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 2406.01544cs.ROcs.AIcs.LG
收藏

基于失败的有效性学习:缓解自动驾驶规划中的分布偏移

Validity Learning on Failures: Mitigating the Distribution Shift in Autonomous Vehicle Planning

Noah’s Ark Lab, Huawei Technologies Canada(诺亚方舟实验室,加拿大华为技术公司)

Fazel Arasteh, Mohammed Elmahgiubi, Behzad Khamidehi, Hamidreza Mirkhani, Weize Zhang, Cao Tongtong, Kasra Rezaee

AI总结:

针对自动驾驶模仿学习中的协变量偏移问题,提出基于失败的有效性学习方法。通过收集预训练规划器的失败状态构建数据集,并引入VL目标在无专家标注下从闭环错误中学习有效轨迹,显著提升了闭环指标并大幅超越现有最先进方法。

摘要:

规划问题是自动驾驶框架的基本组成部分。近期表征学习的进展使车辆能够理解周围环境,从而促进了基于学习的规划策略的整合。在这些方法中,Imitation Learning(模仿学习)因其显著的训练效率而脱颖而出。然而,传统的Imitation Learning方法面临co-variate shift(协变量偏移)现象的挑战。我们提出Validity Learning on Failures(基于失败的有效性学习),简称VL(on failure),作为解决此问题的补救措施。我们方法的本质在于将预训练规划器部署到各种场景中。规划器偏离其即时目标(例如与障碍物保持安全距离或遵守交通规则)的实例被标记为失败。与这些失败对应的状态被编译成一个新数据集,称为failure dataset(失败数据集)。值得注意的是,由于该数据缺乏专家标注,标准模仿学习方法无法适用。为了促进从闭环错误中学习,我们引入了VL目标,旨在当前环境上下文中识别有效轨迹。在反应式CARLA仿真和非反应式日志重放仿真上进行的实验评估表明,Score、Progress和Success Rate等闭环指标有显著提升,凸显了所提方法的有效性。在Bench2Drive基准上的进一步评估表明,VL(on failure)大幅优于现有最先进方法。

英文摘要:

The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their surrounding environments, thereby facilitating the integration of learning-based planning strategies. Among these approaches, Imitation Learning stands out due to its notable training efficiency. However, traditional Imitation Learning methodologies encounter challenges associated with the co-variate shift phenomenon. We propose Validity Learning on Failures, VL(on failure), as a remedy to address this issue. The essence of our method lies in deploying a pre-trained planner across diverse scenarios. Instances where the planner deviates from its immediate objectives, such as maintaining a safe distance from obstacles or adhering to traffic rules, are flagged as failures. The states corresponding to these failures are compiled into a new dataset, termed the failure dataset. Notably, the absence of expert annotations for this data precludes the applicability of standard imitation learning approaches. To facilitate learning from the closed-loop mistakes, we introduce the VL objective which aims to discern valid trajectories within the current environmental context. Experimental evaluations conducted on both reactive CARLA simulation and non-reactive log-replay simulations reveal substantial enhancements in closed-loop metrics such as \textit{Score, Progress}, and Success Rate, underscoring the effectiveness of the proposed methodology. Further evaluations against the Bench2Drive benchmark demonstrate that VL(on failure) outperforms the state-of-the-art methods by a large margin.

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。

↑