自动驾驶场景下因果显著性挖掘与抗干扰语义表征方法
By using self-attention mechanisms and recoding strategies to filter causal features in autonomous driving scenarios, the problems of causal confusion and noise interference are solved, improving the model's generalization ability and the safety and smoothness of trajectory planning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TONGJI UNIV
- Filing Date
- 2026-05-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing autonomous driving scenario representation and planning methods suffer from problems such as causal confusion, difficulty in suppressing noise interference, and insufficient applicability of contrastive learning in complex environments, resulting in insufficient generalization ability and safety of models in unknown scenarios.
An attention-guided automated sampling mechanism and recoding strategy are adopted. The global importance ranking is performed through the self-attention mechanism to select key features with causal relationships. Category-aware automated positive and negative samples are constructed, and the recoding mechanism is used for context alignment. A contrastive loss function is constructed to distinguish key causal information from interference noise.
It significantly improves the model's generalization ability in unknown scenarios, enhances the safety and smoothness of trajectory planning, maintains the structural integrity of the driving scenario, and reduces the impact of causal confusion and noise interference.
Smart Images
Figure CN122173877B_ABST