arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.03155cs.RO
收藏

不确定检测下基于蒙特卡洛规划的无监督主动视觉搜索

Unsupervised Active Visual Search with Monte Carlo planning under Uncertain Detections

University of Verona(维罗纳大学);University of Genoa (UniGe)(热那亚大学);Istituto Italiano di Tecnologia (IIT)(意大利技术研究院);Fondazione Bruno Kessler (FBK)(布鲁诺·凯塞勒基金会)

Francesco Taioli, Francesco Giuliari, Yiming Wang, Riccardo Berra, Alberto Castellini, Alessio Del Bue, Alessandro Farinelli, Marco Cristani, Francesco Setti

AI总结:

针对仅知二维平面图的主动视觉搜索问题,提出无需训练的 POMP-BE-PD,通过信念更新、检测器失效概率建模和蒙特卡洛 POMDP 规划,显著提升成功率并缩短路径。

摘要:

我们提出了一种用于在环境中主动视觉搜索物体的解决方案,其中唯一已知的信息是环境的二维平面图。与现有最先进方法相比,我们的方案具有三个关键特性,使其更加合理并对检测器失效具有鲁棒性:(i)它是无监督的,因为不需要任何训练过程。(ii)在探索过程中,二维平面图上的概率分布会按照一种直观机制进行更新,同时改进的信念更新提高了智能体探索的有效性。(iii)我们利用特定检测器的成功统计信息,将物体检测器可能失效这一认知纳入上述概率建模中。我们的方案称为 POMP-BE-PD(基于 POMCP 的在线运动规划,结合基于探索与概率检测的信念)。它利用智能体当前位姿和 RGB-D 观测来学习最优搜索策略,并采用通过蒙特卡洛规划方法求解的 POMDP。在 Active Vision Database 基准上,相对于竞争方法,我们将所有环境中的平均成功率显著提高了 35%,同时将平均路径长度缩短了 4%。因此,即使没有使用任何训练过程,我们的结果仍达到最先进水平。

英文摘要:

We propose a solution for Active Visual Search of objects in an environment, whose 2D floor map is the only known information. Our solution has three key features that make it more plausible and robust to detector failures compared to state-of-the-art methods: (i) it is unsupervised as it does not need any training sessions. (ii) During the exploration, a probability distribution on the 2D floor map is updated according to an intuitive mechanism, while an improved belief update increases the effectiveness of the agent's exploration. (iii) We incorporate the awareness that an object detector may fail into the aforementioned probability modelling by exploiting the success statistics of a specific detector. Our solution is dubbed POMP-BE-PD (Pomcp-based Online Motion Planning with Belief by Exploration and Probabilistic Detection). It uses the current pose of an agent and an RGB-D observation to learn an optimal search policy, exploiting a POMDP solved by a Monte-Carlo planning approach. On the Active Vision Database benchmark, we increase the average success rate over all the environments by a significant 35% while decreasing the average path length by 4% with respect to competing methods. Thus, our results are state-of-the-art, even without using any training procedure.

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。

↑