arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.04017cs.LG
收藏

通过语义掩码世界模型提升端到端城市自动驾驶的样本效率与鲁棒性

Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model

Institute of Automation, Chinese Academy of Science(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);The University of Hong Kong(香港大学);Tsinghua University(清华大学);University of Science and Technology Beijing(北京科技大学)

Zeyu Gao, Yao Mu, Chen Chen, Jingliang Duan, Shengbo Eben Li, Ping Luo, Yanfeng Lu

AI总结:

针对端到端自动驾驶世界模型潜在状态含无关信息、训练数据不均衡的问题,提出带语义滤波器的SEM2模型与多源数据采样器,在CARLA上的样本效率和鲁棒性优于现有方法。

摘要:

端到端自动驾驶通过将前置摄像头的原始像素直接映射为控制信号,为自动最大化驾驶系统整体性能提供了可行途径。近期的先进方法构建了潜在世界模型,将高维观测映射到紧凑的潜在空间。然而,以往研究提出的世界模型所嵌入的潜在状态可能包含大量与任务无关的信息,导致样本效率低下,且对输入扰动的鲁棒性较差。同时,训练数据分布通常不均衡,所学策略难以应对驾驶过程中的极端情况。为解决上述挑战,我们提出了语义掩码循环世界模型(SEM2),该模型引入语义滤波器提取关键驾驶相关特征,并基于滤波后的特征进行决策;我们还采用多源数据采样器对其进行训练,该采样器将常规数据和多种极端情况数据聚合到单个批次中,以平衡数据分布。在CARLA上开展的大量实验表明,我们的方法在样本效率和对输入扰动的鲁棒性方面优于现有最优方法。

英文摘要:

End-to-end autonomous driving provides a feasible way to automatically maximize overall driving system performance by directly mapping the raw pixels from a front-facing camera to control signals. Recent advanced methods construct a latent world model to map the high dimensional observations into compact latent space. However, the latent states embedded by the world model proposed in previous works may contain a large amount of task-irrelevant information, resulting in low sampling efficiency and poor robustness to input perturbations. Meanwhile, the training data distribution is usually unbalanced, and the learned policy is challenging to cope with the corner cases during the driving process. To solve the above challenges, we present a SEMantic Masked recurrent world model (SEM2), which introduces a semantic filter to extract key driving-relevant features and make decisions via the filtered features, and is trained with a multi-source data sampler, which aggregates common data and multiple corner case data in a single batch, to balance the data distribution. Extensive experiments on CARLA show our method outperforms the state-of-the-art approaches in terms of sample efficiency and robustness to input permutations.

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。

↑