Abstract
In this paper, we analize and benchmark three genetically-evolved reactive obstacle-avoidance behaviors for mobile robots. We built these behaviors with an optimization process using genetic algorithms to find the one allowing a mobile robot to best reactively avoid obstacles while moving towards its destination. We compare three approaches, the first one is a standard method based on potential fields, the second one uses on finite state machines (FSM), and the last one relies on HMM-based probabilistic finite state machines (PFSM). We trained the behaviors in simulated environments to obtain the optimized behaviors and compared them to show that the evolved FSM approach outperforms the other two techniques.
Originalsprache | englisch |
---|---|
Titel | ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence |
Redakteure/-innen | Ana Paula Rocha, Luc Steels, Jaap van den Herik |
Herausgeber (Verlag) | SciTePress |
Seiten | 698-707 |
Seitenumfang | 10 |
Band | 2 |
ISBN (elektronisch) | 978-989758484-8 |
Publikationsstatus | Veröffentlicht - 4 Feb. 2021 |
Veranstaltung | 13th International Conference on Agents and Artificial Intelligence: ICAART 2021 - Virtuell, Österreich Dauer: 4 Feb. 2021 → 6 Feb. 2021 http://www.icaart.org/ |
Konferenz
Konferenz | 13th International Conference on Agents and Artificial Intelligence |
---|---|
Kurztitel | ICAART 2021 |
Land/Gebiet | Österreich |
Ort | Virtuell |
Zeitraum | 4/02/21 → 6/02/21 |
Internetadresse |
ASJC Scopus subject areas
- Ingenieurwesen (sonstige)
- Software
- Artificial intelligence
Fields of Expertise
- Information, Communication & Computing
Treatment code (Nähere Zuordnung)
- Basic - Fundamental (Grundlagenforschung)