Magnetic microrobots are promising for biomedical applications in living organisms, thanks to their remote actuation and non-contact manipulation capabilities. However, controlling single microrobots one after another is technically inefficient. Previous studies showed swarm control of microrobots. Here we introduce a more direct strategy for enhancing the transport efficiency of microrobots by manipulating their assemblies. We present the control of a protein-based microbead system capable of forming magnetic micro-assemblies. By using rotating magnetic fields, we effectively realized the rolling motion of single microbeads, paired microbeads, and assemblies of multiple microbeads. Improved transport velocity is achieved by controlling the assembly of the multiple microrobots. The maximum velocity of the magnetic micro-assembly reaches 1014 μm/s, while the single microbead and micro-dimer is 203 μm/s and 726 μm/s, respectively. And the line coincidence of micro-assembly reaches 0.988. Our results highlight the potential of the controlling strategy based on magnetic assemblies for diverse biomedical applications. The direct control of such magnetic assemblies offers a simpler and more biocompatible solution for improving the transport efficiency of microrobots.
{"title":"Enhanced Locomotion of Protein-Based Microrobots via Magnetic Assemblies*","authors":"Xiangchao Liu, Zhongyi Song, Yuan Liu, Jing Huang, Haifeng Xu","doi":"10.1109/ROBIO58561.2023.10354802","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354802","url":null,"abstract":"Magnetic microrobots are promising for biomedical applications in living organisms, thanks to their remote actuation and non-contact manipulation capabilities. However, controlling single microrobots one after another is technically inefficient. Previous studies showed swarm control of microrobots. Here we introduce a more direct strategy for enhancing the transport efficiency of microrobots by manipulating their assemblies. We present the control of a protein-based microbead system capable of forming magnetic micro-assemblies. By using rotating magnetic fields, we effectively realized the rolling motion of single microbeads, paired microbeads, and assemblies of multiple microbeads. Improved transport velocity is achieved by controlling the assembly of the multiple microrobots. The maximum velocity of the magnetic micro-assembly reaches 1014 μm/s, while the single microbead and micro-dimer is 203 μm/s and 726 μm/s, respectively. And the line coincidence of micro-assembly reaches 0.988. Our results highlight the potential of the controlling strategy based on magnetic assemblies for diverse biomedical applications. The direct control of such magnetic assemblies offers a simpler and more biocompatible solution for improving the transport efficiency of microrobots.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"106 12","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186816","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354790
Zhaoying Wang, Xu Li, Wenkang Hu
Regular defect inspection of the power line using X-ray is essential for the maintenance of the power line. Usually, conducting such an inspection with a wheeled robot requires dragging the robot from the ground and carefully placing it upon the power line, which is laborious and unsafe. To improve inspection efficiency, the newly developed unmanned aerial vehicle (UAV) provides a promising alternative. However, the positioning error from Global Navigation Satellite System (GNSS) brings the small-scaled drifting movement of the UAV and X-ray camera system, which leads to imaging blur. To cope with this issue, we design a flexible towed aerial robot system to alleviate the instability of the X-ray camera system. Specifically, the UAV and X-ray camera carrier are flexibly connected by a cluster of ropes, reducing the physical impact from the small-scaled drifting movement of the UAV. The permitting position error tolerance between the UAV and the carrier is analyzed. In addition, a guide wheel frame is designed on the carrier to facilitate the carrier’s smooth rolling along the power line. Furthermore, aiming to adapt to the different types of power lines, we design a lightweight motor-driven system to adjust the camera angles and the imaging plate position. Multi-view cameras are also designed to assist the pilot to control the UAV carrying the X-ray camera system landing on the power line. To verify the performance of the developed aerial robot system, we conduct real-world experiments with double bundle conductors and four bundle conductors. The results show that the developed system can efficiently complete inspection. The X-ray camera could obtain a stable imaging condition under the small drifting movement of the flight.
使用 X 射线对电力线进行定期缺陷检查对于维护电力线至关重要。通常情况下，使用轮式机器人进行此类检查需要将机器人从地面拖起，然后小心翼翼地放在电力线上，既费力又不安全。为了提高巡检效率，新开发的无人飞行器（UAV）提供了一个很有前途的替代方案。然而，全球导航卫星系统（GNSS）的定位误差会带来无人飞行器和 X 射线摄像系统的小范围漂移，从而导致成像模糊。为解决这一问题，我们设计了一种灵活的牵引式空中机器人系统，以缓解 X 射线摄像系统的不稳定性。具体来说，无人机和 X 射线照相机载体通过一组绳索柔性连接，减少了无人机小范围漂移带来的物理影响。分析了无人机和载体之间的允许位置误差容限。此外，还在载体上设计了导轮架，以方便载体沿电力线平稳滚动。此外，为了适应不同类型的电力线，我们设计了一种轻型电机驱动系统，用于调整相机角度和成像板位置。我们还设计了多视角摄像头，以协助飞行员控制携带 X 射线摄像系统的无人机在电力线上着陆。为了验证所开发的空中机器人系统的性能，我们对双束导线和四束导线进行了实际实验。结果表明，所开发的系统可以高效地完成检测。X 射线照相机在飞行过程中的微小漂移下也能获得稳定的成像条件。
{"title":"A Flexible Towed Aerial Robot System for Stable X-ray Inspection of Power Lines","authors":"Zhaoying Wang, Xu Li, Wenkang Hu","doi":"10.1109/ROBIO58561.2023.10354790","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354790","url":null,"abstract":"Regular defect inspection of the power line using X-ray is essential for the maintenance of the power line. Usually, conducting such an inspection with a wheeled robot requires dragging the robot from the ground and carefully placing it upon the power line, which is laborious and unsafe. To improve inspection efficiency, the newly developed unmanned aerial vehicle (UAV) provides a promising alternative. However, the positioning error from Global Navigation Satellite System (GNSS) brings the small-scaled drifting movement of the UAV and X-ray camera system, which leads to imaging blur. To cope with this issue, we design a flexible towed aerial robot system to alleviate the instability of the X-ray camera system. Specifically, the UAV and X-ray camera carrier are flexibly connected by a cluster of ropes, reducing the physical impact from the small-scaled drifting movement of the UAV. The permitting position error tolerance between the UAV and the carrier is analyzed. In addition, a guide wheel frame is designed on the carrier to facilitate the carrier’s smooth rolling along the power line. Furthermore, aiming to adapt to the different types of power lines, we design a lightweight motor-driven system to adjust the camera angles and the imaging plate position. Multi-view cameras are also designed to assist the pilot to control the UAV carrying the X-ray camera system landing on the power line. To verify the performance of the developed aerial robot system, we conduct real-world experiments with double bundle conductors and four bundle conductors. The results show that the developed system can efficiently complete inspection. The X-ray camera could obtain a stable imaging condition under the small drifting movement of the flight.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"95 12","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186822","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354962
Yiqi Li, Yelin Jiang, Koh Hosoda
In order to control the motion of a robot, a successful approach is to approximate the robot dynamics as a simplified model. However, the discrepancies between the actual mechanical properties of the robot and the simplified model will result in motion failure for the robot. To address this issue, this paper proposes a pneumatic-driven bipedal musculoskeletal robot that match the mechanistic properties of a simplified spring-loaded inverted pendulum (SLIP) model. The SLIP model is widely applied to robots because it exhibits passive stability and dynamic properties that are similar to human gaits. We designed a musculoskeletal biped robot with its center of mass concentrated in the small body near the hip joint, with low leg inertia based on the properties of the SLIP model. In addition, it it has been verified that the robot exhibits similar characteristics to the SLIP model through a sequential jumping experiment.
{"title":"Spring Loaded Inverted Pendulum Model Based Musculoskeletal Biped Robot Design and Sequential Jumping Experiment","authors":"Yiqi Li, Yelin Jiang, Koh Hosoda","doi":"10.1109/ROBIO58561.2023.10354962","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354962","url":null,"abstract":"In order to control the motion of a robot, a successful approach is to approximate the robot dynamics as a simplified model. However, the discrepancies between the actual mechanical properties of the robot and the simplified model will result in motion failure for the robot. To address this issue, this paper proposes a pneumatic-driven bipedal musculoskeletal robot that match the mechanistic properties of a simplified spring-loaded inverted pendulum (SLIP) model. The SLIP model is widely applied to robots because it exhibits passive stability and dynamic properties that are similar to human gaits. We designed a musculoskeletal biped robot with its center of mass concentrated in the small body near the hip joint, with low leg inertia based on the properties of the SLIP model. In addition, it it has been verified that the robot exhibits similar characteristics to the SLIP model through a sequential jumping experiment.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"94 12","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186829","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10355028
Hanne Say, E. Oztop
In continual learning, usually a sequence of tasks are given to a learning agent and the performance of the agent after learning is measured in terms of resistance to catastrophic forgetting, efficacy of knowledge transfer and overall performance on the individual tasks. On the other hand, in multi-task learning, the system is designed to simultaneously acquire knowledge in multiple tasks, often through offline batch learning. A more cognitively valid scenario for lifelong robot learning would be to have a robotic agent to autonomously decide which task to engage and disengage while leveraging many-to-many knowledge transfer ability among tasks during online learning. In this study, we propose a novel lifelong robot learning architecture to fulfill the aforementioned desiderata, and show its validity in an environment where a robot learns the effects of its actions in different task settings. To realize the proposed model, we adopt learning progress measure for task selection, and have the tasks learn by independent neural networks with special structure that allows access to the neural layers of the non-selected tasks. The experiments conducted with a simulated robot arm in an object interaction scenario show that the proposed architecture yields better knowledge transfer and facilitates faster learning compared to baselines of fixed sequence task learning and isolated task learners with no knowledge transfer.
{"title":"A Model for Cognitively Valid Lifelong Learning","authors":"Hanne Say, E. Oztop","doi":"10.1109/ROBIO58561.2023.10355028","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10355028","url":null,"abstract":"In continual learning, usually a sequence of tasks are given to a learning agent and the performance of the agent after learning is measured in terms of resistance to catastrophic forgetting, efficacy of knowledge transfer and overall performance on the individual tasks. On the other hand, in multi-task learning, the system is designed to simultaneously acquire knowledge in multiple tasks, often through offline batch learning. A more cognitively valid scenario for lifelong robot learning would be to have a robotic agent to autonomously decide which task to engage and disengage while leveraging many-to-many knowledge transfer ability among tasks during online learning. In this study, we propose a novel lifelong robot learning architecture to fulfill the aforementioned desiderata, and show its validity in an environment where a robot learns the effects of its actions in different task settings. To realize the proposed model, we adopt learning progress measure for task selection, and have the tasks learn by independent neural networks with special structure that allows access to the neural layers of the non-selected tasks. The experiments conducted with a simulated robot arm in an object interaction scenario show that the proposed architecture yields better knowledge transfer and facilitates faster learning compared to baselines of fixed sequence task learning and isolated task learners with no knowledge transfer.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"83 8","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186865","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354777
Zhenzhen Tan, Wangjie Zhou, Jie Chen, Yang Xian, Quan Zhang, Long Li, Tao Yue, Yingzhong Tian, Sicheng Yi
This paper studies the stabilization control of underactuated Unmanned Surface Vehicles (USV). Firstly, a three-degree-of-freedom (3-DOF) of underactuated USV in complex sea conditions is established. On this basis, a backstepping sliding mode stability controller based on disturbance observer (BSMC-NDC) for USV is designed. The backstepping sliding mode control strategy is used to achieve the stabilization control effect, and the hyperbolic tangent continuous sliding mode is used to reduce the controller jitter. Aiming at the complicated ocean disturbance in the process of USV stabilization, a 3-DOF disturbance observer based on exponential convergence is designed. The effectiveness of the control system is fully verfied by comparing the simulation results of similar controllers. Specifically, simulation results show that the proposed controller can achieve the USV stabilization control and solve the jitter problem in the sliding mode control process.
{"title":"Backstepping sliding mode stabilization controller for underactuated unmanned surface vehicle based on disturbance observer","authors":"Zhenzhen Tan, Wangjie Zhou, Jie Chen, Yang Xian, Quan Zhang, Long Li, Tao Yue, Yingzhong Tian, Sicheng Yi","doi":"10.1109/ROBIO58561.2023.10354777","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354777","url":null,"abstract":"This paper studies the stabilization control of underactuated Unmanned Surface Vehicles (USV). Firstly, a three-degree-of-freedom (3-DOF) of underactuated USV in complex sea conditions is established. On this basis, a backstepping sliding mode stability controller based on disturbance observer (BSMC-NDC) for USV is designed. The backstepping sliding mode control strategy is used to achieve the stabilization control effect, and the hyperbolic tangent continuous sliding mode is used to reduce the controller jitter. Aiming at the complicated ocean disturbance in the process of USV stabilization, a 3-DOF disturbance observer based on exponential convergence is designed. The effectiveness of the control system is fully verfied by comparing the simulation results of similar controllers. Specifically, simulation results show that the proposed controller can achieve the USV stabilization control and solve the jitter problem in the sliding mode control process.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"103 10","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186893","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354772
Jizhong Liang, Han Sun, Xinhao Chen, Yuanze Gu, Qixin Cao
The majority of current bin picking systems, designed for industrial parts, cannot be directly oriented to the downstream task after grasping. This research presents a grasping framework that addresses this challenge by incorporating pose estimation of parts in cluttered bin environments and the targeted design of robot end-effector grippers. This approach ensures that the pose of the part on the gripper is known and fixed, enabling successful assembly tasks in various scenarios. To train an object pose estimation network, we propose a system for generating a dataset of industrial parts using model rendering within a physics engine. We analyze the geometric features of the parts, and further design a gripper, to achieve the grasping strategy. Results demonstrate that for a single known industrial part, the minimum grasping success rate is 91.4% in simulated robot experiments, and the assembly success rates in different scenarios based on this framework exceed 80%. Our framework offers valuable guidance for the deployment of robotic grasping.
{"title":"An Industrial Bin Picking Framework for Assembly Tasks","authors":"Jizhong Liang, Han Sun, Xinhao Chen, Yuanze Gu, Qixin Cao","doi":"10.1109/ROBIO58561.2023.10354772","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354772","url":null,"abstract":"The majority of current bin picking systems, designed for industrial parts, cannot be directly oriented to the downstream task after grasping. This research presents a grasping framework that addresses this challenge by incorporating pose estimation of parts in cluttered bin environments and the targeted design of robot end-effector grippers. This approach ensures that the pose of the part on the gripper is known and fixed, enabling successful assembly tasks in various scenarios. To train an object pose estimation network, we propose a system for generating a dataset of industrial parts using model rendering within a physics engine. We analyze the geometric features of the parts, and further design a gripper, to achieve the grasping strategy. Results demonstrate that for a single known industrial part, the minimum grasping success rate is 91.4% in simulated robot experiments, and the assembly success rates in different scenarios based on this framework exceed 80%. Our framework offers valuable guidance for the deployment of robotic grasping.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"1 3","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186919","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354649
Lucas W. Artmann, Valentin Ameres, Tim C. Lueth
The study presents a new system for automating media exchange in cell cultures. This system is designed to fit inside common incubators and uses T75 flasks as growth vessels. It follows a step-by-step process, involving rotating and tilting mechanisms to drain old media, cleanse flask interiors, and refill with fresh media. The system's design incorporates a loading platform for four flasks, driven by a stepper motor and gear mechanism. Tilting is controlled by a servo motor, while a peristaltic pump refills with fresh media. Electronics, including an Arduino Nano, are sealed for protection. Sensors ensure flask presence and media condition. Validation involved 200 water-based cycles and successful fibroblast cell culture for eight days. The system shows potential for streamlining cell maintenance, although long-term durability and contamination concerns require further investigation.
{"title":"Cell Culture Media Exchange Automation for Screw Cap Flasks within Incubators","authors":"Lucas W. Artmann, Valentin Ameres, Tim C. Lueth","doi":"10.1109/ROBIO58561.2023.10354649","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354649","url":null,"abstract":"The study presents a new system for automating media exchange in cell cultures. This system is designed to fit inside common incubators and uses T75 flasks as growth vessels. It follows a step-by-step process, involving rotating and tilting mechanisms to drain old media, cleanse flask interiors, and refill with fresh media. The system's design incorporates a loading platform for four flasks, driven by a stepper motor and gear mechanism. Tilting is controlled by a servo motor, while a peristaltic pump refills with fresh media. Electronics, including an Arduino Nano, are sealed for protection. Sensors ensure flask presence and media condition. Validation involved 200 water-based cycles and successful fibroblast cell culture for eight days. The system shows potential for streamlining cell maintenance, although long-term durability and contamination concerns require further investigation.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"113 5","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186920","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354748
Di Wu, Yuping Ye, Feifei Gu, Zhan Song
With the fast development of computer vision and artificial intelligence, many technologies from these fields have been introduced to the medical domain. Accurate estimation of burnt skin area is crucial for treatment plan selection and prognostic decision-making. However, state-of-art estimation of burnt skin area exhibits inadequate accuracy and acquisition efficiency. In this paper, a burnt skin acquisition system based on the infrared structured light 3D imaging method is developed. To accurately segment the burnt skin point cloud from the raw point cloud acquired by the proposed system, we employ the Segment Anything Model (SAM). Subsequently, the point clouds segmented from different views are registered using pre-calibrated parameters. Moreover, the surface reconstruction algorithm is employed to generate triangular meshes. Finally, we calculate the area of all the triangular mesh facets to represent the area of burnt skin. Several experiments were conducted to demonstrate the accuracy of the proposed method.
{"title":"A Quick Means for the Burnt Skin Area Calculation via Multiple-view Structured Light Sensors","authors":"Di Wu, Yuping Ye, Feifei Gu, Zhan Song","doi":"10.1109/ROBIO58561.2023.10354748","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354748","url":null,"abstract":"With the fast development of computer vision and artificial intelligence, many technologies from these fields have been introduced to the medical domain. Accurate estimation of burnt skin area is crucial for treatment plan selection and prognostic decision-making. However, state-of-art estimation of burnt skin area exhibits inadequate accuracy and acquisition efficiency. In this paper, a burnt skin acquisition system based on the infrared structured light 3D imaging method is developed. To accurately segment the burnt skin point cloud from the raw point cloud acquired by the proposed system, we employ the Segment Anything Model (SAM). Subsequently, the point clouds segmented from different views are registered using pre-calibrated parameters. Moreover, the surface reconstruction algorithm is employed to generate triangular meshes. Finally, we calculate the area of all the triangular mesh facets to represent the area of burnt skin. Several experiments were conducted to demonstrate the accuracy of the proposed method.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"76 5","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139186953","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354936
Liangjie Tu, Fugang Yi, Bingfei Fan, Mingyu Du, Shibo Cai
Elderly people are easy to suffer from accidental injuries due to loss-of-balance in daily life. Wearable sensing technology is promising for detecting or predicting loss-of-balance events. This paper proposes a human loss-of-balance prediction method based on a customized wearable plantar pressure sensing system. To realize accurate prediction of loss-of-balance, we integrate the simulated annealing algorithm (SA) and the random forest algorithm (RF) to construct a SA-RF prediction model, where the input of the model is the plantar pressure data of the feet and the output of the model is the label of the human motion state. To validate the effectiveness of the proposed SA-RF model, 15 healthy subjects participated in the experiments. The experimental results show that the classification and recognition accuracy of the SA-RF model are significantly improved compared to the RF model, especially for the recognition of the easily loss-of-balance state. The accuracy of the proposed SA-RF model reaches 90%, which is a 5% improvement compared to the RF model. Therefore, the use of the SA-RF model based on plantar pressure can effectively predict loss-of-balance and thus has the potential to be integrated into fall prevention applications.
{"title":"Prediction of Loss-of-Balance of the Human Based on Plantar Pressure by Using the SA-RF Algorithm","authors":"Liangjie Tu, Fugang Yi, Bingfei Fan, Mingyu Du, Shibo Cai","doi":"10.1109/ROBIO58561.2023.10354936","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354936","url":null,"abstract":"Elderly people are easy to suffer from accidental injuries due to loss-of-balance in daily life. Wearable sensing technology is promising for detecting or predicting loss-of-balance events. This paper proposes a human loss-of-balance prediction method based on a customized wearable plantar pressure sensing system. To realize accurate prediction of loss-of-balance, we integrate the simulated annealing algorithm (SA) and the random forest algorithm (RF) to construct a SA-RF prediction model, where the input of the model is the plantar pressure data of the feet and the output of the model is the label of the human motion state. To validate the effectiveness of the proposed SA-RF model, 15 healthy subjects participated in the experiments. The experimental results show that the classification and recognition accuracy of the SA-RF model are significantly improved compared to the RF model, especially for the recognition of the easily loss-of-balance state. The accuracy of the proposed SA-RF model reaches 90%, which is a 5% improvement compared to the RF model. Therefore, the use of the SA-RF model based on plantar pressure can effectively predict loss-of-balance and thus has the potential to be integrated into fall prevention applications.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"64 6","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187001","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}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354940
Junqiu Wang, Jianmei Tan, Peng Lin, Chenguang Xing, Bo Liu
We propose an effective stall recovery learning approach based on a soft actor-critic algorithm with smooth reward functions. Stalling is extremely dangerous for aircraft and unmanned aerial vehicles (UAVs) because altitude decreases can result in fatal accidents. Stall recovery policies perform appropriate control sequences to save aircrafts from such lethal situations. Learning stall recovery policies using reinforcement learning methods is desirable because such policies can be learned automatically. However, stall recovery training is challenging since the interplay between an aircraft and its environment is very complicated. In this work, the proposed stall recovery learning approach yields better performance than other methods. We successfully apply smooth reward functions to the learning process because reward functions are critical for the convergence of policy learning. We achieve good performance by applying reward scaling to the soft actor-critic algorithm with automatic entropy learning. Experimental results demonstrate that stalls can be successfully recovered using the learned policies. The comparison results show that our method provides better results than previous algorithms.
{"title":"Learning Stall Recovery Policies using a Soft Actor-Critic Algorithm with Smooth Reward Functions","authors":"Junqiu Wang, Jianmei Tan, Peng Lin, Chenguang Xing, Bo Liu","doi":"10.1109/ROBIO58561.2023.10354940","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354940","url":null,"abstract":"We propose an effective stall recovery learning approach based on a soft actor-critic algorithm with smooth reward functions. Stalling is extremely dangerous for aircraft and unmanned aerial vehicles (UAVs) because altitude decreases can result in fatal accidents. Stall recovery policies perform appropriate control sequences to save aircrafts from such lethal situations. Learning stall recovery policies using reinforcement learning methods is desirable because such policies can be learned automatically. However, stall recovery training is challenging since the interplay between an aircraft and its environment is very complicated. In this work, the proposed stall recovery learning approach yields better performance than other methods. We successfully apply smooth reward functions to the learning process because reward functions are critical for the convergence of policy learning. We achieve good performance by applying reward scaling to the soft actor-critic algorithm with automatic entropy learning. Experimental results demonstrate that stalls can be successfully recovered using the learned policies. The comparison results show that our method provides better results than previous algorithms.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"64 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187005","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：