Continuous learning of emergent behavior in robotic matter

Abstract

One of the main challenges in robotics is the development of systems that can adapt to their environment and achieve autonomous behavior. Current approaches typically aim to achieve this by increasing the complexity of the centralized controller by, e.g., direct modeling of their behavior, or implementing machine learning. In contrast, we simplify the controller using a decentralized and modular approach, with the aim of finding specific requirements needed for a robust and scalable learning strategy in robots. To achieve this, we conducted experiments and simulations on a specific robotic platform assembled from identical autonomous units that continuously sense their environment and react to it. By letting each unit adapt its behavior independently using a basic Monte Carlo scheme, the assembled system is able to learn and maintain optimal behavior in a dynamic environment as long as its memory is representative of the current environment, even when incurring damage. We show that the physical connection between the units is enough to achieve learning, and no additional communication or centralized information is required. As a result, such a distributed learning approach can be easily scaled to larger assemblies, blurring the boundaries between materials and robots, paving the way for a new class of modular “robotic matter” that can autonomously learn to thrive in dynamic or unfamiliar situations, for example, encountered by soft robots or self-assembled (micro)robots in various environments spanning from the medical realm to space explorations.

Collective Conditioned Reflex: A Bio-Inspired Fast Emergency Reaction Mechanism for Designing Safe Multi-Robot Systems

“…Emergent behaviors make an MRS with better adaptability towards suddenlyapplied disruptions and damages. In [22], the authors applied Monte Carlo methods to enable an MRS to develop emergent behaviors, such as attaching to other units to move. However, such behaviors generalized poorly in unseen environments due to the inherent planning rather than learning property of Monte Carlo methods, resulting in weak adaptation to unstructured environments and the limited application scope.…”

Morphological computation and decentralized learning in a swarm of sterically interacting robots

“…Another approach for swarm design is to keep a cohesive swarm, where robots are constantly touching, keeping a physical interaction that allows continuous transmission of information (17)(18)(19)(20)(21)(22). This approach showed success in self-assembly and morphogenesis (23)(24)(25) as well as coordination of a multicellular robotic body (18,(26)(27)(28). To date, artificial swarms are designed to operate exclusively in a dilute, collision-avoided setting or a cohesive dense population.…”

A distributed nanocluster based multi-agent evolutionary network

“…The swarm intelligence essentially arises from the emergence and self-organization characteristics 2 , 12 , 13 . The evolution of simple individuals through nonlinear interactions under de-centralized collaborative control 14 makes the whole show new structures or functions that the individuals do not possess, that is, “the whole is greater than the sum of its parts”. As a considerable branch of distributed AI, multi-agent system inspired by swarm intelligence can deal with complex tasks that far exceed the capability of single agents, which is based upon the interactions between the agents as well as that between the agents and the environment, showing stupendous potential in diverse applications, such as swarm robots 15 , 16 , multivehicle coordination 17 , and machine learning 18 , 19 .…”