arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.02870cs.AIcs.CVcs.RO
收藏

用于机器人任务执行和监控的视觉搜索和识别

Visual search and recognition for robot task execution and monitoring

Sapienza University of Rome(罗马第一大学)

Lorenzo Mauro, Francesco Puja, Simone Grazioso, Valsamis Ntouskos, Marta Sanzari, Edoardo Alati, Fiora Pirri

摘要:

在环境中进行相关目标的视觉搜索是机器人的一项重要技能。我们提出了一个初步的框架,机器人任务的执行监视器,照顾机器人的态度,以视觉搜索环境中涉及的任务的目标。视觉搜索也与从故障中恢复有关。该框架利用深度强化学习来获取"常识"场景结构,并利用深度卷积网络来检测对象及其之间的相关关系。该框架建立在这些方法的基础上,引入了基于视觉的执行监控,它使用经典的规划作为任务执行的骨干。实验结果表明,提出的基于视觉的执行监视器的机器人可以完成简单的任务,并可以从故障中恢复自主。

英文摘要:

Visual search of relevant targets in the environment is a crucial robot skill. We propose a preliminary framework for the execution monitor of a robot task, taking care of the robot attitude to visually searching the environment for targets involved in the task. Visual search is also relevant to recover from a failure. The framework exploits deep reinforcement learning to acquire a "common sense" scene structure and it takes advantage of a deep convolutional network to detect objects and relevant relations holding between them. The framework builds on these methods to introduce a vision-based execution monitoring, which uses classical planning as a backbone for task execution. Experiments show that with the proposed vision-based execution monitor the robot can complete simple tasks and can recover from failures in autonomy.

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。

↑