Proceedings of the 7th International Conference on Robotics and Artificial Intelligence最新文献

Integral Reinforcement Learning-Based Optimal Control for Nonzero-Sum Games of Multi-Player Input-Constrained Nonlinear Systems 基于积分强化学习的多参与者输入约束非线性系统非零和博弈最优控制

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505698

Bo Zhao, Qiuye Wu, Derong Liu

引用次数: 0

Infrared face recognition based on Yolo network and its application 基于Yolo网络的红外人脸识别及其应用

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505694

Junrong Liao, Hui Zhang, Zhicheng Shang

引用次数: 1

Efficient Mixed-Integer Nonlinear Programming for Optimal Motion Planning of Non-holonomic Autonomous Vehicles 非完整自动驾驶汽车最优运动规划的高效混合整数非线性规划

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505697

Qing Huang, Jibin Hu, Yanxia Zhou, Yongdan Chen, Chao Wei

引用次数: 0

The Segmentation of Perianal Abscess Lesion Area via Gradient Operator of CT Images 基于CT图像梯度算子的肛周脓肿病灶区域分割

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505691

Junxiong Liang, Li Lu, Huan Lei, Nan Wang, Kanglin Yang, Chentong Li, Z. Zhong

引用次数: 0

Design and Optimization of Permanent Magnetic Adsorption Device for Wall-climbing Robot Based on Halbach Array 基于Halbach阵列的爬壁机器人永磁吸附装置设计与优化

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505702

Lei An, Chunguang Zhang, Qingle Yang, Shuai Chu, Jiarui Liu, Guangheng Liu

{"title":"Design and Optimization of Permanent Magnetic Adsorption Device for Wall-climbing Robot Based on Halbach Array","authors":"Lei An, Chunguang Zhang, Qingle Yang, Shuai Chu, Jiarui Liu, Guangheng Liu","doi":"10.1145/3505688.3505702","DOIUrl":"https://doi.org/10.1145/3505688.3505702","url":null,"abstract":"The wall-climbing robot for ship's paint removal is adsorbed and walks on steel plate of the ship, which uses ultra high pressure water jet sprayed by nozzles to remove paint and vacuum recovery system recovers sewage and waste residue. This article established the mechanical model of the wall-climbing robot, analyzed sliding and overturning model, and derived adsorption force. To satisfy the requirements on adsorb safety and maneuverability of the wall-climbing robot, a permanent magnetic adsorption device was designed. Finite element simulation was performed on polarization of traditional type and Halbach array. Simulation results showed that the adsorption force provided by Halbach array was much better than that of traditional type. The adsorption force based on Halbach array was measured and compared with the finite element simulation results. The ratio of the adsorption force provided by the permanent magnetic adsorption device to its mass, as the target function, structural parameters of the permanent magnet were optimized, which greatly increased the utilization rate of magnetic energy of the permanent magnet. Walking performance experiment showed that the wall-climbing robot meets the design requirements of reliable adsorption and flexible walking of the robot.","PeriodicalId":375528,"journal":{"name":"Proceedings of the 7th International Conference on Robotics and Artificial Intelligence","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132031129","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

Event-triggered Suboptimal Control Based Adaptive Reinforcement Learning 基于自适应强化学习的事件触发次优控制

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505699

T. Ma, Ruizhuo Song

引用次数: 0

Study on Pile-soil Model under Horizontal Load 水平荷载作用下桩-土模型研究

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505708

Jing Zhang, Y. Cao

引用次数: 0

Integrate YOLOv3 with a Self-attention Mechanism for Underwater Object Detection Based on Forward-looking Sonar Images 将YOLOv3与基于前视声纳图像的水下目标检测的自关注机制集成

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505689

Jian Yang, Kaibin Xie, Kang Qiu

{"title":"Integrate YOLOv3 with a Self-attention Mechanism for Underwater Object Detection Based on Forward-looking Sonar Images","authors":"Jian Yang, Kaibin Xie, Kang Qiu","doi":"10.1145/3505688.3505689","DOIUrl":"https://doi.org/10.1145/3505688.3505689","url":null,"abstract":"Detection of underwater objects based on sonar images is an important component of underwater robotics in the field of environmental perception and has attracted much attention. However, due to the complexity of the underwater environment, sonar devices, such as forward-looking sonar, encounter interference noises during imaging. In addition, there are few public sonar datasets that can be used for research. These challenges limit the task of underwater object recognition based on Deep Learning and make it difficult to make progress. Therefore, in this study, we first public a forward-looking sonar image dataset (FLSD) with rich data types and a large number of images. Then, we proposed a data augmentation method to address the lack of sonar images, and an experiment demonstrated its effectiveness. Finally, to strengthen the correlation of feature maps between channels in the training process of the network, we introduced the YOLOv3-based self-attention mechanism and proposed YOLOv3-SE. The results of our experiments show an improvement of 2.94% Precision, 3.34% Recall and 4.95% mAP on FLSD. Dataset attachment: https://code.ihub.org.cn/projects/14186","PeriodicalId":375528,"journal":{"name":"Proceedings of the 7th International Conference on Robotics and Artificial Intelligence","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128169931","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

PID Parameter Tuning Based On Adaptive Dynamic Programming 基于自适应动态规划的PID参数整定

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505703

Hua-yun Cao, Ruizhuo Song

引用次数: 0

Automatic 3D Skeleton-based Dynamic Hand Gesture Recognition Using Multi-Layer Convolutional LSTM 基于多层卷积LSTM的自动三维骨架动态手势识别

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence Pub Date : 2021-11-19 DOI: 10.1145/3505688.3505690

A. Mohammed, Yuan Gao, Zhilong Ji, Jiancheng Lv, M. Islam, Yongsheng Sang

{"title":"Automatic 3D Skeleton-based Dynamic Hand Gesture Recognition Using Multi-Layer Convolutional LSTM","authors":"A. Mohammed, Yuan Gao, Zhilong Ji, Jiancheng Lv, M. Islam, Yongsheng Sang","doi":"10.1145/3505688.3505690","DOIUrl":"https://doi.org/10.1145/3505688.3505690","url":null,"abstract":"Accurate and real-time recognition of skeleton-based dynamic hand gestures has gained increasing attention in recent years with the development of depth sensors and the improved hand joints estimation algorithms. This task is challenging due to the spatial and temporal features that exacerbate the task complexity. Although previous works have applied different techniques, it remains challenging to efficiently and simultaneously encode the spatiotemporal features. To address this problem, this work presents a Deep Convolutional LSTM (DConvLSTM) model to learn more discriminative spatiotemporal features from skeleton data implicitly. The model employs multi-layer ConvLSTM to accurately capture the multiscale spatial and sequential information of the gesture and preserves a fast inference and lightweight size. Extensive experiments on three publicly available datasets show strong performance and demonstrate the superiority of our method by outperforming other methods. Furthermore, our method can achieve comparable recognition accuracy while maintaining small models and short inference time.","PeriodicalId":375528,"journal":{"name":"Proceedings of the 7th International Conference on Robotics and Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123728963","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