Octopus-inspired Distributed Control for Soft Robotic Arms: A Graph Neural Network-Based Attention Policy with Environmental Interaction
This work addresses the challenge of resilient coordination for soft robotic arms in complex environments, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled the problem of controlling segmented soft robotic arms in contact-rich environments by proposing SoftGM, an octopus-inspired distributed control architecture using graph neural networks, which achieved the best performance in a wall-with-hole task compared to six MARL baselines.
This paper proposes SoftGM, an octopus-inspired distributed control architecture for segmented soft robotic arms that learn to reach targets in contact-rich environments using online obstacle discovery without relying on global obstacle geometry. SoftGM formulates each arm section as a cooperative agent and represents the arm-environment interaction as a graph. SoftGM uses a two-stage graph attention message passing scheme following a Centralised Training Decentralised Execution (CTDE) paradigm with a centralised critic and decentralised actor. We evaluate SoftGM in a Cosserat-rod simulator (PyElastica) across three tasks that increase the complexity of the environment: obstacle-free, structured obstacles, and a wall-with-hole scenario. Compared with six widely used MARL baselines (IDDPG, IPPO, ISAC, MADDPG, MAPPO, MASAC) under identical information content and training conditions, SoftGM matches strong CTDE methods in simpler settings and achieves the best performance in the wall-with-hole task. Robustness tests with observation noise, single-section actuation failure, and transient disturbances show that SoftGM preserves success while keeping control effort bounded, indicating resilient coordination driven by selective contact-relevant information routing.