Andrew Wilhelm

Andrew Wilhelm, Josie Hughes

Robot swarms offer inherent robustness and the capacity to execute complex, collaborative tasks surpassing the capabilities of single-agent systems. Co-designing these systems is critical, as marginal improvements in individual performance or unit cost compound significantly at scale. However, under traditional frameworks, this scale renders co-design intractable due to exponentially large, non-intuitive design spaces. To address this, we propose SwarmCoDe, a novel Collaborative Co-Evolutionary Algorithm (CCEA) that utilizes dynamic speciation to automatically scale swarm heterogeneity to match task complexity. Inspired by biological signaling mechanisms for inter-species cooperation, the algorithm uses evolved genetic tags and a selectivity gene to facilitate the emergent identification of symbiotically beneficial partners without predefined species boundaries. Additionally, an evolved dominance gene dictates the relative swarm composition, decoupling the physical swarm size from the evolutionary population. We apply SwarmCoDe to simultaneously optimize task planning and hardware morphology under fabrication budgets, successfully evolving specialized swarms of up to 200 agents -- four times the size of the evolutionary population. This framework provides a scalable, computationally viable pathway for the holistic co-design of large-scale, heterogeneous robot swarms.

Andrew Wilhelm, Aaron Wilhelm, Garrett Fosdick

A state space representation of an environment is a classic and yet powerful tool used by many autonomous robotic systems for efficient and often optimal solution planning. However, designing these representations with high performance is laborious and costly, necessitating an effective and versatile tool for autonomous generation of state spaces for autonomous robots. We present a novel state space exploration algorithm by extending the original surprise-based partially-observable Markov Decision Processes (sPOMDP), and demonstrate its effective long-term exploration planning performance in various environments. Through extensive simulation experiments, we show the proposed model significantly increases efficiency and scalability of the original sPOMDP learning techniques with a range of 31-63% gain in training speed while improving robustness in environments with less deterministic transitions. Our results pave the way for extending sPOMDP solutions to a broader set of environments.