通过协同学习提升自动驾驶在未知环境中的端到端转向能力。
End-to-End Steering for Autonomous Vehicles via Conditional Imitation Co-Learning
- 用条件模仿共学习机制，让不同导航指令分支相互协作。
- 在未见环境中成功率达62%的提升，超越传统方法。
- 将转向回归转为分类，融合概率建模提升空间一致性。
自动驾驶涉及数据融合、目标与车道检测、行为预测和路径规划等复杂任务。与各自模块独立处理的方法不同，端到端方法将问题视为单一可学习任务，使用深度神经网络降低系统复杂性并减少对启发式规则的依赖。条件模仿学习（CIL）通过导航指令引导专家驾驶行为来训练模型，采用专用分支学习每种指令下的驾驶任务。然而，该方法在未见环境中的泛化能力不足。本文提出条件模仿共学习（CIC）方法，通过门控双曲正切单元（GTUs）生成共学习矩阵，使各分支间建立关系。同时，将转向回归问题转化为分类，并引入分类-回归混合损失以弥合分类与回归的差距；还提出共存概率以建模转向类间的空间倾向性。实验表明，本模型在未见环境中的自动驾驶成功率平均比CIL方法提升62%。
原文摘要 · Abstract (English)
Autonomous driving involves complex tasks such as data fusion, object and lane detection, behavior prediction, and path planning. As opposed to the modular approach which dedicates individual subsystems to tackle each of those tasks, the end-to-end approach treats the problem as a single learnable task using deep neural networks, reducing system complexity and minimizing dependency on heuristics. Conditional imitation learning (CIL) trains the end-to-end model to mimic a human expert considering the navigational commands guiding the vehicle to reach its destination, CIL adopts specialist network branches dedicated to learn the driving task for each navigational command. Nevertheless, the CIL model lacked generalization when deployed to unseen environments. This work introduces the conditional imitation co-learning (CIC) approach to address this issue by enabling the model to learn the relationships between CIL specialist branches via a co-learning matrix generated by gated hyperbolic tangent units (GTUs). Additionally, we propose posing the steering regression problem as classification, we use a classification-regression hybrid loss to bridge the gap between regression and classification, we also propose using co-existence probability to consider the spatial tendency between the steering classes. Our model is demonstrated to improve autonomous driving success rate in unseen environment by 62% on average compared to the CIL method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。