EgoFSD：面向端到端自动驾驶的以自我为中心的完全稀疏范式，结合不确定性去噪和迭代细化
EgoFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving
AI总结：
EgoFSD通过引入稀疏感知、分层交互和迭代运动规划，提升端到端自动驾驶的效率和性能，减少误差和碰撞，提高训练稳定性。
摘要：
当前端到端自动驾驶（E2E-AD）方法倾向于采用统一的模块化设计来处理各种任务（例如感知、预测和规划）。尽管在规划导向的方式下进行了完全可微分框架的优化，但现有的端到端驾驶系统由于缺乏以自我为中心的设计，仍然面临性能不佳和效率低下问题，原因在于栅格化场景表示学习和冗余信息传输。在本文中，我们提出了一种以自我为中心的完全稀疏范式，称为EgoFSD，用于端到端自动驾驶。具体来说，EgoFSD由稀疏感知、分层交互和迭代运动规划组成。稀疏感知模块基于驾驶场景的稀疏表示进行检测和在线制图。分层交互模块旨在从粗到细选择最近的在路径车辆/静止物体（CIPV/CIPS），受益于额外的几何先验。至于迭代运动规划器，所选交互代理和自动驾驶车辆都被考虑在内，用于联合运动预测，其中输出的多模态驾驶轨迹在迭代过程中进行优化。此外，引入了位置级运动扩散和轨迹级规划去噪，用于不确定性建模，从而增强了训练的稳定性和收敛速度。在nuScenes和Bench2Drive数据集上进行了广泛的实验，显著将平均L2误差降低了59%，碰撞率降低了92%，同时实现了6.9倍更快的运行效率。
英文摘要：
Current End-to-End Autonomous Driving (E2E-AD) methods resort to unifying modular designs for various tasks (e.g. perception, prediction and planning). Although optimized with a fully differentiable framework in a planning-oriented manner, existing end-to-end driving systems lacking ego-centric designs still suffer from unsatisfactory performance and inferior efficiency, due to rasterized scene representation learning and redundant information transmission. In this paper, we propose an ego-centric fully sparse paradigm, named EgoFSD, for end-to-end self-driving. Specifically, EgoFSD consists of sparse perception, hierarchical interaction and iterative motion planner. The sparse perception module performs detection and online mapping based on sparse representation of the driving scene. The hierarchical interaction module aims to select the Closest In-Path Vehicle / Stationary (CIPV / CIPS) from coarse to fine, benefiting from an additional geometric prior. As for the iterative motion planner, both selected interactive agents and ego-vehicle are considered for joint motion prediction, where the output multi-modal ego-trajectories are optimized in an iterative fashion. In addition, position-level motion diffusion and trajectory-level planning denoising are introduced for uncertainty modeling, thereby enhancing the training stability and convergence speed. Extensive experiments are conducted on nuScenes and Bench2Drive datasets, which significantly reduces the average L2 error by 59% and collision rate by 92% than UniAD while achieves 6.9x faster running efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
