- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - DOSeqSLAM: Dynamic On-line Sequence Based Loop Closure Detection Algorithm for SLAM
摘要： Simultaneous Localization and Mapping (SLAM) is vital for modern autonomous robots. Visual place recognition of pre-visited areas, widely known as Loop Closure Detection (LCD), constitutes one of the most important SLAM components. In this paper a sequence-based LCD algorithm is proposed by evolving SeqSLAM method. Instead of using fixed-size sequences’ length during search process, as in the original approach, we suggest a dynamical length definition based on the images’ content proximity. Specifically, sequence segmentation is achieved through a feature matching technique applied on the incoming visual sensory information, while the mechanism operates on-line without the need of any pre-training procedure. Each sequence’s similarity score, produced by a weighted average function, is utilized as a decision factor for the loop closing selection. Finally, an extended image-to-image search in the chosen group of images, avails the system of identifying the appropriate match. A temporal constraint prevents early pre-visited areas to be presented as false-positive matches. The method is evaluated on several outdoor publicly-available datasets, revealing a substantial improvement on SeqSLAM.
关键词： feature matching,Simultaneous Localization and Mapping (SLAM),Loop Closure Detection (LCD),SeqSLAM,dynamic sequence length
更新于2025-09-09 09:28:46
-
[IEEE 2018 IEEE International Conference on Intelligent Transportation Systems (ITSC) - Maui, HI, USA (2018.11.4-2018.11.7)] 2018 21st International Conference on Intelligent Transportation Systems (ITSC) - Automatic Vector-based Road Structure Mapping Using Multi-beam LiDAR
摘要： In this paper, we studied a SLAM method for vector-based road structure mapping using multi-beam LiDAR. We proposed to use the polyline as the primary mapping element instead of grid cell or point cloud, because the vector-based representation is precise and lightweight, and it can directly generate vector-based High-Definition (HD) driving map as demanded by autonomous driving systems. We explored: 1) the extraction and vectorization of road structures based on local probabilistic fusion. 2) the efficient vector-based matching between frames of road structures. 3) the loop closure and optimization based on the pose-graph. In this study, we took a specific road structure, the road boundary, as an example. We applied the proposed matching method in three different scenes and achieved the average absolute matching error of 0.07m. We further applied the vector-based mapping system to a road with the length of 860 meters and achieved an average global accuracy of 0.466m without the aid of GPS.
关键词： vector-based mapping,autonomous driving,multi-beam LiDAR,road boundary,SLAM
更新于2025-09-04 15:30:14
-
[IEEE 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) - Wuhan, China (2018.3.22-2018.3.23)] 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) - Real time UGV positioning based on Reference beacons aided LiDAR scan matching
摘要： in this paper, a real time positioning experiment based on reference beacons aided LiDAR scan matching is designed and conducted. In the experiment, we utilize a robot platform that integrates IMU and 2D LiDAR sensor, to scan matching with prepared 2D environment feature map, which includes the information of reflection beacons. Robot platform estimated heading and position change by point-cloud-based pattern match algorithm –Occupied Grid Gauss - Newton Matching. In featureless area, where scan matching is easy to failure, low-cost reference beacons not only can enrich environmental features, but also can improve indoor position accuracy by adding calibration information in scan matching. The trajectory and positioning result of robot platform prove that the proposed method can provide accurate and reliable navigation and position, with fewer reference beacons, compared to traditional completely laser reflection beacons localization method for Warehouse UGV.
关键词： Reference beacon,Warehouse UGV,SLAM,LiDAR
更新于2025-09-04 15:30:14
-
[IEEE 2018 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) - Bangkok, Thailand (2018.10.21-2018.10.24)] 2018 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) - Research on Laser Navigation Mapping and Path Planning of Tracked Mobile Robot Based on Hector SLAM
摘要： Artificial intelligence and automation technology that can satisfy the ever-increasing demand for technology in industrial, commercial, medical, military and civil fields has introduced new opportunities for robotics research in past decades. In particular, the mobile robot laser navigation has always been the focus and problems in fields covering a wide spectrum of disciplines. The object of this study was to explore the mapping of mobile robot based on Hector-SLAM algorithm and the simulation experiment of the global path planning in static environments. A tracked mobile robot is designed for navigation test platform, which is mainly composed of two dimensional laser radar called Neato XV-11 laser, mobile robot chassis, PC terminal and an Android phone. The motion control commands of robot platform are published by smart phone and executed via Python code in Raspberry Pi board. After algorithm procedure for Hector SLAM are represented in depth, the map building in this way is completed on Robot Operating System (ROS) where RVIZ is run to carry out cartographic visualization. On the other hand, a new ant colony algorithm(ACO), which introduces pheromone orientation, is proposed for the issue about robot shortest path planning in static environment. The results of mapping obtained on ROS show a satisfactory level of indoor environment, which reveals the feasibility of our approach in laser navigation. Furthermore, it is proved from the simulation experiments of modified ACO algorithm that the new algorithm not only can obtain the same optimal path, but also has faster convergence speed and smaller error peak in complex static environments.
关键词： mapping,ant colony algorithm,laser navigation,Hector SLAM,path planning,mobile robot
更新于2025-09-04 15:30:14
-
[IEEE 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) - Wuhan, China (2018.3.22-2018.3.23)] 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) - Monocular Visual-Inertial State Estimation With Online Temporal Calibration
摘要： In most of visual-inertial state estimation frameworks, camera is usually assumed synchronized with inertial measurement unit (IMU). However, in practice, the timestamps of camera and IMU are typically affected by a time-varying delay, especially for low-cost IMU-camera integrated system (e.g. android phone). Tracking failures could occur easily then. In this paper, we discuss the effect of the temporal offset on map points triangulation and nonlinear optimization during visual-inertial simultaneous localization and mapping (SLAM) process, and propose two feasible solutions for compensating the offset between camera and IMU. We choose the simpler solution and propose a computationally tractable approach which can estimate the offset with all other variables of interest (the IMU pose, the camera-IMU calibration, etc.). Our simulation results demonstrate that the proposed approach is effective in scenarios involving both constant and time-varying offsets.
关键词： visual-inertial state estimation,camera,temporal calibration,SLAM,IMU
更新于2025-09-04 15:30:14