Learning to Communicate Among Agents for Large-Scale Dynamic Path Planning With Genetic Programming Hyperheuristic

Created by W.Langdon from gp-bibliography.bib Revision:1.8344

@Article{Liao:2025:TAI,

• author = "Xiao-Cheng Liao and Xiao-Min Hu and Xiang-Ling Chen and Yi Mei and Ya-Hui Jia and Wei-Neng Chen",
• title = "Learning to Communicate Among Agents for Large-Scale Dynamic Path Planning With Genetic Programming Hyperheuristic",
• journal = "IEEE Transactions on Artificial Intelligence",
• year = "2025",
• volume = "6",
• number = "5",
• pages = "1269--1283",
• month = may,
• keywords = "genetic algorithms, genetic programming, Roads, Protocols, Vehicle dynamics, Artificial intelligence, Path planning, Routing, Learning systems, Vehicle routing, Transportation, Communication, dynamic path planning, genetic programming (GP), hyperheuristic",
• ISSN = "2691-4581",
• DOI = "doi:10.1109/TAI.2024.3522861",
• abstract = "Genetic programming hyperheuristic (GPHH) has recently become a promising methodology for large-scale dynamic path planning (LDPP) since it can produce reusable heuristics rather than disposable solutions. However, in this methodology, the extracted local and decentralized heuristic for agents that lack a global systemic view sometimes may be problematic. Therefore, a new challenge is to strike a balance between conciseness to improve generalisation ability and incorporation of more global information to obtain better performance. In this work, we target the LDPP problem and propose a communication learning mechanism (ComLGP) for GPHH to address the above difficulties. In ComLGP, a communication function is introduced to serve as a communication protocol and exist in the form of an extra terminal in GPHH. Compared to the classic terminals which are fixed in genetic programing, this communication function undergoes optimisation along with the evolutionary process of GPHH. In this way, the communication function can be learnt which enables agents to communicate without a predefined communication protocol. Then, a caching and lazy updating mechanism for ComLGP is presented to accelerate the calculation of communication content. Last, we verified our method on 22 scenarios including two real world road networks. The experimental results demonstrate that the proposed ComLGP can successfully learn to communicate. Although in the absence of any manually designed communication features, ComLGP is capable of achieving performance competitive to the state-of-the-art method that employs a predefined communication protocol and outperforms the remaining compared methods in most scenarios.",
• notes = "Also known as \cite{10816321}",

}

Genetic Programming entries for Xiao-Cheng Liao Xiao-Min Hu Xiang-Ling Chen Yi Mei Ya-Hui Jia Wei-Neng Chen

Citations