<ul><li>Imitation learning based planning tasks on the nuPlan dataset have gained interest in generating human-like driving behaviors.</li><li>To tackle challenges in closed-loop testing and long-tail distribution of scenarios, CAFE-AD method is introduced for trajectory planning in autonomous driving.</li><li>CAFE-AD includes an adaptive feature pruning module to capture relevant information and reduce noisy interference.</li><li>The cross-scenario feature interpolation module enhances scenario information and alleviates over-fitting in dominant scenarios.</li></ul>

CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Driving

Discover more