{"title":"A Collision-free Trajectory Planning Algorithm for Manipulators in Unstructured Environment","authors":"Zhaolei Hou, Yong Jiang, Hongya Wang","doi":"10.1109/ROBIO49542.2019.8961613","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961613","url":null,"abstract":"In this article, we propose a collision-free trajectory planning method for the manipulator that satisfies the robot’s operational requirements in unstructured environment. The algorithm considers the collision-free trajectory requirements of the end effector and the manipulator body. The reactive trajectory planning algorithm in the local environment is used to superimpose the control quantity on the velocity layer, which avoids the mechanical dynamics model in the calculation process, Parameter acquisition and computational complexity issues. The method is simulated by MATLAB and further implemented on the UR manipulator. The simulation and experimental results show the real-time and effectiveness of the algorithm.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115656608","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}
Taogang Hou, Xingbang Yang, Haohong Su, Lingkun Chen, Tianmiao Wang, Jianhong Liang, Siyang Zhang
{"title":"Design, Fabrication and Morphing Mechanism of Soft Fins and Arms of a Squid-like Aquatic-aerial Vehicle with Morphology Tradeoff","authors":"Taogang Hou, Xingbang Yang, Haohong Su, Lingkun Chen, Tianmiao Wang, Jianhong Liang, Siyang Zhang","doi":"10.1109/ROBIO49542.2019.8961447","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961447","url":null,"abstract":"Some animals have the ability to shuttle freely between water and air. These creatures have evolved special body structures to accommodate both underwater and airborne environments. Natural creatures have given us great inspiration to the variable structure design for aquatic-aerial multimodal vehicle. In this paper, we propose a new squid-like soft morphing fins according to the flying squid. This squid-like soft morphing fins can spread and fold for the adaptation of the aquatic-aerial multimodal locomotion. When the fin is spread, it can generate lift force for the aquatic-aerial vehicle. When the soft fin is folded, it can reduce the drag force during the underwater movement. An unique air cavity inside the fin was designed as actuator to bend the soft fin. The fabrication method of the soft fin was introduced. The bending performance of the soft fin was analyzed by FEA simulation and tested by several experiments. Then, morphology tradeoff strategy of aquatic-aerial vehicle with soft morphing fins was investigated by the wind and water tunnel. The results demonstrate the soft morphing fins have fast actuating response and good deformability, which verifies the soft fin can help the aquatic-aerial vehicle to realize multi-modal locomotion.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116884317","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":"GC-IGTG: A Rehabilitation Gait Trajectory Generation Algorithm for Lower Extremity Exoskeleton","authors":"Yong He, Xinyu Wu, Yue Ma, Wujing Cao, Nan Li, Jinke Li, Wei Feng","doi":"10.1109/ROBIO49542.2019.8961762","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961762","url":null,"abstract":"It is important to offer a natural and personalized rehabilitation gait trajectory, especially in the early stages of walking rehabilitation, for the patients with lower limb disability. Lower extremity exoskeleton has been proven to be efficient to provide highly repeatable and accurate rehabilitation exercise, but most existing exoskeletons’ gait trajectories won’t vary with the users. This paper proposes an algorithm, named as gait cell based individualized gait trajectory generation (GC-IGTG), for the purpose of offering a natural and personalized gait trajectory reference for the lower extremity exoskeleton based on the body parameters of the patients. The GC-IGTG is based on extreme learning machine and AutoEncoder, which makes it achieve fast training speed and suitable for small sample training conditions. The gait cell concept is proposed to improve the efficiency and safety of the algorithm. The experimental results indicate that the generated trajectories with GC-IGTG are almost identical to the original ones.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117162163","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":"Robust Identification of Visual Markers Under Boundary Occlusion Condition*","authors":"Ruijie Chang, Yanjie Li, Chongying Wu","doi":"10.1109/ROBIO49542.2019.8961861","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961861","url":null,"abstract":"Visual markers are widely used in indoor marker-based positioning systems to achieve higher speed and accurate positioning performance. However, the classic mark identification methods have certain limitations when encountering complex conditions. Especially, if the marker’s boundary is blocked, it is almost impossible to identify the marker. In this paper, we redefine the identification task to a classification task based on CNN method. We also do some image transformations to create the dataset for our task. We train our dataset by transfer learning based on Google’s Inception-V3 CNN model. The experimental results show that the classification method can handle the boundary occlusion problem well, which is also proved to be useful for other complex conditions.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"145 35","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120968839","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 Indirect Control Method to Stabilize Tension in the Process of Towing Transfer","authors":"L. Shen, Zhongjie Meng, Panfeng Huang","doi":"10.1109/ROBIO49542.2019.8961484","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961484","url":null,"abstract":"This paper proposes an indirect control method to stabilize tension for the tethered space system in the process of towing transfer. In the paper, the Kalman filter is designed to estimate the length of the tether and the mass of the debris under the premise that the tension can be measured. The space platform and the debris are both regarded as mass points and the tether is regarded as the massless rigid rod. On the basis of the assumptions, the tension model and the centroid dynamics model are established. And the optimal tether retraction rate is obtained by using the nominal robust model predictive control. The simulation results of our method show that the Kalman filtering method is used for quality identification, and its estimation is close to the real value. The designed control scheme has good control performance and can effectively track the tension step command.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127204189","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":"Driving Flip Origami Motions with Thermal-Responsive Shape Memory Alloy","authors":"Yan Zhang, Hongliang Ren","doi":"10.1109/ROBIO49542.2019.8961539","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961539","url":null,"abstract":"This paper proposes a motion generation approach to flipping origami models. According to the geometrical principle of an infinite flip origami and using the shape memory properties of nickel-titanium alloy with temperature change, the memory alloy spring is selected as the driving units of origami motions. With conductivity, aluminum foil paper is selected as the wire connecting the memory alloy spring. By designing different circuit connection manners, the memory alloy spring will change the temperature deformation and then drive the movement of the origami. The paper provides a detailed description of how to use the geometric principle to design the origami shape, and analyze the movement principle of the model. We use aluminum foil paper and memory alloy spring with serial and parallel circuit design to study the motion form of the combination of origami and memory alloy spring.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127357527","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}
Hao Deng, Hang Su, T. Mei, Wenjun Xu, Zhen Cheng, Xiang Dong
{"title":"Introduction of a Flexible Adaptive AUV-Capture Device Based on bio-inspired hydraulic Soft Robot","authors":"Hao Deng, Hang Su, T. Mei, Wenjun Xu, Zhen Cheng, Xiang Dong","doi":"10.1109/ROBIO49542.2019.8961608","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961608","url":null,"abstract":"To capture the non-cooperative and cross-scale underwater objects, an underwater soft bionic robot is proposed according to task function analysis and bionics inspiration. The device was mainly composed of a soft bionic arm and a soft body. It has the abilities of long-distance reachability, end pose adjustment, cross-scale capture, target measurement and recognition. The soft bionic arm is driven by water filling, which has the characteristics of light weight and large shrinkage ratio. It consists of several serially arranged modular soft actuators with diverse functions which can be designed for deep-sea object retrieving. The soft modules are connected by quick-shift joints, which make it possible to adjust the arm configuration specific to the task requirement in situ. The method to test the performance of each functional module is also introduced.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127479589","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}
Jiangyu Lai, Lanqing Guo, Y. Qiao, XiaoLong Chen, Z. Zhang, Canping Liu, Ying Li, Bin Fu
{"title":"Robust Text Line Detection in Equipment Nameplate Images*","authors":"Jiangyu Lai, Lanqing Guo, Y. Qiao, XiaoLong Chen, Z. Zhang, Canping Liu, Ying Li, Bin Fu","doi":"10.1109/ROBIO49542.2019.8961581","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961581","url":null,"abstract":"Scene text detection for equipment nameplates in the wild is important for equipment inspection robot since it enables inspection robot to take specific actions for different equipment’s. Although text detection in images has achieved great progress in recent years, the detection for equipment nameplates faces several challenges such as extreme illumination and distortion which significantly decrease the detection performance. In this paper, we propose a deep text detection model Robust Text Line Detection (RTLD) for locating word level text instances in equipment cards. Specifically, the proposed model first employs a corner detection module to determine the four corner points of each nameplate, and then a carefully designed image transformed module transforms the irregular nameplate region into a rectangular region. Finally, text detection module is introduced to locate every word level text instance in the transformed images. We conduct extensive experiments to examine our proposed methods on real equipment nameplate images. Our model achieves 91.2% precision and 92.6% recall on Equipment Nameplate Dataset. The experimental results demonstrate the effectiveness of our models.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124812342","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}
Jiayi Qiu, J. Hou, Chongfeng Liu, Hengli Liu, Xiongwei Lin, Zhenglong Sun, Ning Ding, Tin Lun Lam, Huihuan Qian
{"title":"A New Turbine-Sail Coupled Propulsive System for Autonomous Sailboats*","authors":"Jiayi Qiu, J. Hou, Chongfeng Liu, Hengli Liu, Xiongwei Lin, Zhenglong Sun, Ning Ding, Tin Lun Lam, Huihuan Qian","doi":"10.1109/ROBIO49542.2019.8961692","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961692","url":null,"abstract":"Autonomous sailboats are good candidates to perform long-term missions in oceans since they are wind-propelled. Furthermore, wind turbine is a useful device that can provide autonomous sailboats with necessary electrical energy to support controller, drive rudder and sail. Some current applications for onboard wind turbines can reduce fuel demand of autonomous power sailboats. Apart from necessary electrical energy supply, autonomous sailboats also need enough propelling forces to move efficiently in the direction of the course.In this paper, we propose a new turbine-sail coupled system that utilizes wind sources by adding two vertical wind turbines on both sides of the sail. Experiments are conducted in a wind tunnel. The results show that the system can increase the maximum propelling force when sailing downwind and allow further regulation of the force by slowing the rotation speed of wind turbine on one side.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125056110","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":"Synergistic Optimization based Binaural Time-Frequency Masking for Speech Source Localization","authors":"Hong Liu, Lulu Wu, Bing Yang","doi":"10.1109/ROBIO49542.2019.8961527","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961527","url":null,"abstract":"Monaural time-frequency (TF) masking has been demonstrated to advance the performance of binaural speech source localization. However, it fails to consider interaural information, which may result in severe distortion of interaural cues. To mitigate these impacts, this paper presents a novel method for binaural speech source localization based on binaural TF masking. Firstly, the CNN-based binaural TF masking network is designed to suppress the noise and reverberation in TF fragments, which is trained in the independent stage. Then, the resulted binaural TF masking is synergistically refined with the localization network to compensate for the distorted interaural cues. The final source direction is estimated using the trained network. The proposed method is compared with other baseline methods and two-stage models composed by cascade TF masking network and localization network. Experimental results show our method outperforms the other compared methods in the adverse environments with different reverberation time and signal-to-noise ratios.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125897856","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}