Parting with Misconceptions about Learning-based Vehicle Motion Planning

By Daniel Dauner, Marcel Hallgarten, Andreas Geiger, Kashyap Chitta. Conference on Robot Learning, 2023

317 citations recorded by the source corpus.

The release of nuPlan marks a new era in vehicle motion planning research, offering the first large-scale real-world dataset and evaluation schemes requiring both precise short-term planning and long-horizon ego-forecasting. Existing systems struggle to simultaneously meet both requirements. Indeed, we find that these tasks are fundamentally misaligned and should be addressed independently. We further assess the current state of closed-loop planning in the field, revealing the limitations of learning-based methods in complex real-world scenarios and the value of simple rule-based priors such as centerline selection through lane graph search algorithms. More surprisingly, for the open-loop sub-task, we observe that the best results are achieved when using only this centerline as scene context (i.e., ignoring all information regarding the map and other agents). Combining these insights, we propose an extremely simple and efficient planner which outperforms an extensive set of competitors, winning the nuPlan planning challenge 2023.

Subfields: Automotive Engineering

View Paper: https://www.semanticscholar.org/paper/34847169f8ec239292abdefc094b60569b4ef5bd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

1. Kashyap Chitta
2. Andreas Geiger
3. Hongyang Li
4. Li Chen
5. Peng Wu
6. Bernhard Jaeger
7. Katrin Renz
8. Jiageng Mao

Citations in the corpus

• GPT-Driver: Learning to Drive with GPT (2023, background): “In contrast, the learning-based approaches Bojarski et al. (2016) Hu et al. (2022; 2023); Dauner et al. (2023) proposed to handle complex driving scenarios by learning from large-scale human driving data.”
• End-to-End Autonomous Driving: Challenges and Frontiers (2023, background): “However, open-loop results do not provide conclusive evidence of improved driving behavior in closed-loop, due to the aforementioned drawbacks [123], [125], [129], [130].”
• NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking (2024, unknown): “Second, we draw inspiration from the literature of rule-based planning for AVs [41, 18, 39, 16] to identify a set of diverse, efficient, and principled metrics that cover multiple facets of the autonomous driving task.”
• DriveLM: Driving with Graph Visual Question Answering (2023, methodology): “Second, the use of language representations as an input and output offers a platform for human-friendly interaction with these models, unlike bounding boxes or trajectories that are more common to current methods [14, 25, 41, 58].”