POMP：基于Pomcp的室内主动视觉搜索在线运动规划
POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
摘要：
在本文中，我们专注于学习的最佳策略的问题，主动视觉搜索（AVS）的对象在已知的室内环境与在线设置。我们的POMP方法使用代理（例如机器人）的当前姿势和RGB-D帧作为输入。任务是计划下一步行动，使代理更接近目标对象。我们将此问题建模为部分可观测马尔可夫决策过程，通过蒙特卡洛规划方法求解。这使我们能够通过迭代手头的已知场景，同时探索环境和搜索对象来决定下一步的行动。从强化学习的当前技术水平来看，POMP不需要大量和昂贵的（在时间和计算上）标记数据，因此在解决中小型真实场景中的AVS时非常灵活。我们只需要环境的平面图的信息，通常可用的信息或可以很容易地从先验的单次探索运行中提取的信息。我们在公开的AVD基准上验证了我们的方法，平均成功率为0.76，平均路径长度为17.1，接近最先进的水平，但不需要任何培训。此外，我们的实验表明，我们的方法的鲁棒性时，目标检测的质量从理想到故障。
英文摘要：
In this paper we focus on the problem of learning an optimal policy for Active Visual Search (AVS) of objects in known indoor environments with an online setup. Our POMP method uses as input the current pose of an agent (e.g. a robot) and a RGB-D frame. The task is to plan the next move that brings the agent closer to the target object. We model this problem as a Partially Observable Markov Decision Process solved by a Monte-Carlo planning approach. This allows us to make decisions on the next moves by iterating over the known scenario at hand, exploring the environment and searching for the object at the same time. Differently from the current state of the art in Reinforcement Learning, POMP does not require extensive and expensive (in time and computation) labelled data so being very agile in solving AVS in small and medium real scenarios. We only require the information of the floormap of the environment, an information usually available or that can be easily extracted from an a priori single exploration run. We validate our method on the publicly available AVD benchmark, achieving an average success rate of 0.76 with an average path length of 17.1, performing close to the state of the art but without any training needed. Additionally, we show experimentally the robustness of our method when the quality of the object detection goes from ideal to faulty.
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。
