RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time
This addresses real-time autonomous driving planning by integrating rules for reliability and language for adaptability, though it is incremental as it builds on existing planning methods.
The paper tackled autonomous driving by developing a hybrid planner combining rule-based (RAD) and language-action (LAD) approaches, achieving ~3x lower latency than prior models and setting new state-of-the-art performance on nuPlan benchmarks.
We present LAD, a real-time language--action planner with an interruptible architecture that produces a motion plan in a single forward pass (~20 Hz) or generates textual reasoning alongside a motion plan (~10 Hz). LAD is fast enough for real-time closed-loop deployment, achieving ~3x lower latency than prior driving language models while setting a new learning-based state of the art on nuPlan Test14-Hard and InterPlan. We also introduce RAD, a rule-based planner designed to address structural limitations of PDM-Closed. RAD achieves state-of-the-art performance among rule-based planners on nuPlan Test14-Hard and InterPlan. Finally, we show that combining RAD and LAD enables hybrid planning that captures the strengths of both approaches. This hybrid system demonstrates that rules and learning provide complementary capabilities: rules support reliable maneuvering, while language enables adaptive and explainable decision-making.