TY - GEN
T1 - Automatically evolving a general controller for robot swarms
AU - Ericksen, John
AU - Moses, Melanie
AU - Forrest, Stephanie
N1 - Funding Information:
The authors thank the UNM Adaptive Computation Lab members Andrew Milligan, Cari Martinez, Cynthia Freeman, Jessica Jones, Joe Renzullo, and Padraic Cashin for their support and feedback on this research. Also, we thank the UNM Biological Computation Lab members Joshua Hecker, Matthew Fricke, and Wayne Just for their help gathering comparison data. We like to recognize Laura Patrizi for her contributions to the early stages of this research effort. SF acknowledges the partial support of NSF (1518878), DARPA (FA8750-15-C-0118), AFRL (FA8750-15-2-0075), the Sandia National Laboratories Academic Alliance, and the Santa Fe Institute. MEM was supported by NASA MUREP #NNX15AM14A and a James S. McDonnell Foundation Complex Systems Scholar Award.
Publisher Copyright:
© 2017 IEEE.
PY - 2018/2/2
Y1 - 2018/2/2
N2 - Controller design is an important problem for swarm robotics. Although many successful controllers have been proposed, most are hand-coded, sometimes using adaptive mechanisms to tune parameters of a manually designed algorithm. These solutions are generally tailored to specific environments, or problem instances, and often fail to scale well as swarm size is increased. This paper focuses on the problem of swarm foraging, proposing an automated method for designing scalable controllers that can perform effectively in multiple foraging environments. We use Neuroevolution of Augmented Topologies (NEAT) to design a neural network controller for a swarm of homogeneous robots. Our system, called NeatFA (NEAT Foraging Algorithm), is compared to existing swarm foraging algorithms, the Central Place Foraging Algorithm (CPFA), and the Distributed Deterministic Spiral Algorithm (DDSA). We find that NEAT produces controllers with performance that is comparable to both the CPFA and the DDSA. This is significant because the controller design was evolved automatically without preprogramming high-level behaviors or movements. The evolved neural network controller responds to sensed inputs and produces movements and actions that lead to effective collective foraging by the swarm. We find that the NeatFA controller performs comparably or outperforms the DDSA and CPFA for large swarm sizes. Finally, we show that a NeatFA general controller, when evolved for multiple environments but smaller swarm sizes, scales successfully to larger swarm sizes.
AB - Controller design is an important problem for swarm robotics. Although many successful controllers have been proposed, most are hand-coded, sometimes using adaptive mechanisms to tune parameters of a manually designed algorithm. These solutions are generally tailored to specific environments, or problem instances, and often fail to scale well as swarm size is increased. This paper focuses on the problem of swarm foraging, proposing an automated method for designing scalable controllers that can perform effectively in multiple foraging environments. We use Neuroevolution of Augmented Topologies (NEAT) to design a neural network controller for a swarm of homogeneous robots. Our system, called NeatFA (NEAT Foraging Algorithm), is compared to existing swarm foraging algorithms, the Central Place Foraging Algorithm (CPFA), and the Distributed Deterministic Spiral Algorithm (DDSA). We find that NEAT produces controllers with performance that is comparable to both the CPFA and the DDSA. This is significant because the controller design was evolved automatically without preprogramming high-level behaviors or movements. The evolved neural network controller responds to sensed inputs and produces movements and actions that lead to effective collective foraging by the swarm. We find that the NeatFA controller performs comparably or outperforms the DDSA and CPFA for large swarm sizes. Finally, we show that a NeatFA general controller, when evolved for multiple environments but smaller swarm sizes, scales successfully to larger swarm sizes.
UR - http://www.scopus.com/inward/record.url?scp=85046157142&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046157142&partnerID=8YFLogxK
U2 - 10.1109/SSCI.2017.8285399
DO - 10.1109/SSCI.2017.8285399
M3 - Conference contribution
AN - SCOPUS:85046157142
T3 - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
SP - 1
EP - 8
BT - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017
Y2 - 27 November 2017 through 1 December 2017
ER -