Enhancing Autonomous Vehicle Planning With a Robust Fault-Tolerant Mechanism for Action-Induced Agent Detection

Abstract

In autonomous driving, accurately identifying traffic participants that may influence vehicle behavior is crucial for effective system planning. To address this challenge, we propose a fault-tolerant mechanism for detecting action-induced objects, which significantly improves decision-making performance and system explainability. Since these objects are often linked to the vehicle’s driving intentions, we introduce a top-down attention network that adjusts attention weights for traffic participants based on navigational information. Additionally, we define potentially hazardous objects in the driving environment and employ supervised training with a classification head to detect them. To further enhance detection accuracy, we integrate a fault-tolerant process that merges attention maps with classification results, effectively reducing false positives and false negatives in identifying action-induced objects. Extensive testing validates the robustness and effectiveness of our approach, demonstrating its ability to improve both planning and interpretability in autonomous vehicles.