AppleVLM: End-to-end Autonomous Driving with Advanced Perception and Planning-Enhanced Vision-Language Models

TL;DR

AppleVLM is a comprehensive vision-language model for autonomous driving that integrates advanced perception and planning modules, demonstrating superior performance in simulation and real-world environments by addressing perception and decision-making challenges.

Contribution

The paper introduces AppleVLM, a novel end-to-end autonomous driving model with a deformable transformer-based vision encoder and a planning modality, improving robustness and generalization over prior VLM approaches.

Findings

Achieved state-of-the-art performance on CARLA benchmarks.

Successfully deployed on a real AGV platform for outdoor driving.

Enhanced perception robustness through multi-view, multi-timestep fusion.

Abstract

End-to-end autonomous driving has emerged as a promising paradigm integrating perception, decision-making, and control within a unified learning framework. Recently, Vision-Language Models (VLMs) have gained significant attention for their potential to enhance the robustness and generalization of end-to-end driving models in diverse and unseen scenarios. However, existing VLM-based approaches still face challenges, including suboptimal lane perception, language understanding biases, and difficulties in handling corner cases. To address these issues, we propose AppleVLM, an advanced perception and planning-enhanced VLM model for robust end-to-end driving. AppleVLM introduces a novel vision encoder and a planning strategy encoder to improve perception and decision-making. Firstly, the vision encoder fuses spatial-temporal information from multi-view images across multiple timesteps using a deformable transformer mechanism, enhancing robustness to camera variations and facilitating scalable deployment across different vehicle platforms. Secondly, unlike traditional VLM-based approaches, AppleVLM introduces a dedicated planning modality that encodes explicit Bird's-Eye-View spatial information, mitigating language biases in navigation instructions. Finally, a VLM decoder fine-tuned by a hierarchical Chain-of-Thought integrates vision, language, and planning features to output robust driving waypoints. We evaluate AppleVLM in closed-loop experiments on two CARLA benchmarks, achieving state-of-the-art driving performance. Furthermore, we deploy AppleVLM on an AGV platform and successfully showcase real-world end-to-end autonomous driving in complex outdoor environments.