基于条件模仿协同学习的端到端自动驾驶转向控制
End-to-End Steering for Autonomous Vehicles via Conditional Imitation Co-Learning
AI总结：
本文提出条件模仿协同学习（CIC）方法，通过协同学习矩阵建模CIL专家分支间关系，并将转向回归转化为分类问题，使端到端自动驾驶在未知环境中的成功率平均提升62%。
摘要：
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。与采用独立子系统分别处理每项任务的模块化方法不同，端到端方法将问题视为使用深度神经网络的单一可学习任务，从而降低系统复杂度并减少对启发式规则的依赖。条件模仿学习（CIL）训练端到端模型模仿人类专家，同时考虑引导车辆到达目的地的导航指令，CIL采用专门的分支网络分别学习每个导航指令下的驾驶任务。然而，CIL模型在部署到未见过的环境时缺乏泛化能力。本文引入条件模仿协同学习（CIC）方法来解决这一问题，通过由门控双曲正切单元（GTU）生成的协同学习矩阵，使模型能够学习CIL专家分支之间的关系。此外，我们提出将转向回归问题建模为分类问题，使用分类-回归混合损失来弥合回归与分类之间的差距，并提出使用共存概率来考虑转向类别之间的空间倾向性。实验证明，与CIL方法相比，我们的模型在未见过的环境中将自动驾驶成功率平均提高了62%。
英文摘要：
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.
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。
