地平线ResAD：残差学习让自动驾驶决策更接近人类逻辑

Core Insights - The article discusses the limitations of traditional modular approaches in autonomous driving and introduces the ResAD framework, which aims to improve efficiency and safety by using an end-to-end model that focuses on learning necessary adjustments from a baseline trajectory [2][50]. Group 1: Framework Overview - ResAD framework proposes a shift from directly predicting future trajectories to learning the necessary adjustments from a physical baseline trajectory, termed "inertial reference line" [2][50]. - The model focuses on understanding the reasons for trajectory adjustments, such as obstacles and traffic rules, rather than memorizing data correlations [50]. Group 2: Methodology - The ResAD framework incorporates a "normalized residual trajectory modeling" approach, which simplifies the learning problem by defining trajectory predictions as adjustments to a reference line [11][50]. - The framework employs a "point-wise residual normalization" technique to balance the optimization weights of near and far trajectory points, ensuring that critical adjustments are not overlooked [20][50]. Group 3: Testing and Results - Real-world testing demonstrated the effectiveness of the ResAD framework, showcasing its ability to handle complex driving scenarios and respond intelligently to dynamic obstacles [6]. - In benchmark evaluations, ResAD achieved state-of-the-art performance on NAVSIM v1 and v2, with a PDMS score of 88.6 and an EPDMS score of 85.5, indicating high safety and efficiency in route completion [38][39]. Group 4: Comparative Analysis - ResAD outperformed existing models like DiffusionDrive in various metrics, including lane adherence and route completion efficiency, highlighting its superior trajectory generation capabilities [41][39]. - The article emphasizes the importance of the unique trajectory modeling strategy in ResAD, which allows for the generation of contextually relevant and diverse trajectories without relying on a static trajectory library [10][41].