arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.00285cs.CVcs.ROcs.SYeess.SY
收藏

虚拟到现实:学习在视觉语义分割中的控制

Virtual-to-Real: Learning to Control in Visual Semantic Segmentation

Elsa Lab(Elsa实验室);Department of Computer Science(计算机科学系);National Tsing Hua University(国立清华大学)
Zhang-Wei Hong, Chen Yu-Ming, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Hsuan-Kung Yang, Brian Hsi-Lin Ho, Chih-Chieh Tu, Yueh-Chuan Chang, Tsu-Ching Hsiao,… 展开作者

Zhang-Wei Hong, Chen Yu-Ming, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Hsuan-Kung Yang, Brian Hsi-Lin Ho, Chih-Chieh Tu, Yueh-Chuan Chang, Tsu-Ching Hsiao, Hsin-Wei Hsiao, Sih-Pin Lai, Chun-Yi Lee

AI总结:

本文提出了一种模块化架构,通过将感知模块和控制策略模块结合,利用语义图像分割作为元表示,解决虚拟到现实的迁移问题,并在障碍避让和目标跟随任务中展示了优越的性能。

摘要:

从物理世界收集训练数据通常是耗时且甚至对脆弱机器人来说是危险的,因此最近的机器人学习进展倡导使用模拟器作为训练平台。不幸的是,合成与真实视觉数据之间的现实差距阻止了在虚拟世界中训练的模型直接迁移到现实世界。本文提出了一种模块化架构来解决虚拟到现实的问题。所提出的架构将学习模型分为感知模块和控制策略模块,并使用语义图像分割作为这些模块之间关联的元表示。感知模块将感知的RGB图像转换为语义图像分割。控制策略模块实现为一个深度强化学习代理,根据转换后的图像分割执行动作。我们的架构在避障任务和目标跟随任务中进行了评估。实验结果表明,我们的架构在虚拟和现实环境中均显著优于所有基线方法,并且比它们具有更快的学习曲线。我们还对各种变体配置进行了详细分析,并验证了我们模块化架构的可迁移性。

英文摘要:

Collecting training data from the physical world is usually time-consuming and even dangerous for fragile robots, and thus, recent advances in robot learning advocate the use of simulators as the training platform. Unfortunately, the reality gap between synthetic and real visual data prohibits direct migration of the models trained in virtual worlds to the real world. This paper proposes a modular architecture for tackling the virtual-to-real problem. The proposed architecture separates the learning model into a perception module and a control policy module, and uses semantic image segmentation as the meta representation for relating these two modules. The perception module translates the perceived RGB image to semantic image segmentation. The control policy module is implemented as a deep reinforcement learning agent, which performs actions based on the translated image segmentation. Our architecture is evaluated in an obstacle avoidance task and a target following task. Experimental results show that our architecture significantly outperforms all of the baseline methods in both virtual and real environments, and demonstrates a faster learning curve than them. We also present a detailed analysis for a variety of variant configurations, and validate the transferability of our modular architecture.

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。

↑