解决自动驾驶中状态感知模仿学习的局限性
Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving
AI总结：
本文针对条件模仿学习在自动驾驶中的惯性问题和离线在线性能相关性低的问题，提出一种基于多阶段视觉Transformer与状态令牌传播的多任务学习智能体，通过状态引导、数据增强和可视化解释显著减少惯性并提升指标一致性。
摘要：
条件模仿学习是训练自动驾驶智能体的一种常见且有效的方法。然而，有两个问题限制了该方法的全部潜力：（i）惯性问题，这是因果混淆的一种特殊情况，智能体错误地将低速与不加速关联起来；（ii）由于小误差的累积使智能体进入此前未见过的状态，导致离线性能与在线性能之间的相关性较低。这两个问题对于状态感知模型都至关重要，而将智能体的内部状态以及环境状态告知驾驶智能体具有至关重要的意义。在本文中，我们提出了一种基于多阶段视觉Transformer并具有状态令牌传播机制的多任务学习智能体。我们将车辆状态与环境表示一起作为Transformer的一个特殊令牌输入，并在整个网络中传播该令牌。这使我们能够从不同角度解决上述问题：利用学习到的停车/行驶信息引导驾驶策略，直接在车辆状态上执行数据增强，并以可视化方式解释模型的决策。我们报告了惯性问题的显著减少以及离线指标与在线指标之间的高相关性。
英文摘要：
Conditional Imitation learning is a common and effective approach to train autonomous driving agents. However, two issues limit the full potential of this approach: (i) the inertia problem, a special case of causal confusion where the agent mistakenly correlates low speed with no acceleration, and (ii) low correlation between offline and online performance due to the accumulation of small errors that brings the agent in a previously unseen state. Both issues are critical for state-aware models, yet informing the driving agent of its internal state as well as the state of the environment is of crucial importance. In this paper we propose a multi-task learning agent based on a multi-stage vision transformer with state token propagation. We feed the state of the vehicle along with the representation of the environment as a special token of the transformer and propagate it throughout the network. This allows us to tackle the aforementioned issues from different angles: guiding the driving policy with learned stop/go information, performing data augmentation directly on the state of the vehicle and visually explaining the model's decisions. We report a drastic decrease in inertia and a high correlation between offline and online metrics.
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。
