RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915900735619072 |
|---|---|
| author | Ghosh, Anurag Narasimhan, Srinivasa Chandraker, Manmohan Pittaluga, Francesco |
| author_facet | Ghosh, Anurag Narasimhan, Srinivasa Chandraker, Manmohan Pittaluga, Francesco |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28522 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time Ghosh, Anurag Narasimhan, Srinivasa Chandraker, Manmohan Pittaluga, Francesco Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 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. |
| title | RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2603.28522 |