2022 22nd International Conference on Control, Automation and Systems (ICCAS)最新文献_第10页

Continuous Control of Autonomous Vehicles using Plan-assisted Deep Reinforcement Learning 基于计划辅助深度强化学习的自动驾驶车辆连续控制

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003698

Tanay Dwivedi, Tobias Betz, Florian Sauerbeck, P. Manivannan, M. Lienkamp

{"title":"Continuous Control of Autonomous Vehicles using Plan-assisted Deep Reinforcement Learning","authors":"Tanay Dwivedi, Tobias Betz, Florian Sauerbeck, P. Manivannan, M. Lienkamp","doi":"10.23919/ICCAS55662.2022.10003698","DOIUrl":"https://doi.org/10.23919/ICCAS55662.2022.10003698","url":null,"abstract":"End-to-end deep reinforcement learning (DRL) is emerging as a promising paradigm for autonomous driving. Although DRL provides an elegant framework to accomplish final goals without extensive manual engineering, capturing plans and behavior using deep neural networks is still an unsolved issue. End-to-end architectures, as a result, are currently limited to simple driving scenarios, often performing sub-optimally when rare, unique conditions are encountered. We propose a novel plan-assisted deep reinforcement learning framework that, along with the typical state-space, leverages a “trajectory-space” to learn optimal control. While the trajectory-space, generated by an external planner, intrinsically captures the agent’s high-level plans, world models are used to understand the dynamics of the environment for learning behavior in latent space. An actor-critic network, trained in imagination, uses these latent features to predict policy and state-value function. Based primarily on DreamerV2 and Racing Dreamer, the proposed model is first trained in a simulator and eventually tested on the FITENTH race car. We evaluate our model for best lap times against parameter-tuned and learning-based controllers on unseen race tracks and demonstrate that it generalizes to complex scenarios where other approaches perform sub-optimally. Furthermore, we show the model’s enhanced stability as a trajectory tracker and establish the improvement in interpretability achieved by the proposed framework.","PeriodicalId":129856,"journal":{"name":"2022 22nd International Conference on Control, Automation and Systems (ICCAS)","volume":"46 14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131646057","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: 3

Generation Method of Autonomous Evasive Maneuver Strategy in Air Combat 空战中自主规避机动策略的生成方法

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003888

Lin Li, Zhen Yang, Zhixiao Sun, Guang Zhan, Haiyin Piao, Deyun Zhou

{"title":"Generation Method of Autonomous Evasive Maneuver Strategy in Air Combat","authors":"Lin Li, Zhen Yang, Zhixiao Sun, Guang Zhan, Haiyin Piao, Deyun Zhou","doi":"10.23919/ICCAS55662.2022.10003888","DOIUrl":"https://doi.org/10.23919/ICCAS55662.2022.10003888","url":null,"abstract":"Air combat is usually a continuous process involving multiple rounds of missile attacks, UCAV(Unmanned Combat Aerial Vehicle) should consider the impact of maneuver on the entire air combat countermeasure mission rather than solely focusing on safety factors when evading incoming air to air missiles. In this paper, a method of generating autonomous evasive maneuver strategy in UCAV air combat is proposed under the condition of miss distance and energy dissipation. Firstly, the UCAV-missile three-dimensional space pursuit model and the UCAV autonomous evading state space, action space and reward function model are established. Dueling DDQN (Double Deep Q Network) algorithm is used to solve the model, which integrates Double DQN and Dueling DQN Network model. Simulation experiments and analysis show that the method proposed in this paper has significant effectiveness in solving the problem of autonomous evasive maneuvers in air combat under the conditions of miss distance and energy dissipation tactical requirements. The evasive maneuvers strategy obtained can reflect the two tactical requirements of air combat while ensuring the safety of UCAV itself.","PeriodicalId":129856,"journal":{"name":"2022 22nd International Conference on Control, Automation and Systems (ICCAS)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116554662","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

Development of Painting Robot for Cage-shape Iron Pillar Supporting Train Track: Prototype Design and Basic Motion Verification 笼形铁柱支撑列车轨道涂装机器人的研制:样机设计与基本运动验证

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003938

Seonghee Jeong, Katsushi Ogawa, T. Jozen

{"title":"Development of Painting Robot for Cage-shape Iron Pillar Supporting Train Track: Prototype Design and Basic Motion Verification","authors":"Seonghee Jeong, Katsushi Ogawa, T. Jozen","doi":"10.23919/ICCAS55662.2022.10003938","DOIUrl":"https://doi.org/10.23919/ICCAS55662.2022.10003938","url":null,"abstract":"In this paper, a prototype painting robot that can paint a surface of steel material while climbing up and down an inside of a cage-type iron pillar supporting a train track is proposed. Target specifications are set based on the requirements of the painting robot, and then, the robot is designed so that each specification can be cleared. The robot consists a climbing device that climbing up and down the inside of the iron pillar, a painting arm that paints the surface of the steel material, and a paint suppling device that supplies paint to a brush. The climbing device has a leg-shaped structure, and climbs up and down inside the iron pillar while alternately gripping the steel material with an upper and lower legs. In addition, the painting arm has a 6-DOF serial link mechanism, and the brush can be appropriately posed on the surface of the target steel. The paint supply device is equipped with a uniaxial screw type mohno pump so that an appropriate amount of high-viscosity paint could be supplied to the brush. Through simple experiments, it was confirmed that each device could realize basic functions according to the design specifications.","PeriodicalId":129856,"journal":{"name":"2022 22nd International Conference on Control, Automation and Systems (ICCAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121077268","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

Lidar SLAM Comparison in a Featureless Tunnel Environment 无特征隧道环境下的激光雷达SLAM比较

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003820

Iulian Filip, Juhyun Pyo, Meungsuk Lee, Hangil Joe

{"title":"Lidar SLAM Comparison in a Featureless Tunnel Environment","authors":"Iulian Filip, Juhyun Pyo, Meungsuk Lee, Hangil Joe","doi":"10.23919/ICCAS55662.2022.10003820","DOIUrl":"https://doi.org/10.23919/ICCAS55662.2022.10003820","url":null,"abstract":"Simultaneous Localization and Mapping (SLAM) algorithm consists a vital part of decision-making process of autonomous robot platforms. Many lidar-based SLAM methods have been proposed for indoor and urban environments. However, a few studies are reported in a featureless tunnel environment. In this paper we consider recent lidar SLAM frameworks and test their performance in a tunnel environment. Our dataset is collected by a four-wheeled ground vehicle that is equipped with a lidar sensor used for mapping and feature detection and an IMU sensor used for odometry tracking information. The performance of seven different lidar SLAM algorithms is tested and as a result, in corridor environment LIO-SAM and SC-LIO-SAM frameworks show the lowest trajectory and point cloud error, respectively. On the other hand, LIO-SAM and FAST-LIO2 displays the best trajectory accuracy in the tunnel environment with addition of artificial landmarks and without them, respectively. The results obtained during the performance of seven different lidar SLAM algorithms can contribute to the development of a SLAM framework in a featureless tunnel environment.","PeriodicalId":129856,"journal":{"name":"2022 22nd International Conference on Control, Automation and Systems (ICCAS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115062845","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

Performance Comparison of Human Activity Recognition for Unmanned Retails 无人零售中人类活动识别的性能比较

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003872

Sheilla Wesonga, Nusrat Jahan Tahira, Jangsik Park

引用次数: 0

A Resiliency Coordinator Against Malicious Attacks for Cyber-Physical Systems 针对网络物理系统恶意攻击的弹性协调器

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003922

Y. Eun, Jaegeun Park, Yechan Jeong, Dae-Heon Kim, Kyung-Joon Park

{"title":"A Resiliency Coordinator Against Malicious Attacks for Cyber-Physical Systems","authors":"Y. Eun, Jaegeun Park, Yechan Jeong, Dae-Heon Kim, Kyung-Joon Park","doi":"10.23919/ICCAS55662.2022.10003922","DOIUrl":"https://doi.org/10.23919/ICCAS55662.2022.10003922","url":null,"abstract":"Resiliency of cyber-physical systems (CPSs) against malicious attacks has been a topic of active research in the past decade due to widely recognized importance. Resilient CPS is capable of tolerating some attacks, operating at a reduced capacity with core functions maintained, and failing gracefully to avoid any catastrophic consequences. Existing work includes an architecture for hierarchical control systems, which is a subset of CPS with wide applicability, that is tailored for resiliency. Namely, the architecture consists of local, network and supervision layers and features such as simplex structure, resource isolation by hypervisors, redundant sensors/actuators, and software defined network capabilities. Existing work also includes methods of ensuring a level of resiliency at each one of the layers, respectively. However, for a holistic system level resiliency, individual methods at each layers must be coordinated in their deployment because all three layers interact for the operation of CPS. For this purpose, a resiliency coordinator for CPS is proposed in this work. The resiliency coordinator is the interconnection of central resiliency coordinator in the supervision layer, network resiliency coordinator in the network layer, and finally, local resiliency coordinators in multiple physical systems that compose the physical layer. We show, by examples, the operation of the resiliency coordinator and illustrate that RC accomplishes a level of attack resiliency greater than the sum of resiliency at each one of the layers separately.","PeriodicalId":129856,"journal":{"name":"2022 22nd International Conference on Control, Automation and Systems (ICCAS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116485699","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 and Precise Indoor Localization System in Multi-Floor Buildings for Pedestrian using Cloud Platform 基于云平台的多层建筑行人室内实时精确定位系统

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003879

Taehun Kim, B. Shin, C. Kang, Jung Ho Lee, Changsoo Yu, Hankyeol Kyung, DongHyun Shin, Taikjin Lee

{"title":"Real-time and Precise Indoor Localization System in Multi-Floor Buildings for Pedestrian using Cloud Platform","authors":"Taehun Kim, B. Shin, C. Kang, Jung Ho Lee, Changsoo Yu, Hankyeol Kyung, DongHyun Shin, Taikjin Lee","doi":"10.23919/ICCAS55662.2022.10003879","DOIUrl":"https://doi.org/10.23919/ICCAS55662.2022.10003879","url":null,"abstract":"Pedestrians use their smartphones to determine their location. Accordingly, there is a growing demand for seamless localization that can estimate the location regardless of indoor and outdoor space. However, the Global Navigation Satellite System used for outdoor location estimation has poor reception in the indoor environment, making it difficult to use in indoor space. Therefore, we propose the indoor localization technology based on Surface Correlation (SC). This indoor localization technology can estimate the location of pedestrians on only one floor. In this study, floor detection was performed using only RF signal without using other sensors such as barometric pressure sensor in the multi-floor building. The most important thing in floor detection is the reliability of the current floor and floor change detection. We can estimate the coarse floor using the unique ID of the RF source installed on each floor. Then, the virtual trajectory is generated using only RF signal, and the degree of similarity with the floor is determined by identifying the fine floor of the coarse floor estimated by applying the existing SC-based localization. Once the fine floor of pedestrians is identified, the final absolute location of pedestrians in the multi-floor building can be estimated by calculating the indoor location of the estimated floor using conventional SC-based localization. To verify the performance of the proposed algorithm in real-time, the algorithm was implemented in Google Cloud Platform. Pedestrians can check the indoor location results through real-time connection with the smartphone. In the actual multi-floor building, the similarity between the floor estimated by the proposed algorithm and the floor estimated using the barometric pressure sensor is about 95.0%. And the RMSE of the indoor localization results of the proposed system is about 3. 662m.","PeriodicalId":129856,"journal":{"name":"2022 22nd International Conference on Control, Automation and Systems (ICCAS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130291819","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

Magnetic Recording Reliability Evaluation 磁记录可靠性评估

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003844

Ekkaphon Phonyiam, P. Netisopakul

引用次数: 0

Frequency-Domain Data Augmentation of Vibration Data for Fault Diagnosis using Deep Neural Networks 基于深度神经网络的振动数据频域增强故障诊断

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003718

Minseon Gwak, S. Ryu, Yongbeom Park, Hyeon-Woo Na, P. Park

引用次数: 1

Simultaneous Optimization of Task Allocation and Path Planning Using Mixed-Integer Programming for Time and Capacity Constrained Multi-Agent Pickup and Delivery 基于混合整数规划的时间和容量约束下多智能体取送任务分配和路径规划同步优化

2022 22nd International Conference on Control, Automation and Systems (ICCAS) Pub Date : 2022-11-27 DOI: 10.23919/ICCAS55662.2022.10003849

Takuma Okubo, Masaki Takahashi

{"title":"Simultaneous Optimization of Task Allocation and Path Planning Using Mixed-Integer Programming for Time and Capacity Constrained Multi-Agent Pickup and Delivery","authors":"Takuma Okubo, Masaki Takahashi","doi":"10.23919/ICCAS55662.2022.10003849","DOIUrl":"https://doi.org/10.23919/ICCAS55662.2022.10003849","url":null,"abstract":"Lately, there has been a need to improve the efficiency of material movements within factories and multi-agents are required to perform these tasks. In this study, graphical representation and mixed-integer programming have been adopted for simultaneous optimization of task allocation and path planning for each agent to achieve the following three goals. First, this study realizes time and capacity constrained multi-agent pickup and delivery (TCMAPD) that simultaneously considers time constraints, capacity constraints, and collision avoidance. Previous studies have not considered these constraints simultaneously. Thus, we can solve the problems associated with using multi-agents in actual factories. Second, we achieved TCMAPD that optimizes the collision avoidance between multi-agents. In conventional research, only a single collision avoidance method can be used. However, an appropriate route was selected from a variety of avoidance methods in this study. Hence, we could achieve a more efficient task allocation and path planning with collision avoidance. Third, the proposed method simultaneously optimizes task allocation and path planning for each agent. Previous studies have separately considered the approach of optimizing task allocation and path planning or used the cost of path planning after task allocation to again perform task allocation and path planning. To simultaneously optimize them in a single plan, we have developed a solution-derivable formulation using mixed-integer programming to derive a globally optimal solution. This enables efficient planning with a reduced total time traveled by the agents.","PeriodicalId":129856,"journal":{"name":"2022 22nd International Conference on Control, Automation and Systems (ICCAS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133495176","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: 2