Autonomous System
Autonomous systems research focuses on developing machines capable of operating independently and achieving goals without continuous human intervention. Current research emphasizes improving robustness and safety through techniques like vulnerability-adaptive protection, advanced control algorithms (including model predictive control and reinforcement learning), and the use of diverse sensor modalities (e.g., dynamic vision sensors, LiDAR) integrated with sophisticated model architectures such as neural networks and transformers. This field is crucial for advancing safety-critical applications across various sectors, including transportation, robotics, and industrial automation, by enabling more reliable and efficient systems.
Papers
Using Formal Models, Safety Shields and Certified Control to Validate AI-Based Train Systems
Jan Gruteser (Heinrich Heine University Düsseldorf), Jan Roßbach (Heinrich Heine University Düsseldorf), Fabian Vu (Heinrich Heine University Düsseldorf), Michael Leuschel (Heinrich Heine University Düsseldorf)
Convex Approximation of Probabilistic Reachable Sets from Small Samples Using Self-supervised Neural Networks
Jun Xiang, Jun Chen
Grand Challenges in the Verification of Autonomous Systems
Kevin Leahy, Hamid Asgari, Louise A. Dennis, Martin S. Feather, Michael Fisher, Javier Ibanez-Guzman, Brian Logan, Joanna I. Olszewska, Signe Redfield
LLM-based Multi-Agent Systems: Techniques and Business Perspectives
Yingxuan Yang, Qiuying Peng, Jun Wang, Ying Wen, Weinan Zhang