This paper provide an overview of the emerging trends and challenges in the field of decision-making of unmanned ground vehicles. Specifically, four important decision-making methods are analyzed, including the classical rule-based, the decision tree based, reinforcement learning based, and POMDP based decision-making system. Furthermore, we compare the pros and cons among these methods, and analyze the difficulties encountered in current decision-making systems. On the basis of these comparison and analysis, we suggest that the integration of different methods could improve the performance of the decision-making systems. Finally, we discuss the future development for the decision-making system and recommend to combine graph-based knowledge representation and learning-based method to tackle the complex task and traffic information in the decision-making process.
Review and Outlook of Decision-Making Methods in Unmanned Ground Vehicles
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 287 ; 2931-2941
2022-03-18
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Unmanned Aerial Vehicles Outlook
Online Contents | 2002
Unmanned Aerial Vehicles Outlook
Online Contents | 1998
Unmanned Aerial Vehicles Outlook
Online Contents | 1997
Unmanned Aerial Vehicles Outlook
Online Contents | 2009
1 Outlook-Specifications - Unmanned Aerial Vehicles Outlook
Online Contents | 2007