@inproceedings{c3b88b90c2564fd6959efe30d438b08c,
title = "Intent Recognition for Multi-agent Systems with Incomplete Information via Spatiotemporal Feature Fusion",
abstract = "This paper constructs six mathematical intention models for adversarial scenarios, such as encirclement and interception. A unified target point generation transforms intent recognition into time-series classification using a three-layer architecture for environment cognition, feature extraction, and inference. Kalman filtering with a nonlinear fade-in/out mechanism improves trajectory prediction and adaptability. Situation maps based on artificial potential fields integrate obstacles and agent dynamics. LSTM and Transformer networks extract multi-scale temporal and global features. Experiments on a multi-intent simulation dataset demonstrate the method{\textquoteright}s high accuracy, robustness, and fast response, supporting intelligent reasoning and tactical decision-making in multi-agent systems.",
keywords = "intent recognition, Kalman filtering, LSTM, multi-agent systems, situation map, Transformer",
author = "Qianning Liu and Xin Huo and Hang Zhang and Hongfeng Xu",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 9th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2025 ; Conference date: 31-10-2025 Through 03-11-2025",
year = "2026",
doi = "10.1007/978-981-95-8435-2\_59",
language = "英语",
isbn = "9789819584345",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "730--739",
editor = "Qing Wang and Xiwang Dong and Peng Song",
booktitle = "Proceedings of 2025 9th Chinese Conference on Swarm Intelligence and Cooperative Control - Swarm Control Technologies",
address = "德国",
}