Autonomous driving must cope with motion blur, low light, and dynamic agents, where RGB frames and event cameras offer complementary strengths. This thesis investigates how to fuse them across the perception–reasoning–planning pipeline. It introduces FlexEvent, a frequency-robust detector with adaptive fusion and label-efficient training; Talk2Event, the first benchmark for event–language grounding with attribute-aware modeling; and the ongoing EventChat, an event–frame VLM for perception, spatial relations, and ego reasoning. Future work will extend this framework with iterative perception and reinforcement learning for long-horizon decision making. Together, these efforts aim to deliver robust perception, interpretable reasoning, and planning support through event–frame fusion.