Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912013956939776 |
|---|---|
| author | Hallgarten, Marcel Zapata, Julian Stoll, Martin Renz, Katrin Zell, Andreas |
| author_facet | Hallgarten, Marcel Zapata, Julian Stoll, Martin Renz, Katrin Zell, Andreas |
| contents | Real-world autonomous driving systems must make safe decisions in the face of rare and diverse traffic scenarios. Current state-of-the-art planners are mostly evaluated on real-world datasets like nuScenes (open-loop) or nuPlan (closed-loop). In particular, nuPlan seems to be an expressive evaluation method since it is based on real-world data and closed-loop, yet it mostly covers basic driving scenarios. This makes it difficult to judge a planner's capabilities to generalize to rarely-seen situations. Therefore, we propose a novel closed-loop benchmark interPlan containing several edge cases and challenging driving scenarios. We assess existing state-of-the-art planners on our benchmark and show that neither rule-based nor learning-based planners can safely navigate the interPlan scenarios. A recently evolving direction is the usage of foundation models like large language models (LLM) to handle generalization. We evaluate an LLM-only planner and introduce a novel hybrid planner that combines an LLM-based behavior planner with a rule-based motion planner that achieves state-of-the-art performance on our benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios? Hallgarten, Marcel Zapata, Julian Stoll, Martin Renz, Katrin Zell, Andreas Robotics Artificial Intelligence Machine Learning Real-world autonomous driving systems must make safe decisions in the face of rare and diverse traffic scenarios. Current state-of-the-art planners are mostly evaluated on real-world datasets like nuScenes (open-loop) or nuPlan (closed-loop). In particular, nuPlan seems to be an expressive evaluation method since it is based on real-world data and closed-loop, yet it mostly covers basic driving scenarios. This makes it difficult to judge a planner's capabilities to generalize to rarely-seen situations. Therefore, we propose a novel closed-loop benchmark interPlan containing several edge cases and challenging driving scenarios. We assess existing state-of-the-art planners on our benchmark and show that neither rule-based nor learning-based planners can safely navigate the interPlan scenarios. A recently evolving direction is the usage of foundation models like large language models (LLM) to handle generalization. We evaluate an LLM-only planner and introduce a novel hybrid planner that combines an LLM-based behavior planner with a rule-based motion planner that achieves state-of-the-art performance on our benchmark. |
| title | Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios? |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.07569 |