ME$^3$-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception

TL;DR

This paper introduces ME$^3$-BEV, a deep reinforcement learning framework that integrates bird's-eye view perception with the Mamba model for improved end-to-end autonomous driving, demonstrating superior performance in urban scenarios.

Contribution

The paper presents the Mamba-BEV model for efficient spatio-temporal feature extraction and integrates it into an end-to-end DRL framework, enhancing perception and decision-making in autonomous driving.

Findings

Outperforms existing models in CARLA simulator benchmarks

Reduces collision rate and improves trajectory accuracy

Provides interpretable high-dimensional feature visualizations

Abstract

Autonomous driving systems face significant challenges in perceiving complex environments and making real-time decisions. Traditional modular approaches, while offering interpretability, suffer from error propagation and coordination issues, whereas end-to-end learning systems can simplify the design but face computational bottlenecks. This paper presents a novel approach to autonomous driving using deep reinforcement learning (DRL) that integrates bird's-eye view (BEV) perception for enhanced real-time decision-making. We introduce the \texttt{Mamba-BEV} model, an efficient spatio-temporal feature extraction network that combines BEV-based perception with the Mamba framework for temporal feature modeling. This integration allows the system to encode vehicle surroundings and road features in a unified coordinate system and accurately model long-range dependencies. Building on this, we propose the \texttt{ME$^3$-BEV} framework, which utilizes the \texttt{Mamba-BEV} model as a feature input for end-to-end DRL, achieving superior performance in dynamic urban driving scenarios. We further enhance the interpretability of the model by visualizing high-dimensional features through semantic segmentation, providing insight into the learned representations. Extensive experiments on the CARLA simulator demonstrate that \texttt{ME$^3$-BEV} outperforms existing models across multiple metrics, including collision rate and trajectory accuracy, offering a promising solution for real-time autonomous driving.