TY  - GEN
SN  - 2161-8089
UR  - https://doi.org/10.1109/CASE59546.2024.10711550
A1  - Champagnie, Kale
A1  - Chen, Boli
A1  - Arvin, Farshad
A1  - Hu, Junyan
SP  - 1000
N1  - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions.
ID  - discovery10193055
N2  - Two promising approaches to coverage path planning are reward-based and pheromone-based methods. Rewardbased methods allow heuristics to be learned automatically, often yielding a superior performance over hand-crafted rules. On the other hand, pheromone-based methods consistently demonstrate superior generalization and adaptation abilities when placed in unfamiliar environments. To obtain the best of both worlds, we introduce Greedy Entropy Maximization (GEM), a hybrid approach that aims to maximize the entropy of a pheromone deposited by a swarm of homogeneous antlike agents. We begin by establishing a sharp upper-bound on achievable entropy and show that this corresponds to optimal dynamic coverage path planning. Next, we demonstrate that GEM closely approaches this upper-bound despite depriving agents of basic necessities such as memory and explicit communication. Finally, we show that GEM can be executed asynchronously in constant-time, enabling it to scale arbitrarily.
PB  - Institute of Electrical and Electronics Engineers (IEEE)
CY  - Bari, Italy
KW  - Computer aided software engineering
KW  -  Automation
KW  -  Neural networks
KW  -  Reinforcement learning
KW  -  Path planning
KW  -  Entropy
T3  - IEEE International Conference on Automation Science and Engineering (CASE)
TI  - Online Multi-Robot Coverage Path Planning in Dynamic Environments Through Pheromone-Based Reinforcement Learning
EP  - 1005
AV  - public
Y1  - 2024/10/23/
ER  -