Dynamically Local-Enhancement Planner for Large-Scale Autonomous Driving

2025-02-28

AI Summary

To address the poor generalization of monolithic foundation models to diverse local road conditions in large-scale autonomous driving, this paper proposes the Dynamic Local Enhancement (DLE) paradigm. Without modifying the architecture of the base driving planner, DLE enables zero-parameter, online adaptation to real-time regional observations by jointly leveraging location-aware Markov Decision Process (MDP) modeling and a lightweight graph neural network. The method integrates real-time local feature extraction, reinforcement learning policy fine-tuning, and dynamic MDP reconfiguration to significantly improve regional adaptability. Extensive multi-scenario evaluations demonstrate that DLE reduces collision rates by 37% and increases average reward by 22%, while incurring no increase in model size. It consistently outperforms unified monolithic models across all metrics, offering a scalable, parameter-efficient solution for geographically heterogeneous deployment.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Enhance autonomous driving scalability using local data
• Address limited model capacity for novel scenarios
• Improve safety and efficiency without expanding model size

Innovation

• Dynamic enhancement with local driving data
• Position-varying Markov Decision Process formulation
• Graph neural network for region-specific features