Exploring the Potential of World Models for Anomaly Detection in Autonomous Driving
It addresses the problem of handling unexpected situations in autonomous driving for improved safety, but is incremental as it builds on existing world model concepts.
The paper explores using world models from model-based reinforcement learning for anomaly detection in autonomous driving, providing an overview and characterization to relate components to prior work.
In recent years there have been remarkable advancements in autonomous driving. While autonomous vehicles demonstrate high performance in closed-set conditions, they encounter difficulties when confronted with unexpected situations. At the same time, world models emerged in the field of model-based reinforcement learning as a way to enable agents to predict the future depending on potential actions. This led to outstanding results in sparse reward and complex control tasks. This work provides an overview of how world models can be leveraged to perform anomaly detection in the domain of autonomous driving. We provide a characterization of world models and relate individual components to previous works in anomaly detection to facilitate further research in the field.