Jiangnan Li, Jian-wei Gong, Guojie Kong, Yaogang Zhao, Xi Zhang
{"title":"A Hierarchical Trajectory Planning Framework for Autonomous Driving","authors":"Jiangnan Li, Jian-wei Gong, Guojie Kong, Yaogang Zhao, Xi Zhang","doi":"10.1109/ICUS50048.2020.9274923","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274923","url":null,"abstract":"In this paper, we introduce a layered trajectory planning method for autonomous vehicles. The trajectory planning problem is decomposed into three parts: path planning, speed planning, and path-speed iteration. In the path planning section, we combine the advantages of search-based and optimization based methods. Firstly, we use different search-based methods for safe navigation and then smooth the searched path to get a high-quality reference path. Secondly, the path planning problem under the Frenet frame is formulated as a quadratic program (QP), which can be solved efficiently. Then a speed profile is generated based on the planned path. Furthermore, we propose an iterative strategy for path planning and speed planning to ensure the feasibility of the planned trajectory. Our algorithm is implemented in C++, and the path planning part is open-sourced on our GitHub page 1.1Please visit https://github.com/LiJiangnanBit/path-optimizer to get the source code.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128637364","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}
Nuo Ma, Moning Li, Xiaozhu Li, Junhui Meng, Li Liu
{"title":"Aerodynamic Optimal Design of Guided Bullets Based on Improved Orthogonal Test","authors":"Nuo Ma, Moning Li, Xiaozhu Li, Junhui Meng, Li Liu","doi":"10.1109/ICUS50048.2020.9274998","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274998","url":null,"abstract":"With the development and miniaturization of guidance technology, guided bullets have revolutionaryly improved the accuracy and survivability of sniper. Different from the designing of traditional bullets that focus on minimizing drag, the guidance raises the requirement of high lift-drag ratio of guided bullets during maneuvering to ensure the efficiency of maneuver and the ability of storing energy. In this paper, based on the improved orthogonal test optimization, the boundary between each segment of the projectile is selected as the control factors, and lift-drag ratio under the maximum rudder deflection is set as the objective factor to optimize aerodynamic shape of the guided bullet. In terms of conclusion, the maximum lift-drag ratio is increased by about 80%, which shows that the optimization has significant effect. The proposed new method improves the searching ability while taking the processing capacity of the control factors and computational cost of orthogonal test into account. It has certain significance for the solution of low-dimensional unconstrained optimization problems and provides a reference for the design of guided bullets.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126517030","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-target threat assessment in unmanned cluster confrontation scenarios","authors":"Hualin Chen, Xiaowen Cao, Yin Hao, Jieru Fan, Derong Chen, Dexia Chen","doi":"10.1109/icus50048.2020.9274929","DOIUrl":"https://doi.org/10.1109/icus50048.2020.9274929","url":null,"abstract":"Threat assessment is a key module of the unmanned intelligent platform decision-making system. This paper mainly studies the target threat assessment in multiparty unmanned cluster confrontation scenarios. First, a three-level threat assessment functional model is established, and the target intent is regarded as a tactical threat, the threat assessment index system has been improved. Then the Adaboost algorithm is introduced into the threat assessment problem, and on this basis, the Adaboost algorithm is improved by building a various meta-learner algorithm library, which reduces the algorithm’s error rate. Finally, the threat assessment based on improved Adaboost is simulated, and the results show that the algorithm can be used in the threat assessment of multi-party unmanned cluster confrontation scenarios.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122907636","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":"Evaluation Index System for Autonomous Capability of the Ground-attack UAV","authors":"Yuxuan Feng, Shuguang Liu, Wujie Xie","doi":"10.1109/ICUS50048.2020.9274815","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274815","url":null,"abstract":"The evaluation of autonomous capability for ground-attack unmanned aerial vehicle (UAV) comes from the demand of troops. The level of autonomous capability determines the operational use of man-machine authority, such as allocation time, allocation content and allocation amount. Constructing a scientific evaluation index system is the first task to evaluate autonomous capability. Based on the analysis of airborne equipment system, 31 airborne equipment parameters are selected as the underlying indicators for autonomous capability evaluation from four aspects of observation capability, decision capability, action capability and security capability(ODAS),which provide the standard for the effective man-machine authority division.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134019110","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":"Development Status and Key Navigation Technology Analysis of Autonomous Underwater Vehicles","authors":"Zhi Li, Yilin Wang, Wenvu Yang, Yunfang Ji","doi":"10.1109/ICUS50048.2020.9274926","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274926","url":null,"abstract":"As an important tool for ocean exploration, Autonomous Underwater Vehicle (AUV) plays an important role in the exploration and development of marine resources, diving support, underwater search and rescue and military reconnaissance. The accuracy of AUV underwater navigation technology is a powerful guarantee for carrying out tasks such as search, detection and anti-submarine underwater. In this paper, the research status of AUVs is reviewed, the key navigation technologies are introduced in detail. Furthermore, the development prospect of AUV Navigation Technology is predicted.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122376330","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}
Kaiqiang Wang, Z. Gong, Yanze Hou, Minjie Zhang, C. Liu, Runfeng Chen
{"title":"Model Based Design and Procedure of Flight Control System for Unmanned Aerial Vehicle","authors":"Kaiqiang Wang, Z. Gong, Yanze Hou, Minjie Zhang, C. Liu, Runfeng Chen","doi":"10.1109/ICUS50048.2020.9274980","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274980","url":null,"abstract":"Model-based design (MBD) is an efficient systematic approach for complex system design. It uses models for information transfer and interaction among the designers and engineers. With the use of MBD, communication accuracy and quality are enhanced, a large sum of iterative manual work is saved, and the system design efficiency can be improved. This paper presents practical design and procedure of flight control system for unmanned aerial vehicle (UAV). The basic design contents and procedure of flight control system based on MBD are illustrated first. Then, the system model as well as the constitutional modules for MBD are established and presented. On the basis of the model, the flight software or the C code is generated automatically, and the system validation through X-In-the-Loop (XIL) tests is carried out. The model used in each step of XIL tests is also introduced. Finally, a test case is given as an example.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116714147","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}
Junbo Liao, Shaobin Wu, Jian-wei Gong, Haijie Guan, Kunhong Ye, Shixing Li
{"title":"Learning to Represent and Generalize Lateral Control Deviation Based on Driving Data","authors":"Junbo Liao, Shaobin Wu, Jian-wei Gong, Haijie Guan, Kunhong Ye, Shixing Li","doi":"10.1109/ICUS50048.2020.9274934","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274934","url":null,"abstract":"The lateral control deviation caused by insufficient control algorithm and defective actuator response Will lead to the deviation between the actual driving trajectory and planned trajectory. How to use the driving data to represent lateral control deviations and then generalize them to the correction of planned trajectories will further improve the driving safety of intelligent vehicles. In this paper, a statistical model is established to predict the lateral control deviation. The lateral control deviation between the planned trajectory and the actual driving trajectory is represented by velocity, curvature, and heading deviation. We select three kinds of features to train the statistical models: the previous, current, and future state of path point sequences. The Gaussian Mixture Model (GMM) is used to train the statistical model of lateral control deviation, and Gaussian Mixture Regression (GMR) is used to predict the lateral control deviation. Meanwhile, the actual driving trajectory of the vehicle can be generated directly according to the planned trajectory and the vehicle state. Experiment results show that the proposed method in this paper can predict the future lateral control deviation value With higher accuracy by comparing it with the K-means clustering method.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115698940","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}
Shi Feng, Junqiang Xi, Cheng Gong, Jian-wei Gong, Shengguo Hu, Yuedong Ma
{"title":"A Collaborative Decision Making Approach for Multi-Unmanned Combat Vehicles based on the Behaviour Tree","authors":"Shi Feng, Junqiang Xi, Cheng Gong, Jian-wei Gong, Shengguo Hu, Yuedong Ma","doi":"10.1109/ICUS50048.2020.9275007","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9275007","url":null,"abstract":"Aiming at the difficulty of effective behaviour decision-making in multi-unmanned combat vehicle systems under complex environments and multi-task conditions, based on analyzing existing unmanned vehicle behaviour decision systems, this paper proposes a multi-unmanned combat vehicle cooperative behaviour decision method based on the behaviour tree. In this paper, we describe the behaviour tree modeling method for a multi-unmanned combat vehicle collaborative behavioural decision system, analyze the general process of behavioural tree modeling, and demonstrate the effectiveness of the method by implementing a multi-unmanned combat vehicle collaborative behavioural decision based on the Robomaster AI robot.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115628458","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 Of Aircraft Pursuit-Evasion Game Based on Improved DQN","authors":"Yameng Cui, Chunsheng Zheng, Jiarun Liu, Huixia Wang, Ruiguang Hu, Zhaolei Wang","doi":"10.1109/ICUS50048.2020.9274907","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274907","url":null,"abstract":"The intelligent combat of aircraft has become an important research area. This paper studies the 1Vs1 pursuit-evasion game confrontation scenario of the aircraft, aiming to enable the red agent to find the optimal strategy to avoid the blue interception. First, the aircraft is abstracted into an agent, the kinematics model of the aircraft is simplified, and the behavior model of the aircraft with the bait throwing behavior is established. Based on the improved DQN algorithm, with relative distance, line-of-sight angle and azimuth as the state; the reward function design comprehensively considers the time, number of bait throwing, maneuvering time, and miss distance, and proposes an aircraft pursuit-evasion game algorithm (RB-DQN) in a three-dimensional environment. Experimental results show that the algorithm can effectively control the aircraft to complete the escape mission, and has satisfactory generalization.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115756308","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":"An Unscented Kalman Filter-based Visual Pose Estimation Method for Underwater Vehicles","authors":"Yuanxu Zhang, Chenyi Bian, Jian Gao","doi":"10.1109/ICUS50048.2020.9274896","DOIUrl":"https://doi.org/10.1109/ICUS50048.2020.9274896","url":null,"abstract":"Pose estimation is a critical technique for underwater vehicles to perform observation and manipulation tasks. Acoustic positioning systems are traditionally used for underwater vehicles, but visual systems have the advantages of low cost, high resolution and high data rates, which have unique advantages in underwater vehicle positioning system. In this paper, an unscented Kalman filter-based visual pose estimation is designed based on the models of underwater vehicles and visual systems. Select the image information of feature points as measurement information, perform the 6DOF pose estimation based on the kinematics model of underwater vehicle. The proposed algorithm is validated by comparative tests with a conventional Perspective-N-Points algorithm, based on the visual data of visual targets collected by a real underwater vehicle.","PeriodicalId":110715,"journal":{"name":"2020 3rd International Conference on Unmanned Systems (ICUS)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114612979","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}