly interchangeable and thus limits their flexibility. Here, we focus on Voxel-based Soft Robots (VSRs), aggregations of mechanically identical elastic blocks. We use the same neural controller inside each voxel, but without any inter-voxel communication, hence enabling ideal conditions for modularity: modules are all equal and interchangeable. We optimize the parameters of the neural controller-shared among the voxels-by evolutionary computation. Crucially, we use a local self-attention mechanism inside the controller to overcome the absence of inter-module communication channels, thus enabling our robots to truly be driven by the collective intelligence of their modules. We show experimentally that the evolved robots are effective in the task of locomotion: thanks to self-attention, instances of the same controller embodied in the same robot can focus on different inputs. We also find that the evolved controllers generalize to unseen morphologies, after a short fine-tuning, suggesting that an inductive bias related to the task arises from true modularity.

arXiv commentAccepted at the Genetic and Evolutionary Computation Conference 2022 (GECCO'22) complex systems track as a full paper

References in corpus (13)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Neural Machine Translation by Jointly Learning to Align and Translate
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Attention in Natural Language Processing
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Visual Transformers: Token-based Image Representation and Processing for Computer Vision
• Using Fast Weights to Attend to the Recent Past
• Information driven self-organization of complex robotic behaviors
• Neuroevolution of Self-Interpretable Agents
• The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
• Multi-focus Attention Network for Efficient Deep Reinforcement Learning
• One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control
• The Effects of Learning in Morphologically Evolving Robot Systems

Cited by in corpus (4)

• Design Optimizer for Planar Soft-Growing Robot Manipulators
• Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots
• Towards Multi-Morphology Controllers with Diversity and Knowledge Distillation
• Controller Distillation Reduces Fragile Brain-Body Co-Adaptation and Enables Migrations in MAP-Elites