# Dynamically Local-Enhancement Planner for Large-Scale Autonomous Driving

arXiv: https://arxiv.org/abs/2502.21134 · HTML: https://mlsanity.com/paper/2502.21134/

## 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 18 of its 31 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)

## Builds on (most cited first, 18 of 18)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Transfer Learning in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2009.07888/) (2020)
- [A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles](https://mlsanity.com/paper/1604.07446/) (2016)
- [Distral: Robust Multitask Reinforcement Learning](https://mlsanity.com/paper/1707.04175/) (2017)
- [Model-free Deep Reinforcement Learning for Urban Autonomous Driving](https://mlsanity.com/paper/1904.09503/) (2019)
- [A Survey of Deep RL and IL for Autonomous Driving Policy Learning](https://mlsanity.com/paper/2101.01993/) (2021)
- [Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships](https://mlsanity.com/paper/2011.04251/) (2020)
- [Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks](https://mlsanity.com/paper/2010.05313/) (2020)
- [Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehicles](https://mlsanity.com/paper/2207.00788/) (2022)
- [Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge](https://mlsanity.com/paper/1709.02066/) (2017)
- [Dynamically Conservative Self-Driving Planner for Long-Tail Cases](https://mlsanity.com/paper/2305.07497/) (2023)
- [Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving](https://mlsanity.com/paper/2005.11470/) (2020)

## Abstract (arXiv)

Current autonomous vehicles operate primarily within limited regions, but there is increasing demand for broader applications. However, as models scale, their limited capacity becomes a significant challenge for adapting to novel scenarios. It is increasingly difficult to improve models for new situations using a single monolithic model. To address this issue, we introduce the concept of dynamically enhancing a basic driving planner with local driving data, without permanently modifying the planner itself. This approach, termed the Dynamically Local-Enhancement (DLE) Planner, aims to improve the scalability of autonomous driving systems without significantly expanding the planner's size. Our approach introduces a position-varying Markov Decision Process formulation coupled with a graph neural network that extracts region-specific driving features from local observation data. The learned features describe the local behavior of the surrounding objects, which is then leveraged to enhance a basic reinforcement learning-based policy. We evaluated our approach in multiple scenarios and compared it with a one-for-all driving model. The results show that our method outperforms the baseline policy in both safety (collision rate) and average reward, while maintaining a lighter scale. This approach has the potential to benefit large-scale autonomous vehicles without the need for largely expanding on-device driving models.