# Learning to Sample: Reinforcement Learning-Guided Sampling for Autonomous Vehicle Motion Planning

arXiv: https://arxiv.org/abs/2509.24313 · HTML: https://mlsanity.com/paper/2509.24313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)
- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 21 of 21)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles](https://mlsanity.com/paper/1604.07446/) (2016)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients](https://mlsanity.com/paper/2109.13333/) (2021)
- [Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives](https://mlsanity.com/paper/2303.09824/) (2023)
- [Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles](https://mlsanity.com/paper/2001.11231/) (2020)
- [Learning Sampling Distributions for Robot Motion Planning](https://mlsanity.com/paper/1709.05448/) (2017)
- [World Models for Autonomous Driving: An Initial Survey](https://mlsanity.com/paper/2403.02622/) (2024)
- [SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies](https://mlsanity.com/paper/2109.13602/) (2021)
- [Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning](https://mlsanity.com/paper/2103.14666/) (2021)
- [FRENETIX: A High-Performance and Modular Motion Planning Framework for Autonomous Driving](https://mlsanity.com/paper/2402.01443/) (2024)
- [A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures](https://mlsanity.com/paper/2108.13619/) (2021)
- [Planning with Adaptive World Models for Autonomous Driving](https://mlsanity.com/paper/2406.10714/) (2024)
- [A Reinforcement Learning-Boosted Motion Planning Framework: Comprehensive Generalization Performance in Autonomous Driving](https://mlsanity.com/paper/2402.01465/) (2024)
- [Optimizing Trajectories for Highway Driving with Offline Reinforcement Learning](https://mlsanity.com/paper/2203.10949/) (2022)
- [Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning](https://mlsanity.com/paper/2302.12826/) (2023)
- [Trajectory Planning Using Reinforcement Learning for Interactive Overtaking Maneuvers in Autonomous Racing Scenarios](https://mlsanity.com/paper/2404.10658/) (2024)
- [From Shadows to Safety: Occlusion Tracking and Risk Mitigation for Urban Autonomous Driving](https://mlsanity.com/paper/2504.01408/) (2025)
- [A Non-uniform Sampling Approach for Fast and Efficient Path Planning](https://mlsanity.com/paper/2108.01291/) (2021)
- [Informed sampling-based trajectory planner for automated driving in dynamic urban environments](https://mlsanity.com/paper/2210.02335/) (2022)

## Abstract (arXiv)

Sampling-based motion planning is a well-established approach in autonomous driving, valued for its modularity and analytical tractability. In complex urban scenarios, however, uniform or heuristic sampling often produces many infeasible or irrelevant trajectories. We address this limitation with a hybrid framework that learns where to sample while keeping trajectory generation and evaluation fully analytical and verifiable. A reinforcement learning (RL) agent guides the sampling process toward regions of the action space likely to yield feasible trajectories, while evaluation and final selection remains governed by deterministic feasibility checks and cost functions. We couple the RL sampler with a world model (WM) based on a decodable deep set encoder, enabling both variable numbers of traffic participants and reconstructable latent representations. The approach is evaluated in the CommonRoad (CR) simulation environment and compared against uniform-sampling baselines, showing up to 99% fewer required samples and a runtime reduction of up to 84% while maintaining planning quality in terms of success and collision-free rates. These improvements lead to faster, more reliable decision-making for autonomous vehicles in urban environments.