Cognitive swarming: An approach from the theoretical neuroscience of hippocampal function

摘要

The rise of mobile multi-agent robotic platforms is outpacing control paradigms for tasks that require operatingin complex, realistic environments. To leverage inertial, energetic, and cost bene ts of small-scale robots, criticalfuture applications may depend on coordinating large numbers of agents with minimal onboard sensing andcommunication resources. In this article, we present the perspective that adaptive and resilient autonomouscontrol of swarms of minimal agents might follow from a direct analogy with the neural circuits of spatial cognitionin rodents. We focus on spatial neurons such as place cells found in the hippocampus. Two major emergenthippocampal phenomena, self-stabilizing attractor maps and temporal organization by shared oscillations, revealtheoretical solutions for decentralized self-organization and distributed communication in the brain. We considerthat autonomous swarms of minimal agents with low-bandwidth communication are analogous to brain circuits ofoscillatory neurons with spike-based propagation of information. The resulting notion of `neural swarm control'has the potential to be scalable, adaptive to dynamic environments, and resilient to communication failures andagent attrition. We illustrate a path toward extending this analogy into multi-agent systems applications anddiscuss implications for advances in decentralized swarm control.