Explainable AI Algorithm for Driving Decision-Making
ICEL's research in AI Algorithms for Driving Decision-Making
Last Updated: 01/21/2026 | All information is accurate and up-to-date
Explainable AI Algorithm for Driving Decision-Making
Key Features
- Implicit visual-semantic module captures the region-based action-inducing components (implicit visual semantics) to provide a human-understandable explanation;
- Explicit reasoning module is developed to jointly align the human-annotated explanation and intention prediction in a multi-task fashion.
Multi-modal Feedback for Explainable Driving Decision-making
Key Features
- Multi-head-attention-based self-learning scene graph;
- Adjustable balance between global and local features, which determines automatic and human-guided feature weighting.
- Action prediction accuracy is optimal at balanced λ;
- Explanation accuracy always increases.
