2022 IEEE International Conference on Unmanned Systems (ICUS)最新文献_第2页

Autonomous On-ramp Merge Strategy Using Deep Reinforcement Learning in Uncertain Highway Environment 不确定公路环境下基于深度强化学习的自主入匝道合并策略

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986560

Sifan Wu, Daxin Tian, Jianshan Zhou, Xuting Duan, Zhengguo Sheng, Dezong Zhao

引用次数: 0

U-LOAM: A Real-Time 3D Lidar SLAM System for Water-Surface Scene Applications U-LOAM:用于水面场景应用的实时3D激光雷达SLAM系统

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986766

Heng Zhang, Zhao-Qing Liu, Yulong Wang

引用次数: 0

Trajectory Optimization with Polygonal No-Fly Zone Constraints for Hypersonic Glide Vehicle 高超声速滑翔飞行器多边形禁飞区约束下的轨迹优化

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986788

Rouhe Zhang, Zhili Sun, Changzhu Wei

引用次数: 0

Autonomous Taxiing-in Control Law of Large Dual-body UAVs 大型双体无人机自主滑行控制律研究

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987126

Yanming Fan, Yunhui Wang, Jiaxing Zhu, Dezhong Zhou

引用次数: 0

Consensus Predefined-time Cooperative Interception Guidance Law for Multi Vehicles 多载机共识预定义时间协同拦截制导律

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986993

Mingkun Guo, Yuhe Yang, Guangqing Xia, Feng Yang

引用次数: 1

A Cooperative Guidance Law for Multiple Missiles based on Reinforcement Learning 一种基于强化学习的多导弹协同制导律

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986718

Hongxu Chen, Jianglong Yu, Xiwang Dong

引用次数: 1

Few-Shot Incremental Learning for Aerial Image Scene Classification Based on Feature Adaptation and Prototype Continuous Optimization 基于特征自适应和原型连续优化的航拍图像场景少镜头增量学习分类

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987193

Yizhi Zeng, Bohan Xue, Wenqi Han

{"title":"Few-Shot Incremental Learning for Aerial Image Scene Classification Based on Feature Adaptation and Prototype Continuous Optimization","authors":"Yizhi Zeng, Bohan Xue, Wenqi Han","doi":"10.1109/ICUS55513.2022.9987193","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987193","url":null,"abstract":"Aerial image scene classification plays a significant role in many applications, however, it generally faces the problem of lacking labeled samples and incremental classification tasks. Existing deep networks directly applied for incremental learning may lead to knowledge forgetting of old categories and overfitting to identify novel category. In this paper, a few-shot incremental learning (FSIL) model based on feature adaptation and prototype continuous optimization is presented for aerial image scene classification. In the proposed framework, a feature extractor and a cosine distance classifier based on residual networks are constructed firstly. Then, a feature adaptation module is developed to calculate relation coefficient between training samples and test samples of incremental stage in order to adjust feature weights. In addition, a prototype continuous optimizer is proposed to correct prototype features to enhance the discrimination during incremental stage and reduce knowledge forgetting of old categories. Experimental results on two datasets verify that the presented method is effective for few-shot incremental aerial scene image classification(FS-IASIC).","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"23 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":"129611636","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

The Evaluation of Information Contribution for Unmanned Aerial Vehicle Integrating into the Air Combat System 无人机融入空战系统的信息贡献评估

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986552

H. Chang, Ranxi Zhang, Yan Zhang

引用次数: 0

Optimal Path Planning for Underwater Robots Based on Improved Ant Colony Algorithm 基于改进蚁群算法的水下机器人最优路径规划

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9987098

Kai He, Yuhuan Fei, Xiaowen Teng, Xiaoguang Chu, Zhenwei Ma

{"title":"Optimal Path Planning for Underwater Robots Based on Improved Ant Colony Algorithm","authors":"Kai He, Yuhuan Fei, Xiaowen Teng, Xiaoguang Chu, Zhenwei Ma","doi":"10.1109/ICUS55513.2022.9987098","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987098","url":null,"abstract":"When applying traditional ant colony algorithm in the path optimization of underwater robots, there are several problems such as slow convergence speed and poor optimization effect. In this paper, an improved ant colony algorithm was proposed. The improved algorithm enhances the pheromone concentration in the core area of the grid map in the first inquiry stage, which can improve the confluence efficiency of the algorithm. In order to reduce the number of turns of the ants and make the path smoother, the corner heuristic function was added to the state transition probability equation. The position of the target point was added to the heuristic function to boost the target point's guiding influence on the ant colony. In the pheromone update part, the allocation strategy of the wolf pack algorithm was introduced to strengthen the pheromone of the optimal path and at the same time limit the pheromone concentration to reduce the generation of local optimal solutions. In the MATLAB simulation verification, the improved ant colony algorithm plans a shorter path length and fewer turns. The algorithm can effectively avoid obstacles, has better global optimization, and avoids the energy loss of underwater robots. This paper verifies the feasibility and superiority of the improved ant colony algorithm in static path planning.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"7 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":"128753026","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

UAV Gust Wind Mitigation Measurement and Control System Design 无人机阵风缓解测控系统设计

2022 IEEE International Conference on Unmanned Systems (ICUS) Pub Date : 2022-10-28 DOI: 10.1109/ICUS55513.2022.9986549

Ying-Chen Lu, Chunhui Liu

{"title":"UAV Gust Wind Mitigation Measurement and Control System Design","authors":"Ying-Chen Lu, Chunhui Liu","doi":"10.1109/ICUS55513.2022.9986549","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986549","url":null,"abstract":"UAVs are susceptible to turbulence when flying, which can alter the expected navigational attitude, flight trajectory and other states and affect the reasonable execution of the mission, and gust mitigation technology is a powerful means for UAVs to cope with the effects of gusts. This paper designs a gust mitigation measurement and control system for UAVs using the STM32H743 as the control core. The system consists of a master control unit, a data acquisition module, a serial module, a rudder control module and a data storage module. When the UAV is affected by gusts of wind, the system acquires the current flight status of the UAV by accurately collecting data from the UAV sensors, and then combines the control commands from the ground station and the flight control to fuse and solve the data, and then generates rudder control commands to control the rudder deflection, so that the UAV can maintain stable flight and achieve gust mitigation. After actual circuit fabrication and experimental testing, the measurement and control system designed in this paper can achieve stable serial communication, accurate analogue signal acquisition, precise motor and rudder control and stable power supply, meeting all the indicators and requirements required to achieve gust mitigation.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"1 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":"129344538","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