Touch-based object localization is an important component of autonomous robotic systems that are to perform dexterous tasks in real-world environments. When the objects to locate are placed within clutters, this touch-based procedure tends to generate outlier measurements which, in turn, can lead to a significant loss in localization precision. Our first contribution is to address this problem by applying the RANdom SAmple Consensus (RANSAC) method to a Bayesian estimation framework. As RANSAC requires repeatedly applying the (computationally intensive) Bayesian updating step, it is crucial to improve that step in order to achieve practical running times. Our second contribution is therefore a fast method to find the most probable object face that corresponds to a given touch measurement, which yields a significant acceleration of the Bayesian updating step. Experiments show that our overall algorithm provides accurate localization in practical times, even when the measurements are corrupted by outliers.
Uncertainty-aware Gaussian Mixture Model for UWB Time Difference of Arrival Localization in Cluttered Environments
University of Toronto(多伦多大学);University of Toronto Robotics Institute(多伦多大学机器人研究所);Vector Institute for Artificial Intelligence(矢量人工智能研究所);Technical University of Munich(慕尼黑工业大学);Munich Institute for Robotics and Machine Intelligence(慕尼黑机器人与机器智能研究所)
Navigating by Touch: Haptic Monte Carlo Localization via Geometric Sensing and Terrain Classification
Oxford Robotics Institute, University of Oxford(牛津大学牛津机器人研究所);Institute of Robotics and Machine Intelligence, Poznan University of Technology(波兹南理工大学机器人与机器智能研究所)
Localization and Control of Magnetic Suture Needles in Cluttered Surgical Site with Blood and Tissue
Johns Hopkins University(约翰斯·霍普金斯大学);University of Maryland, College Park(马里兰大学帕克分校);Weinberg Medical Physics, Inc.(温伯格医学物理公司)
针的实时视觉定位对于各种手术应用是必要的,包括手术自动化和视觉反馈。在这项研究中,我们调查的背景下,我们的磁共振系统的针的定位和自主机器人控制。我们的系统具有手术操作的潜力,具有微创和减少患者副作用的优点。然而,非线性磁场会产生非直观的力,并需要精细的基于位置的控制,这超出了人类直接操纵的能力。这使得自动针定位成为必要。我们的定位方法结合了基于神经网络的分割和经典技术,并且我们能够在清洁环境中以0.73 mm RMS误差和在具有血液和闭塞的挑战性环境中以2.72 mm RMS误差一致地定位我们的针。对于我们在实验中使用的所有环境,平均定位RMS误差为2.16 mm。我们结合我们的闭环反馈控制系统的本地化方法,以证明本地化自主控制的进一步适用性。我们的缝针能够在(1)无血液,无组织;(2)大量血液,无组织;(3)无血液,有组织;和(4)大量血液,有组织环境中遵循连续缝合路径。尖端位置跟踪误差范围为2.6 mm至3.7 mm RMS,为自主导航任务打开了大门。
Drones Guiding Drones: Cooperative Navigation of a Less-Equipped Micro Aerial Vehicle in Cluttered Environments
Multi-robot Systems Group, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague(多机器人系统组,控制系,电气工程系,捷克技术大学)
EGO-Swarm: A Fully Autonomous and Decentralized Quadrotor Swarm System in Cluttered Environments
Zhejiang University(浙江大学);National Engineering Research Center for Industrial Automation (Ningbo Institute)(国家工业自动化工程技术研究中心(宁波研究院));Huzhou Institute, Zhejiang University(浙江大学湖州研究院)
UTIL: An Ultra-wideband Time-difference-of-arrival Indoor Localization Dataset
University of Toronto Institute for Aerospace Studies (UTIAS)(多伦多大学航空航天研究所);University of Toronto Robotics Institute(多伦多大学机器人研究所);Vector Institute for Artificial Intelligence(向量人工智能研究所);Technical University of Munich(慕尼黑工业大学);Munich Institute for Robotics and Machine Intelligence (MIRMI)(慕尼黑机器人与机器智能研究所)
MDF: Multi-Modal Data Fusion with CNN-Based Object Detection for Enhanced Indoor Localization Using LiDAR-SLAM
Department of Artificial Intelligence Convergence, Pukyong National University(人工智能融合系,浦项国立大学);School of Computer Science, University of Nottingham Ningbo China(计算机科学学院,诺丁汉国际大学)
3-D Volumetric Gamma-ray Imaging and Source Localization with a Mobile Robot
Carnegie Mellon University(卡内基梅隆大学);University of Michigan(密歇根大学)
迄今为止,辐射检测主要是使用点传感器(例如盖革-穆勒计数器和闪烁光谱仪)的人工检查过程。虽然他们对源接近度的观察证明是有用的,但他们缺乏在具有多个辐射源的杂乱环境中有效源定位和表征所必需的方向信息。康普顿伽马相机最近的商业化首次为更广泛的辐射探测界提供了方向信息。本文介绍了一个自定位地面机器人精确的三维辐射映射的康普顿伽马相机的集成。使用机器人的位置和取向,在共享参考系中的遍历路径上累积来自伽马相机的辐射图像,以构建一致的基于体素网格的辐射图。在预先指定的能量窗口处的图的峰值被选择为源位置估计,其与地面实况源位置进行比较。所提出的方法在两个5 x 4 m^2和14 x 6 m^2的实验室环境中将多个源定位到平均0.2 m以内。
Mobile Robot Localization Using a Novel Whisker-Like Sensor
Touch Lab, Center for Virtual Reality and Haptics, Indian Institute of Technology Madras(触觉实验室、虚拟现实与触觉中心、印度理工学院马德拉斯学院);Center for Ubiquitous Computing, Faculty of Information Technology and Electrical Engineering, University of Oulu(无处不在计算中心、信息科技与电气工程学院、奥卢大学)
TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environments
Amazon Fulfillment Technologies & Robotics(亚马逊履约技术与机器人);Siebel School of Computing and Data Science, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校西贝尔计算与数据科学学院);Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所)
Split Deep Q-Learning for Robust Object Singulation
Aristotle University of Thessaloniki(塞萨洛尼基亚里士多德大学);Information Technologies Institute (ITI) Center of Research and Technology Hellas (CERTH)(希腊研究与技术中心信息技术研究所)