Online automatic code generation for robot swarms: LLMs and self-organizing hierarchy
This addresses the challenge of autonomous recovery for robot swarms in dynamic environments, though it appears incremental as it builds on prior SoNS work.
The paper tackled the problem of robot swarms getting stuck during missions by using a self-organizing nervous system (SoNS) to enable online automatic code generation with LLMs, resulting in an 85% success rate in completing missions as demonstrated with real and simulated robots.
Our recently introduced self-organizing nervous system (SoNS) provides robot swarms with 1) ease of behavior design and 2) global estimation of the swarm configuration and its collective environment, facilitating the implementation of online automatic code generation for robot swarms. In a demonstration with 6 real robots and simulation trials with >30 robots, we show that when a SoNS-enhanced robot swarm gets stuck, it can automatically solicit and run code generated by an external LLM on the fly, completing its mission with an 85% success rate.