Explore, Approach, and Terminate: Evaluating Subtasks in Active Visual Object Search Based on Deep Reinforcement Learning
Explore, Approach, and Terminate: Evaluating Subtasks in Active Visual Object Search Based on Deep Reinforcement Learning
复制标题
DOI：
10.1109/iros40897.2019.8967805
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Jan Fabian Schmid;M. Lauri;S. Frintrop
中科院分区：
文献类型：
--
作者：
Jan Fabian Schmid;M. Lauri;S. Frintrop
搜索对象并将任务相关对象与其他对象区分开是服务机器人的关键要求。我们提出了一个强化学习解决方案的主动视觉对象搜索问题。我们的方法成功地学习探索环境，接近目标对象，并决定何时终止搜索的目标对象已被发现。我们证明了我们的解决方案的效率，由机器人收集的真实世界的图像数据集。我们的方法优于状态空间规划或其他基线搜索策略，在更短的时间内达到更高的成功率。我们还研究了主动视觉对象搜索的各个子任务。尽管子任务存在强大的基线，但我们的RL解决方案在整体搜索任务中优于它们。
Searching for objects and distinguishing task-relevant objects from others is a key requirement for service robots. We propose a reinforcement learning solution to the active visual object search problem. Our method successfully learns to explore the environment, to approach the target object, and to decide when to terminate the search as the target object has been found. We demonstrate the efficiency of our solution on a dataset of real-world images collected by a robot. Our approach outperforms state-space planning or other baseline search strategies, reaching a higher success rate in a shorter time. We also study individual subtasks of active visual object search. Although strong baselines exist for the subtasks, our RL solution outperforms them in the overall search task.