Research papers · Posted 2025.11.24 · Preprint
Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
Overview
Percept-WAM encodes 2D and 3D perception through spatial and confidence-bearing tokens within a vision-language model. Experiments assess dense object perception, long-tail generalization and integration with autonomous-driving trajectory decoders.
Version: v1