Verifiable Goal Recognition for Autonomous Driving with Occlusions
This addresses the challenge of predicting vehicle behavior in occluded environments for autonomous driving systems, representing an incremental improvement with a focus on interpretability and verifiability.
The paper tackles the problem of inferring other vehicles' goals in autonomous driving under partial observability due to occlusions, presenting OGRIT, a method that uses decision trees to achieve fast, accurate, interpretable, and verifiable goal recognition across multiple scenarios.
Goal recognition (GR) involves inferring the goals of other vehicles, such as a certain junction exit, which can enable more accurate prediction of their future behaviour. In autonomous driving, vehicles can encounter many different scenarios and the environment may be partially observable due to occlusions. We present a novel GR method named Goal Recognition with Interpretable Trees under Occlusion (OGRIT). OGRIT uses decision trees learned from vehicle trajectory data to infer the probabilities of a set of generated goals. We demonstrate that OGRIT can handle missing data due to occlusions and make inferences across multiple scenarios using the same learned decision trees, while being computationally fast, accurate, interpretable and verifiable. We also release the inDO, rounDO and OpenDDO datasets of occluded regions used to evaluate OGRIT.