2022 IEEE International Conference on Unmanned Systems (ICUS)最新文献_第10页

Towards Real-time Semantic SLAM Based on Undesired Regions Segmentation 基于非期望区域分割的实时语义SLAM

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987026

Tianci Li, Jingyi Zhou, Junbin Guo, Dan Shen, Qizhen Weng, Xiangwei Zhu

{"title":"Towards Real-time Semantic SLAM Based on Undesired Regions Segmentation","authors":"Tianci Li, Jingyi Zhou, Junbin Guo, Dan Shen, Qizhen Weng, Xiangwei Zhu","doi":"10.1109/ICUS55513.2022.9987026","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987026","url":null,"abstract":"Visual SLAM (vSLAM) is an essential technology for providing robots with position and environment information in unknown environments. But the problem of robustness has not been well solved. For example, the features near the skyline will aggravate the scale drift of monocular SLAM systems, and the existence of challenging dynamic objects violates the static world assumption. In this paper, a robust vSLAM method to remove three undesired regions of the sky, skyline and potentially dynamic objects, building on ORB-SLAM2, is proposed. We incorporate a real-time semantic segmentation network into a vSLAM system to quickly obtain accurate semantic information to eliminate the influence of undesired regions on localization and mapping. In addition, for real-time efficiency, we put the semantic segmentation network in a separate thread and perform semantic segmentation only on keyframes. We conduct monocular and stereo SLAM experiments in 11 sequences (00–10) of the KITTI dataset. The evaluations show that our method achieves a 44.44% accuracy improvement over the baseline ORB-SLAM2 in the best case, and alleviates the scale drift in the monocular case. Compared with DynaSLAM, the advanced dynamic semantic SLAM, our method is slightly more accurate and much faster.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123371442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Three-Dimensional Task Allocation of Multiple-Agent Based on Graph Attention Pointer Network 基于图注意力指针网络的多智能体三维任务分配

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987230

Wen Shi, Kaiwen Wang, Chengpu Yu

引用次数: 0

Gaussian Process based Non-myopic Cooperative Exploration of Multiple Robots 基于高斯过程的多机器人非近视眼协同探索

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986879

Junjie Fu, G. Wen

引用次数: 0

Reliability-Aware Vehicular Communication and Mobility Optimization: Joint Data Transmission Scheduling and Motion Planning 可靠性感知车辆通信和机动性优化:联合数据传输调度和运动规划

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987102

Gangchuan Xu, Jianshan Zhou, Daxin Tian, Chenghao Ren, Xuting Duan, Zhengguo Sheng

{"title":"Reliability-Aware Vehicular Communication and Mobility Optimization: Joint Data Transmission Scheduling and Motion Planning","authors":"Gangchuan Xu, Jianshan Zhou, Daxin Tian, Chenghao Ren, Xuting Duan, Zhengguo Sheng","doi":"10.1109/ICUS55513.2022.9987102","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987102","url":null,"abstract":"Motion planning and vehicular communication are two enabling technologies for the practical realization of connected autonomous vehicles (CAVs), However, few studies have recently provided an effective systematic design from a joint optimization perspective. In our research, we present an optimization system that joins the reliability-oriented cellular vehicle-to-infrastructure communication (V2I) and the multi-objective motion planning into a model predictive control (MPC) model. We propose a stochastic model characterizing the V2I communication reliability and an optimization cost function for the motion planning of a CAV regarding control energy consumption, mobility efficiency, and smoothness. The system model is to maximize the V2I communication reliability meanwhile minimizing the motion cost by jointly optimizing the velocity and data transmission of the vehicle. Using an E-constraint method, we transform the multi-objective optimization model into a tractable problem and propose a numerical optimization algorithm to solve it. Simulation results demonstrate the validity of our joint optimization method for reliability-guaranteed vehicular communication and optimal motion planning and its performance outperforms several baselines.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123692484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A path planning algorithm based on improved RRT* for UAVs 基于改进RRT*的无人机路径规划算法

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986963

Jun-Lin Tian, T. Chao, Ming Yang, Jiahao Zhu, Song-yan Wang

{"title":"A path planning algorithm based on improved RRT* for UAVs","authors":"Jun-Lin Tian, T. Chao, Ming Yang, Jiahao Zhu, Song-yan Wang","doi":"10.1109/ICUS55513.2022.9986963","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986963","url":null,"abstract":"The path planning for UAVs in cluttered environments is one of the keys to ensuring flight missions. This paper considers a more radical strategy based on the informed rapidly exploring random tree star algorithm and presents an improved rapidly exploring random tree star algorithm. In the stage where the feasible path between the starting position and the target position is not searched, the random sampling range is reduced to a variable ellipse whose two focuses are the start and end positions, respectively. The ellipse's major axis depends on an adaptation factor that varies with the number of sample points. The improved rapidly exploring random tree star algorithm can sample in the ellipse at the initial stage of path planning to obtain a higher search efficiency and expand the search range when no feasible path is found for a long time. At the same time, the rapidly exploring random tree, rapidly exploring random tree star, and informed rapidly exploring random tree star algorithms are compared with the proposed improved rapidly exploring random tree star algorithm in simulation. The simulation results show that the improved rapidly exploring random tree star algorithm in this paper can achieve higher search efficiency.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123188726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Imitation Learning Based Simulation Module for Testing Unmanned Surface Vehicle Control System 基于模仿学习的无人水面车辆控制系统仿真测试模块

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986789

Wenjing Zhang, Xiangfeng Ma, Xu Liang, Wei Zhang

{"title":"Imitation Learning Based Simulation Module for Testing Unmanned Surface Vehicle Control System","authors":"Wenjing Zhang, Xiangfeng Ma, Xu Liang, Wei Zhang","doi":"10.1109/ICUS55513.2022.9986789","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986789","url":null,"abstract":"Unmanned surface vehicle (USV) is a kind of robot that can control and execute water surface tasks by satellite positioning and self sensing without human intervention. However, the high costs of labor and the environment-sensitivity property, such as the sea storm and weather condition, contributes to a numerous and complicated testing process of USV control system. Except the aboved, this task also faces the risk of equipment hardware deterioration. In total, the test on USV control system now suffer from various kinds of dilemma, such as high cost on human and material resources, high requirements for conditions, low efficiency, etc. In order to solve the aboved problems, the most urgent matter is to put forward an USV virtual simulation module to support the needs of testing the control system. With the assistant of imitation learning algorithm, we propose a virtual simulation module from a large number of the historical data to construct the virtual simulation environment of USV. Specifically, we combine the behavioral cloning algorithm and the generative adversarial imitation learning algorithm, and get further improvement in several practical problems. Experimental results show that the improved generative adversary imitation learning algorithm converges faster than the baseline generative adversary imitation learning algorithm, and effectively reduce the compound error when comparing with behavior cloning.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116586351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Real-time Measurement of Vibration Frequency of REPDS Based on Vision 基于视觉的REPDS振动频率实时测量

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986997

Xiao Shen, Xin Wang, Derong Chen, Zepeng Wang, Jiulu Gong

引用次数: 0

Research on Trusted Data Sharing Method for Multi-party Edge Terminals 多方边缘终端可信数据共享方法研究

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987168

Yong Pan, Zi-Yao Cheng, Yi Liu, Bowen Wang, Wenhao Wang, Cheng Zhu

引用次数: 0

A Vision/Map Attitude Matrix Aided IMU/Odometer Integrated Navigation Method 视觉/地图姿态矩阵辅助IMU/里程计组合导航方法

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987065

Ziyue Li, Yuchao Liu, Qing-hua Zeng, Jianye Liu, Fangdong Li, Gaorui Zhang

{"title":"A Vision/Map Attitude Matrix Aided IMU/Odometer Integrated Navigation Method","authors":"Ziyue Li, Yuchao Liu, Qing-hua Zeng, Jianye Liu, Fangdong Li, Gaorui Zhang","doi":"10.1109/ICUS55513.2022.9987065","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987065","url":null,"abstract":"In the environment of complex urban roads, problems such as GNSS signal occlusion and multi-path effects caused by tall buildings, overpasses, tunnels, and dense tree canopies have brought great technical challenges to the navigation and positioning system of autonomous vehicles. In the GNSS-denied environment (such as signal occlusion and interference), the accuracy of the integrated navigation system will drop rapidly due to incomplete odometer measurement information. To solve this problem, we proposes a vision/map attitude matrix aided IMU/odometer integrated navigation system scheme. The scheme first obtains the direction, slope, and cross slope angle information of the road through positioning and high-precision maps, and constructs a road attitude matrix. Then, the scheme uses computer vision technology to calculate the angle between the vehicle and the lane line, and then obtains the vehicle attitude matrix based on vision/map information, realizing the decoupling of the odometer measurement information and the IMU attitude matrix. Based on the factor graph model, we implemented the above-mentioned multi-sensor fusion positioning algorithm and used the Matlab simulation platform to verify the performance of the algorithm. The experimental results show that our algorithm achieves a significant improvement in the accuracy of the IMU/odometer integrated navigation system in a GNSS-denied environment, which will help to promote the engineering and application of autonomous driving technology in complex environments.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133940448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Construction Method of Digital Twin USV Capability Model 数字孪生USV能力模型的构建方法

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986594

Zishuai Wang, Wei Han, Sheng-Li Song, Fuyu Luo, Rulei Liu, Wei Wang

引用次数: 0