{"title":"Enhanced Neural SLAM with Semantic Segmentation in Dynamic Environments","authors":"Zhengcheng Shen, Minzhe Mao, Linh Kästner, Jens Lambrecht","doi":"10.1109/ICARM58088.2023.10218889","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218889","url":null,"abstract":"Mobile robots face a significant challenge when navigating in dynamic environments such as human crowds. Existing research works typically employ separate data or simulators for dynamic object detection and navigation tasks. This paper combines the photo-realistic simulator Habitat with embedded dynamic objects to create a playground for optimizing vision-based navigation algorithms. To validate our system, we implement and train three approaches - zero masks, image memory inpainting, and semantic map filter - using semantically segmented information. We then implement and evaluate an adapted reinforcement-learning-based SLAM algorithm using the validation Gibson dataset. The results indicate that moderate localization bias occurs when the environment is small and the navigation process is short. However, the error will accumulate over time. Additionally, a dynamic environment leads to less accurate localization. All three approaches can reduce the localization error, while the semantic map filter approach shows the best overall performance.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128917497","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":"Autonomous Path Planning and Realization for Dual Robot Cooperation Based on ROS Framework","authors":"Jiawei Shao, Yahui Gan, X. Dai","doi":"10.1109/ICARM58088.2023.10218950","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218950","url":null,"abstract":"To realize dual-robot autonomous path planning and realization, the trajectory planning research of dual-robot is carried out using the open-source robot operating system ROS as the simulation platform. The motion planning-related file configuration is completed by using MoveIt! In trajectory planning, cubic spline interpolation is performed on the trajectory points generated by the RRT-Connect path planning algorithm to complete the planning of the dual-arm assembly task. The communication between ROS nodes and ROS is established in the controller, and the processed trajectory points are communicated with the controller through ROS-Industrial. The experimental results show that the trajectory of the dual robot movement process is smooth and continuous, the stability is strong, and the error is small, which can ensure the completion of basic assembly tasks.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"239 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116121858","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}
Rongqi Gu, Tianhang Wang, Tianpei Zou, Bo Zhang, Zhijun Li, Haotian Zhang, G. Chen
{"title":"PQMPV: Parallel and Quantified Dense Stereo Disparity Estimation Based on Multi-Path Viterbi","authors":"Rongqi Gu, Tianhang Wang, Tianpei Zou, Bo Zhang, Zhijun Li, Haotian Zhang, G. Chen","doi":"10.1109/ICARM58088.2023.10218824","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218824","url":null,"abstract":"Stereo depth estimation plays a crucial role in enabling robots, autonomous driving and other applications. As an ill-posed problem, both deep learning based and traditional methods have been extensively studied in recent years. Traditional methods mainly focus on feature matching between multiple images to estimate depth, but often result in blank pixels with zero disparity and also require significant computation time. In this paper, we propose a new stereo disparity estimation algorithm based on the dynamic programming method known as Viterbi. Our approach optimize the range of disparity calculation through image pyramid, combined with Viterbi algorithm for cost aggregation, and accelerates several calculation steps through parallel computing techniques. Additionally, we improve data transmission and processing speed by quantifying data from float to integer. Experiments on the KITTI dataset and MiddEval benchmark demonstrate that our algorithm achieves significant improvements in average error rate and processing speed of disparity map, making it a promising solution for stereo depth estimation in practical applications.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121128700","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}
Yi Zhao, Qing Gao, Zhaojie Ju, Jian Zhou, Junkang Chen
{"title":"Skeleton-Based Action Recognition Using Residual Activation Fish-Shaped Network for Human-Robot Interaction","authors":"Yi Zhao, Qing Gao, Zhaojie Ju, Jian Zhou, Junkang Chen","doi":"10.1109/ICARM58088.2023.10218954","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218954","url":null,"abstract":"In the field of human-robot interaction, action recognition is a challenging problem. In this paper, a residual activation fish-shaped network is proposed for action recognition, which contains 3 parts of fish tail, fish body and fish head. A multi-feature input model with physiognomic Cartesian motion features and intrinsic Geometric features is constructed, which can eliminate the influence of changes in camera depth of field and observation orientation. An extended residual convolution structure is designed to utilize global information to refine coupled useful sub-features, and learn a structured semantic representations on skeletons of each frame. Experimental results show that the proposed method achieves an accuracy of 80.96% on the JHMDB dataset, 95.02% on SHREC14, and 93.16% on SHREC28. In addition, a human-robot interaction experiment is conducted, which verifies the effectiveness of the proposed action recognition method.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121148117","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}
Xinbo Chen, Sibo Hao, Yue Wang, Boyi Zhang, Haoshuang Su, Yong Cao, Di Cui, Qinghao Hu, Haoyu Wang, Mingchuan Zhou
{"title":"Master-Slave Control Strategy Applied in Microsurgical Robot","authors":"Xinbo Chen, Sibo Hao, Yue Wang, Boyi Zhang, Haoshuang Su, Yong Cao, Di Cui, Qinghao Hu, Haoyu Wang, Mingchuan Zhou","doi":"10.1109/ICARM58088.2023.10218823","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218823","url":null,"abstract":"With the rapid spread of microsurgery, more attention has been paid to the development of medical tools, especially microsurgical robotics, which contributes to improving the performance of surgery and reducing the risk caused by artificial operation. Among the components applied in a robotic system, the master-slave control system has been attached with great significance. In this study, a master-slave control method has been developed for the special designed microsurgical robotic system. In order to free surgeons from the physical limitations of their own hands and simplify the difficulty of operation, a forceps-like manipulator is employed as the master device. A wrist articulation-based end-effector with seven degrees of freedom is used to follow the motion of the master device. It has been initially proved that the robot is able to achieve the goal of master-slave control.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116461384","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":"Prediction Models of Arterial Pressure during CPR Based on Force Data of Manual Chest Compression","authors":"Mingze Sun, Ke-jia Li, Lijun Jiang, Fengyang Xu, Jiali Wang, Feng Xu, Yuguo Chen","doi":"10.1109/ICARM58088.2023.10218832","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218832","url":null,"abstract":"Chest compressions are essential for CPR and the quality of it can be evaluated in terms of physical parameters: force, frequency, or physiological parameters: mean arterial pressure (MAP). In this study, an animal model was finished for CPR experiment. The data of the force of manual chest compression and the arterial blood pressure of animals were collected during the experiment, and the force, frequency, MAP and pulse pressure (PP) of manual chest compression were obtained through data processing. In this study, linear fitting was used to solve the linear relationship between force-MAP, frequency-MAP, force-PP and frequency-PP. The relationship between frequency-force-MAP and the relationship of frequency-force-PP was constructed and predicted by the method of RBF and LSTM. As the results showed that the best linear fitting results are frequency-MAP (R-square = 0.58, RMSE = 9.51) and frequency-PP (R-square = 0.62, RMSE = 9.00), and the best prediction results are the PP prediction using the method of RBF (R-square = 0.80, RMSE = 5.73). The method of LSTM got the best result to predict MAP (R-square = 0.74, RMSE = 5.80).","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125980419","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":"Blind Lane Detection and Following for Assistive Navigation of Vision Impaired People","authors":"Zhicheng Han, J. Gu, Ying Feng","doi":"10.1109/ICARM58088.2023.10218843","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218843","url":null,"abstract":"The task of safely navigating outdoor environ-ments presents significant difficulties for people with visual impairments. This paper aims to address this issue by proposing a wearable assistance system for visually impaired individuals in blind lane detection and following scenarios. The system consists of two stages: the first stage employs a fully convolutional network to detect blind lanes and an object detection network to identify obstacles. The second stage utilizes an improved artificial potential field method to achieve real-time path following based on the detection results. Our experiments involving subjects in dynamic outdoor environments demonstrate the robustness of our proposed method in navigating and avoiding obstacles under challenging outdoor conditions.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125115989","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":"Resilient Switching Control of the Tilt-Rotor Aircraft Based on the Disturbance Observer","authors":"Zhengcai An, Shuyi Shao","doi":"10.1109/ICARM58088.2023.10218762","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218762","url":null,"abstract":"Aiming at the problem of external composite disturbance in the conversion flight mode of the tilt-rotor aircraft, a robust resilient switching flight control scheme based on the disturbance observer is developed. First of all, the linear longitudinal kinematic switching model of the aircraft is given, and the switching rule based on the average dwell time is designed. Then, the external disturbance is compensated by the designed disturbance observer, the H∞ control method is used to suppress the energy-bounded disturbance. In addition, the non-fragile control method is introduced to reduce the effect of controller gain perturbations. With the Lyapunov function, the controller gains are solved by the linear matrix inequality toolbox. Finally, the simulation results demonstrate the effectiveness of the proposed method.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128809244","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":"A Magnetic Micro Robotic Trajectory Controller Design for Cell Trapping","authors":"Fanghao Wang, Daoyuan Jin, Youchao Zhang, Xiangyu Guo, Chuanjie Liu, Mingchuan Zhou","doi":"10.1109/ICARM58088.2023.10218798","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218798","url":null,"abstract":"Cell trapping is considered a complicated and challenging task due to the small scale of manipulation involved. Image guided robotic micro manipulation is among the novel and promising solutions that may enhance human capabilities. In this paper we demonstrate 3-degree-of-freedom (3-DOF) wireless magnetic control of an untethered microrobot (2-DOF position and 1-DOF pointing orientation). An accurate orientation control model has been employed to determine the microrobot's orientation in 2D space. In addition, multiple orientation experiments were conducted to verify the proposed model. Finally, a feedback control algorithm including a Proportional-Integral-Derivative controller (PID) is conducted to eliminate external disturbance during the trajectory tracking task. This system was primarily designed to control magnetic microrobots for cell trapping in vitro.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129151355","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":"A Soft Finger Resistant to Lateral Forces through Endoskeleton Embedding","authors":"Runzhe Zhang, Yu Yan, Wenbin Chen","doi":"10.1109/ICARM58088.2023.10218861","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218861","url":null,"abstract":"Soft robotic hands have attracted widespread attention due to their unique compliance, but the overly soft material makes it difficult for them to maintain their own shape, which contradicts the original intention of soft hands to mimic the human hand. This paper introduces a soft finger embedded in endoskeleton (SFEE) that enhances its resistance to lateral forces without compromising its flexion-extension capabilities. Inspired by the interphalangeal joints of human fingers, the endoskeleton adopts a hinge-like connection. The endoskeleton consists of multiple interconnected units, which are articulated and embedded within the chamber of the soft finger. This paper describes the design, fabrication process, and preliminary performance testing of SFEE. The necessity of the soft finger to resist the lateral force is demonstrated by finite element simulation and the grasping ability of SFEE is demonstrated using a three fingers gripper. Due to the purely passive bending of the endoskeleton and its small size, it can be applied to most soft actuators with cavities to reproduce the characteristics of human hands.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127306065","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}