Uncertainty-aware correspondence identification for collaborative perception
Uncertainty-aware correspondence identification for collaborative perception
复制标题
DOI：
10.1007/s10514-023-10086-9
复制
发表时间：
2023-02
影响因子：
3.5
通讯作者：
Peng Gao;Qingzhao Zhu;Hao Zhang-
中科院分区：
文献类型：
--
作者：
Peng Gao;Qingzhao Zhu;Hao Zhang-
对应识别是多机器人协同感知的关键，其目的是识别相同的物体，以确保一组机器人/代理在各自的视野中对物体的一致引用。尽管最近的深度学习方法在对应识别方面显示出令人鼓舞的表现，但它们存在两个缺点，包括无法解决非共见性问题，以及无法量化和减少不确定性以改进对应识别。为了解决这两个问题，我们提出了一种新的不确定性感知深度图匹配方法用于协作感知中的对应识别。我们的新方法将对应识别定义为深度图匹配问题，该问题基于深度图神经网络特征识别对应，并在贝叶斯框架下明确量化识别对应中的不确定性。此外，我们设计了一个新的损失函数，明确地减少了学习过程中的对应不确定性和感知非共视性。最后，我们设计了一种新的多机器人传感器融合方法，该方法集成了给定识别对应的多机器人观测数据，以进行协同目标定位。我们使用高保真仿真和物理机器人来评估我们在协作装配、多机器人协调和互联自动驾驶等机器人应用中的方法。实验表明，我们的方法达到了最先进的通信识别性能。此外，识别出的对象对应关系可以很好地集成到多机器人协作中进行对象定位。
Correspondence identification is essential for multi-robot collaborative perception, which aims to identify the same objects in order to ensure consistent references of the objects by a group of robots/agents in their own fields of view. Although recent deep learning methods have shown encouraging performance on correspondence identification, they suffer from two shortcomings, including the inability to address non-covisibility and the inability to quantify and reduce uncertainty to improve correspondence identification. To address both issues, we propose a novel uncertainty-aware deep graph matching method for correspondence identification in collaborative perception. Our new approach formulates correspondence identification as a deep graph matching problem, which identifies correspondences based on deep graph neural network-based features and explicitly quantify uncertainties in the identified correspondences under the Bayesian framework. In addition, we design a novel loss function that explicitly reduces correspondence uncertainty and perceptual non-covisibility during learning. Finally, we design a novel multi-robot sensor fusion method that integrates the multi-robot observations given the identified correspondences to perform collaborative object localization. We evaluate our approach in the robotics applications of collaborative assembly, multi-robot coordination and connected autonomous driving using high-fidelity simulations and physical robots. Experiments have shown that, our approach achieves the state-of-the-art performance of correspondence identification. Furthermore, the identified correspondences of objects can be well integrated into multi-robot collaboration for object localization.