C. Zhou, Huijun Di, Shaohang Xu, Chaoran Wang, Guang-ming Xiong, Jian-wei Gong
{"title":"Obstacle Detection Based on Logistic Regression in Unstructured Environment","authors":"C. Zhou, Huijun Di, Shaohang Xu, Chaoran Wang, Guang-ming Xiong, Jian-wei Gong","doi":"10.1109/ICUS48101.2019.8995921","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8995921","url":null,"abstract":"Obstacles in off-road environments can pose a greater risk to autonomous vehicles, so it is necessary to accurately detect obstacles. This paper proposes an obstacle detection method based on logistic regression. In order to extract the obstacle features better, we first project the discrete point cloud data into the two-dimensional depth map, and then we extract the height difference value and distance difference value between the pixels neighborhoods, after that we use the logistic regression to train and get the corresponding parameters. Combining the training parameters and the extracted effective features, we can obtain the passable probability in the depth map coordinates, and then back-project the depth map pixels into the two-dimensional grid map to obtain the final passable region result. We conduct a number of experiments and the results demonstrate the effectiveness of our method. Furthermore, our method meets the requirements of real-time applications and provides accurate environmental information for unmanned vehicle decision-making and planning.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127961903","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}
{"title":"Connected Cruise Control Systems Of Intelligent And Connected Vehicle With Acceleration Feedback","authors":"Hui Sun, Zhiyu Xi","doi":"10.1109/ICUS48101.2019.8995941","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8995941","url":null,"abstract":"In this paper, we propose the connected cruise control (CCC) algorithm by analyzing human driver behavior, based on which a dynamic model is established for intelligent and connected vehicle (ICV). Changing values of model parameters, the CCC vehicle and the human-driven vehicle can be represented at the same time in this unified model. As a result, while ensuring the string stability of the platoon, the CCC algorithm does not require the same model parameters and control algorithms for the members of the platoon as comparative of the cooperative adaptive cruise control (CACC) algorithm, which improves its practicality under the real road conditions. A Lyapunov equation is used to verify the stability of the CCC vehicle and the string stability of the CCC platoon is verified in the two-predecessors following condition, while stability constraints on the model parameters are also given. Simulations are performed to verify the stability of dynamic models and the string stability of CCC platoon for different parameters.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125359971","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}
{"title":"The Research on Simulation Technology for multi-aircraft cooperative guidance","authors":"Li Jing, Shen Chao, Tong Jiahui","doi":"10.1109/ICUS48101.2019.8995914","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8995914","url":null,"abstract":"In this paper, the composition and operation mechanism of a multi-aircraft cooperative simulation system is analyzed, with its formal architecture identified as a discrete event system & differential equation system specifications (DEV&DESS). Then, the operation and control problem of the cooperative simulation system is converted into the simulation control problem of a specific DEV&DESS system. A coordinator-based test method for cooperative simulation is proposed and validated by tests of real-time mathematical simulation.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123086942","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}
{"title":"Robust 3-D low-altitude airdrop flight control via the sigmoid function-based observer","authors":"Zikang Su, Zunkun Cheng, Honglun Wang","doi":"10.1109/ICUS48101.2019.8996031","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8996031","url":null,"abstract":"A robust 3-D trajectory tracking controller for the low-altitude airdrop of the transport aircraft is established in the presence of airflow disturbances, by combining the back- stepping technique and sigmoid function-based disturbance observer. The transport aircraft’s nonlinear dynamics during the low-altitude airdrop process is modeled in the affine nonlinear form which consists of the effect of the movement and abrupt drop of the heavy cargo, the ground effect, and the airflow disturbances. The three-dimensional airdrop flight controller design is divided into several cascade subsystems, via the back-stepping technique. In each subsystem dynamic, items caused by the disturbances during the extraction are viewed as part of the \"lumped disturbances\". They are individually reconstituted and compensated via the sigmoid function-based disturbance observers with high estimation accuracy and nice disturbance attenuation ability. With the estimated the lumped disturbances, an anti-disturbance 3-D back-stepping based controller is proposed for the low-altitude airdrop. Simulations are carried out to verify the proposed control method’s effectiveness in improving the robustness and tracking accuracy.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126097309","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}
{"title":"Coordinated Motion Planning of Dual-arm Space Robot with Deep Reinforcement Learning","authors":"Mengying Tang, Xiaofei Yue, Zhan Zuo, Xiaoping Huang, Yanfang Liu, N. Qi","doi":"10.1109/ICUS48101.2019.8996069","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8996069","url":null,"abstract":"In this paper, we focus on coordinated motion planning of dual-arm robot. The kinematics model of the robotic arm is established by Denavit-Hartenberg (D-H) coordinate method and the mathematical model of the cooperative motion planning problem is established. The rapidly-exploring random trees (RRT) algorithm and the deep deterministic policy gradient (DDPG) algorithm are used to carry out dual-arm coordinated motion planning, respectively. The simulation results show that these algorithms can effectively complete the robot arm motion planning task, but the RRT improved algorithm cannot balance the planning efficiency and result optimization. Compared with the RRT algorithm, the DDPG algorithm trains the model through continuous trial and error to optimize its planning strategy. The trained model can be used to obtain an optimized path and it can ensure the efficiency of the planning with the optimized strategy.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115309768","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}
{"title":"Adaptive Path Planning for Unmanned Planetary Rover with Dynamic Obstacle","authors":"Zhang Wenyuan, Guo Jifeng, Bai Chengchao","doi":"10.1109/ICUS48101.2019.8996050","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8996050","url":null,"abstract":"More and more wheeled planetary probes have been applied to exploration missions in order to realize the exploration of extraterrestrial planets. In order to ensure the ability to perform tasks in complex environments, planetary vehicles need the ability of autonomous path planning and obstacle avoidance. In this paper, RRT* and dynamic window approach are combined to complete autonomous path planning and dynamic obstacle avoidance under the dynamic environment with some prior map information. The simulation and physical verification under ROS development platform and Jackal unmanned vehicle platform are realized. It provides ideas for path planning and obstacle avoidance of unmanned planetary vehicles in static and dynamic environments.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121213270","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}
Tonghuazhai Xu, Nan Wang, Hongtao Lin, Zhaomei Sun
{"title":"UAV Autonomous Reconnaissance Route Planning Based on Deep Reinforcement Learning","authors":"Tonghuazhai Xu, Nan Wang, Hongtao Lin, Zhaomei Sun","doi":"10.1109/ICUS48101.2019.8995935","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8995935","url":null,"abstract":"In order to improve the autonomous reconnaissance efficiency of unmanned aerial vehicle (UAV) in an uncertain environment, situation and observation information acquired by UAV are input into the replay buffer. Model-free training is performed on the data of the replay buffer by deep reinforcement learning (DRL) method, so as to generate the corresponding network model. The reward function is designed for UAV regional reconnaissance missions to further improve the generalization ability of the model. The simulation results show that the UAV autonomous reconnaissance route planning algorithm based on DRL has a high degree of sustainable coverage and its patrol path is unpredictable.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125176279","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}
W. Jia-liang, Song Chuang, Lin Lijun, Fan Yu, Hao Mingrui
{"title":"Coupling control design for the lateral system of lifting body airerafts based on the sliding mode disturbanee observer","authors":"W. Jia-liang, Song Chuang, Lin Lijun, Fan Yu, Hao Mingrui","doi":"10.1109/ICUS48101.2019.8996002","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8996002","url":null,"abstract":"For large lifting body plane symmetric aircrafts, lateral maneuvering near the target may cause severe aerodynamic coupling between the lateral channels, possibly resulting in instability of the rolling channel. Aiming at this kind of coupling problem, the lateral system is decomposed based on the singular perturbation theory, and the cascade model of the inner and the outer loops is established. The outer loop is used as an example to design the sliding mode (SM) control law, and the stability of the closed-loop system is analyzed. The sliding mode disturbance observer (SMDO) is also employed to estimate and compensate for the coupling term and improves the robustness of the rolling channel against the lateral coupling. Simulation results show that the designed controller has good dynamic characteristics and anti-disturbance ability, improving the robustness and performance of the control system.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122456483","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}
{"title":"Multi-UGV Experimental Platform Based on Cloud and Edge Control: Design and Implementation","authors":"Rui Hu, Yuanqing Xia, Min Lin, Shuang Wu","doi":"10.1109/ICUS48101.2019.8995965","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8995965","url":null,"abstract":"This paper presents a novel framework of a multi-UGV experimental platform based on cloud and edge control. Cloud control is introduced to the framework aiming at the problems caused by increasing amount of data as the number of UGV increases. In order to ensure the real-time control, edge control is also adopted in the framework. In addition, cloud workflow scheduling is considered in this paper, which involves finding the optimal mapping between computing resources and work tasks. An experiment of consensus-based dynamic role assignment was implemented on the designed platform to verify the feasibility and reliability in multi-UGV control.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127631266","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}
{"title":"Research on Adaptive Fusion Tracking Algorithm for Bearings-Only Measurement","authors":"Kun Yang, C. Jiang, Ming Li","doi":"10.1109/ICUS48101.2019.8995998","DOIUrl":"https://doi.org/10.1109/ICUS48101.2019.8995998","url":null,"abstract":"Target tracking is one of the key technologies in the military application of wireless sensor networks. This paper aims at the characteristics of wireless sensor network nodes, which have limited computing capacity but can conduct data fusion through wireless communication, to improve tracking accuracy from two aspects. On the one hand, an adaptive bias- compensated pseudo-measurement Kalman filter based on process noise is proposed, on the other hand, an adaptive weighted fusion algorithm based on innovation is proposed. Through multiple simulations, the proposed algorithms can significantly improve the tracking accuracy and robustness of the system on the premise of low computational complexity.","PeriodicalId":344181,"journal":{"name":"2019 IEEE International Conference on Unmanned Systems (ICUS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116756228","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}