Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3495453
Farhad Aghili
This paper introduces an innovative guidance and control method for simultaneously capturing and stabilizing a target satellite using a spinning-base servicing satellite equipped with a robotic manipulator, joint locks, and reaction wheels (RWs). We assume the target satellite reaches a state of minimum kinetic energy due to the slow dissipation of energy caused by internal friction, resulting in a pure major axis spin. The method involves controlling the RWs of the servicing satellite to replicate the spinning motion of the target satellite while locking the manipulator's joints to achieve spin-matching. This maneuver makes the target stationary with respect to the rotating frame of the servicing satellite located at its center-of-mass (CoM), simplifying the robot capture trajectory planning and eliminating post-capture trajectory planning entirely. In the next phase, the joints are unlocked, and a coordination controller drives the robotic manipulator to capture the target satellite while maintaining zero relative rotation between the servicing and target satellites. The spin stabilization phase begins after completing the capture phase, where the joints are locked to form a single tumbling rigid body consisting of the rigidly connected servicing and target satellites. An optimal controller applies negative control torques to the RWs to dampen out the tumbling motion of the interconnected satellites as quickly as possible, subject to the actuation torque limit of the RWs and the maximum torque and force exerted by the manipulator's end-effector.
{"title":"Spinning-Base Space Robot for Seamless Capture and Stabilization of Rotating Objects","authors":"Farhad Aghili","doi":"10.1109/LRA.2024.3495453","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495453","url":null,"abstract":"This paper introduces an innovative guidance and control method for simultaneously capturing and stabilizing a target satellite using a spinning-base servicing satellite equipped with a robotic manipulator, joint locks, and reaction wheels (RWs). We assume the target satellite reaches a state of minimum kinetic energy due to the slow dissipation of energy caused by internal friction, resulting in a pure major axis spin. The method involves controlling the RWs of the servicing satellite to replicate the spinning motion of the target satellite while locking the manipulator's joints to achieve spin-matching. This maneuver makes the target stationary with respect to the rotating frame of the servicing satellite located at its center-of-mass (CoM), simplifying the robot capture trajectory planning and eliminating post-capture trajectory planning entirely. In the next phase, the joints are unlocked, and a coordination controller drives the robotic manipulator to capture the target satellite while maintaining zero relative rotation between the servicing and target satellites. The spin stabilization phase begins after completing the capture phase, where the joints are locked to form a single tumbling rigid body consisting of the rigidly connected servicing and target satellites. An optimal controller applies negative control torques to the RWs to dampen out the tumbling motion of the interconnected satellites as quickly as possible, subject to the actuation torque limit of the RWs and the maximum torque and force exerted by the manipulator's end-effector.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11593-11600"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3495372
Bang-Shien Chen;Yu-Kai Lin;Jian-Yu Chen;Chih-Wei Huang;Jann-Long Chern;Ching-Cherng Sun
Robust estimation is essential in computer vision, robotics, and navigation, aiming to minimize the impact of outlier measurements for improved accuracy. We present a fast algorithm for Geman-McClure robust estimation, FracGM, leveraging fractional programming techniques. This solver reformulates the original non-convex fractional problem to a convex dual problem and a linear equation system, iteratively solving them in an alternating optimization pattern. Compared to graduated non-convexity approaches, this strategy exhibits a faster convergence rate and better outlier rejection capability. In addition, the global optimality of the proposed solver can be guaranteed under given conditions. We demonstrate the proposed FracGM solver with Wahba's rotation problem and 3-D point-cloud registration along with relaxation pre-processing and projection post-processing. Compared to state-of-the-art algorithms, when the outlier rates increase from 20% to 80%, FracGM shows 53% and 88% lower rotation and translation increases. In real-world scenarios, FracGM achieves better results in 13 out of 18 outcomes, while having a 19.43% improvement in the computation time.
{"title":"FracGM: A Fast Fractional Programming Technique for Geman-McClure Robust Estimator","authors":"Bang-Shien Chen;Yu-Kai Lin;Jian-Yu Chen;Chih-Wei Huang;Jann-Long Chern;Ching-Cherng Sun","doi":"10.1109/LRA.2024.3495372","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495372","url":null,"abstract":"Robust estimation is essential in computer vision, robotics, and navigation, aiming to minimize the impact of outlier measurements for improved accuracy. We present a fast algorithm for Geman-McClure robust estimation, FracGM, leveraging fractional programming techniques. This solver reformulates the original non-convex fractional problem to a convex dual problem and a linear equation system, iteratively solving them in an alternating optimization pattern. Compared to graduated non-convexity approaches, this strategy exhibits a faster convergence rate and better outlier rejection capability. In addition, the global optimality of the proposed solver can be guaranteed under given conditions. We demonstrate the proposed FracGM solver with Wahba's rotation problem and 3-D point-cloud registration along with relaxation pre-processing and projection post-processing. Compared to state-of-the-art algorithms, when the outlier rates increase from 20% to 80%, FracGM shows 53% and 88% lower rotation and translation increases. In real-world scenarios, FracGM achieves better results in 13 out of 18 outcomes, while having a 19.43% improvement in the computation time.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11666-11673"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3495455
Neng Wang;Xieyuanli Chen;Chenghao Shi;Zhiqiang Zheng;Hongshan Yu;Huimin Lu
Loop closing is a crucial component in SLAM that helps eliminate accumulated errors through two main steps: loop detection and loop pose correction. The first step determines whether loop closing should be performed, while the second estimates the 6-DoF pose to correct odometry drift. Current methods mostly focus on developing robust descriptors for loop closure detection, often neglecting loop pose estimation. A few methods that do include pose estimation either suffer from low accuracy or incur high computational costs. To tackle this problem, we introduce SGLC, a real-time semantic graph-guided full loop closing method, with robust loop closure detection and 6-DoF pose estimation capabilities. SGLC takes into account the distinct characteristics of foreground and background points. For foreground instances, it builds a semantic graph that not only abstracts point cloud representation for fast descriptor generation and matching but also guides the subsequent loop verification and initial pose estimation. Background points, meanwhile, are exploited to provide more geometric features for scan-wise descriptor construction and stable planar information for further pose refinement. Loop pose estimation employs a coarse-fine-refine registration scheme that considers the alignment of both instance points and background points, offering high efficiency and accuracy. Extensive experiments on multiple publicly available datasets demonstrate its superiority over state-of-the-art methods. Additionally, we integrate SGLC into a SLAM system, eliminating accumulated errors and improving overall SLAM performance.
闭环是 SLAM 的一个重要组成部分，它通过两个主要步骤帮助消除累积误差：环路检测和环路姿态校正。第一步是确定是否应执行闭环，第二步是估计 6-DoF 姿态以纠正里程漂移。目前的方法大多侧重于开发用于环路闭合检测的鲁棒描述符，往往忽略了环路姿态估计。少数包含姿态估计的方法要么精度低，要么计算成本高。为了解决这个问题，我们引入了 SGLC，这是一种实时语义图引导的全闭环方法，具有鲁棒闭环检测和 6-DoF 姿势估计功能。SGLC 考虑了前景点和背景点的不同特征。对于前景实例，它建立了一个语义图，不仅抽象了点云表示，以便快速生成描述符和进行匹配，还能指导后续的环路验证和初始姿态估计。同时，背景点还能为扫描描述符的构建提供更多几何特征，并为进一步的姿态改进提供稳定的平面信息。环路姿态估计采用了一种粗-细-精配准方案，该方案同时考虑了实例点和背景点的配准，具有高效率和高精度的特点。在多个公开数据集上进行的广泛实验证明，它优于最先进的方法。此外，我们还将 SGLC 集成到 SLAM 系统中，消除了累积误差，提高了 SLAM 的整体性能。
{"title":"SGLC: Semantic Graph-Guided Coarse-Fine-Refine Full Loop Closing for LiDAR SLAM","authors":"Neng Wang;Xieyuanli Chen;Chenghao Shi;Zhiqiang Zheng;Hongshan Yu;Huimin Lu","doi":"10.1109/LRA.2024.3495455","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495455","url":null,"abstract":"Loop closing is a crucial component in SLAM that helps eliminate accumulated errors through two main steps: loop detection and loop pose correction. The first step determines whether loop closing should be performed, while the second estimates the 6-DoF pose to correct odometry drift. Current methods mostly focus on developing robust descriptors for loop closure detection, often neglecting loop pose estimation. A few methods that do include pose estimation either suffer from low accuracy or incur high computational costs. To tackle this problem, we introduce SGLC, a real-time semantic graph-guided full loop closing method, with robust loop closure detection and 6-DoF pose estimation capabilities. SGLC takes into account the distinct characteristics of foreground and background points. For foreground instances, it builds a semantic graph that not only abstracts point cloud representation for fast descriptor generation and matching but also guides the subsequent loop verification and initial pose estimation. Background points, meanwhile, are exploited to provide more geometric features for scan-wise descriptor construction and stable planar information for further pose refinement. Loop pose estimation employs a coarse-fine-refine registration scheme that considers the alignment of both instance points and background points, offering high efficiency and accuracy. Extensive experiments on multiple publicly available datasets demonstrate its superiority over state-of-the-art methods. Additionally, we integrate SGLC into a SLAM system, eliminating accumulated errors and improving overall SLAM performance.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11545-11552"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3495574
Jennifer A. Shum;Perrin E. Schiebel;Alyssa M. Hernandez;Robert J. Wood
While previous studies have explored electroadhesive climbing using the insect-scale Harvard Ambulatory Microrobot platform, the robot's ability to climb reliably over irregular terrain has remained limited. To evaluate potential solutions, we conducted an investigation of the electroadhesive pad design space and characterized the shear force climbing capabilities of the robot with different pad designs. We find that on smooth, flat terrains, a large simple circular footpad structure exhibited the greatest shear forces. However, on rougher inclined surfaces, pads which adjusted the width, length, and number of spoke-like features provide greater compliance and achieve more consistent shear adhesion forces. Such compliant spoke pad designs on rough surfaces performed with 84 % stick reliability and 1.02 kPa average adhesion forces compared to 45 % stick reliability and 0.81 kPa average adhesion forces for a comparable circular pad. We demonstrate the improved climbing capability of the 4.5 cm robot on terrain with 75 $mu$ m roughness and observe an average increase in climbing speed of 48 % over a range of angles from 0–45 degrees.
{"title":"Electroadhesive Pad Design for Increased Adhesion of Climbing Microrobots on Diverse Terrains","authors":"Jennifer A. Shum;Perrin E. Schiebel;Alyssa M. Hernandez;Robert J. Wood","doi":"10.1109/LRA.2024.3495574","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495574","url":null,"abstract":"While previous studies have explored electroadhesive climbing using the insect-scale Harvard Ambulatory Microrobot platform, the robot's ability to climb reliably over irregular terrain has remained limited. To evaluate potential solutions, we conducted an investigation of the electroadhesive pad design space and characterized the shear force climbing capabilities of the robot with different pad designs. We find that on smooth, flat terrains, a large simple circular footpad structure exhibited the greatest shear forces. However, on rougher inclined surfaces, pads which adjusted the width, length, and number of spoke-like features provide greater compliance and achieve more consistent shear adhesion forces. Such compliant spoke pad designs on rough surfaces performed with 84 % stick reliability and 1.02 kPa average adhesion forces compared to 45 % stick reliability and 0.81 kPa average adhesion forces for a comparable circular pad. We demonstrate the improved climbing capability of the 4.5 cm robot on terrain with 75 \u0000<inline-formula><tex-math>$mu$</tex-math></inline-formula>\u0000m roughness and observe an average increase in climbing speed of 48 % over a range of angles from 0–45 degrees.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11569-11576"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3495454
Wangtao Lu;Lei Chen;Yunkai Wang;Yufei Wei;Zifei Wu;Rong Xiong;Yue Wang
Trajectory planning in highly constrained environments is crucial for robotic navigation. Classical algorithms are widely used for their interpretability, generalization, and system robustness. However, these algorithms often require parameter retuning when adapting to new scenarios. To address this issue, we propose a demonstration data-driven reinforcement learning (RL) method for automatic parameter adjustment. Our approach includes two main components: a front-end policy network and a back-end asynchronous controller. The policy network selects appropriate parameters for the trajectory planner, while a discriminator in a Conditional Generative Adversarial Network (CGAN) evaluates the planned trajectory, using this evaluation as an imitation reward in RL. The asynchronous controller is employed for high-frequency trajectory tracking. Experiments conducted in both simulation and real-world demonstrate that our proposed method significantly enhances the performance of classical algorithms.
{"title":"Demonstration Data-Driven Parameter Adjustment for Trajectory Planning in Highly Constrained Environments","authors":"Wangtao Lu;Lei Chen;Yunkai Wang;Yufei Wei;Zifei Wu;Rong Xiong;Yue Wang","doi":"10.1109/LRA.2024.3495454","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495454","url":null,"abstract":"Trajectory planning in highly constrained environments is crucial for robotic navigation. Classical algorithms are widely used for their interpretability, generalization, and system robustness. However, these algorithms often require parameter retuning when adapting to new scenarios. To address this issue, we propose a demonstration data-driven reinforcement learning (RL) method for automatic parameter adjustment. Our approach includes two main components: a front-end policy network and a back-end asynchronous controller. The policy network selects appropriate parameters for the trajectory planner, while a discriminator in a Conditional Generative Adversarial Network (CGAN) evaluates the planned trajectory, using this evaluation as an imitation reward in RL. The asynchronous controller is employed for high-frequency trajectory tracking. Experiments conducted in both simulation and real-world demonstrate that our proposed method significantly enhances the performance of classical algorithms.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11641-11648"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142671934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3495579
Hendrik Schäfke;Tim-Lukas Habich;Christian Muhmann;Simon F. G. Ehlers;Thomas Seel;Moritz Schappler
Soft robots pose difficulties in terms of control, requiring novel strategies to effectively manipulate their compliant structures. Model-based approaches face challenges due to the high dimensionality and nonlinearities such as hysteresis effects. In contrast, learning-based approaches provide nonlinear models of different soft robots based only on measured data. In this letter, recurrent neural networks (RNNs) predict the behavior of an articulated soft robot (ASR) with five degrees of freedom (DoF). RNNs based on gated recurrent units (GRUs) are compared to the more commonly used long short-term memory (LSTM) networks and show better accuracy. The recurrence enables the capture of hysteresis effects that are inherent in soft robots due to viscoelasticity or friction but cannot be captured by simple feedforward networks. The data-driven model is used within a nonlinear model predictive control (NMPC), whereby the correct handling of the RNN's hidden states is focused. A training approach is presented that allows measured values to be utilized in each control cycle. This enables accurate predictions of short horizons based on sensor data, which is crucial for closed-loop NMPC. The proposed learning-based NMPC enables trajectory tracking with an average error of 1.2 $mathrm{^{circ }}$ in experiments with the pneumatic five-DoF ASR.
{"title":"Learning-Based Nonlinear Model Predictive Control of Articulated Soft Robots Using Recurrent Neural Networks","authors":"Hendrik Schäfke;Tim-Lukas Habich;Christian Muhmann;Simon F. G. Ehlers;Thomas Seel;Moritz Schappler","doi":"10.1109/LRA.2024.3495579","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495579","url":null,"abstract":"Soft robots pose difficulties in terms of control, requiring novel strategies to effectively manipulate their compliant structures. Model-based approaches face challenges due to the high dimensionality and nonlinearities such as hysteresis effects. In contrast, learning-based approaches provide nonlinear models of different soft robots based only on measured data. In this letter, recurrent neural networks (RNNs) predict the behavior of an articulated soft robot (ASR) with five degrees of freedom (DoF). RNNs based on gated recurrent units (GRUs) are compared to the more commonly used long short-term memory (LSTM) networks and show better accuracy. The recurrence enables the capture of hysteresis effects that are inherent in soft robots due to viscoelasticity or friction but cannot be captured by simple feedforward networks. The data-driven model is used within a nonlinear model predictive control (NMPC), whereby the correct handling of the RNN's hidden states is focused. A training approach is presented that allows measured values to be utilized in each control cycle. This enables accurate predictions of short horizons based on sensor data, which is crucial for closed-loop NMPC. The proposed learning-based NMPC enables trajectory tracking with an average error of 1.2\u0000<inline-formula><tex-math>$mathrm{^{circ }}$</tex-math></inline-formula>\u0000 in experiments with the pneumatic five-DoF ASR.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11609-11616"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bird's eye view (BEV) segmentation map is a recent development in autonomous driving that provides effective environmental information, such as drivable areas and lane dividers. Most of the existing methods use cameras and LiDAR as inputs for segmentation and the fusion of different modalities is accomplished through either concatenation or addition operations, which fails to exploit fully the correlation and complementarity between modalities. This letter presents the CMGFA (Cross-Modal Group-mix attention Feature Aggregator), an end-to-end learning framework that can adapt to multiple modal feature combinations for BEV segmentation. The CMGFA comprises the following components: i) The camera has a dual-branch structure that strengthens the linkage between local and global features. ii) Multi-head deformable cross-attention is applied as cross-modal feature aggregators to aggregate camera, LiDAR, and Radar feature maps in BEV for implicit fusion. iii) The Group-Mix attention is used to enrich the attention map feature space and enhance the ability to segment between different categories. We evaluate our proposed method on the nuScenes and Argoverse2 datasets, where the CMGFA significantly outperforms the baseline.
{"title":"CMGFA: A BEV Segmentation Model Based on Cross-Modal Group-Mix Attention Feature Aggregator","authors":"Xinkai Kuang;Runxin Niu;Chen Hua;Chunmao Jiang;Hui Zhu;Ziyu Chen;Biao Yu","doi":"10.1109/LRA.2024.3495376","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495376","url":null,"abstract":"Bird's eye view (BEV) segmentation map is a recent development in autonomous driving that provides effective environmental information, such as drivable areas and lane dividers. Most of the existing methods use cameras and LiDAR as inputs for segmentation and the fusion of different modalities is accomplished through either concatenation or addition operations, which fails to exploit fully the correlation and complementarity between modalities. This letter presents the CMGFA (Cross-Modal Group-mix attention Feature Aggregator), an end-to-end learning framework that can adapt to multiple modal feature combinations for BEV segmentation. The CMGFA comprises the following components: i) The camera has a dual-branch structure that strengthens the linkage between local and global features. ii) Multi-head deformable cross-attention is applied as cross-modal feature aggregators to aggregate camera, LiDAR, and Radar feature maps in BEV for implicit fusion. iii) The Group-Mix attention is used to enrich the attention map feature space and enhance the ability to segment between different categories. We evaluate our proposed method on the nuScenes and Argoverse2 datasets, where the CMGFA significantly outperforms the baseline.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11497-11504"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3496315
Yang Tian;Hayato Jitsukawa;Shugen Ma;Guoteng Zhang
With the aging of critical infrastructure like bridges and plant facilities, the development of innovative wall-climbing robots using permanent magnets has become increasingly important. Traditional designs of such robots depend on controlling the position of lifters or permanent magnets to control the adhesion condition, which introduces significant safety concerns, including inconsistent adhesion during surface transitions and the risk of falls when control is lost. To overcome these issues, this paper introduces a novel magnet wheel design that utilizes Soft Magnetic Material (SMM) to control the reduction of adhesive force in a specific direction. The effect on adhesion was shown with a comparative analysis of various magnet and SMM configurations. Based on the analyses, a wheel design was provided with investigating the effect of the SMM cover region. For verifying the effectiveness of the adhesion reduction, a robot with the proposed wheel is presented and analyzed to realize wall-climbing tasks. In experiments, a prototype robot equipped with the proposed wheel design demonstrates enhanced safety for wall-climbing tasks under controlled conditions.
{"title":"Magnetic Wall-Climbing Wheels With Controllable Adhesion Reduction via Soft Magnetic Material","authors":"Yang Tian;Hayato Jitsukawa;Shugen Ma;Guoteng Zhang","doi":"10.1109/LRA.2024.3496315","DOIUrl":"https://doi.org/10.1109/LRA.2024.3496315","url":null,"abstract":"With the aging of critical infrastructure like bridges and plant facilities, the development of innovative wall-climbing robots using permanent magnets has become increasingly important. Traditional designs of such robots depend on controlling the position of lifters or permanent magnets to control the adhesion condition, which introduces significant safety concerns, including inconsistent adhesion during surface transitions and the risk of falls when control is lost. To overcome these issues, this paper introduces a novel magnet wheel design that utilizes Soft Magnetic Material (SMM) to control the reduction of adhesive force in a specific direction. The effect on adhesion was shown with a comparative analysis of various magnet and SMM configurations. Based on the analyses, a wheel design was provided with investigating the effect of the SMM cover region. For verifying the effectiveness of the adhesion reduction, a robot with the proposed wheel is presented and analyzed to realize wall-climbing tasks. In experiments, a prototype robot equipped with the proposed wheel design demonstrates enhanced safety for wall-climbing tasks under controlled conditions.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11553-11560"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intuitive teleoperation enables operators to embody remote robots, providing the sensation that the robot is part of their own body during control. The sense of agency (SoA), i.e., the feeling of controlling the robot, contributes to enhanced motivation and embodiment during teleoperation. However, the SoA can be diminished by time-varying communication delays associated with teleoperation. We propose a visual guidance system to assist operations while maintaining a high SoA when teleoperating robots with time-varying delays, thereby improving positioning accuracy. In the proposed system, a recurrent neural network (RNN) model, trained on the pouring tasks of skilled operators, predicts the input position 500 ms ahead of the input from the novice operator and visually presents it in real-time as the end-effector target position. Experiments with time-varying delays confirmed that the proposed method provides a visual representation of the target position interpolated in time and space from the real-time input of the operator, guiding the operator to align with the trajectory of the skilled operator. The proposed method significantly improves task performance even under time-varying delays while maintaining a high SoA compared with other conditions. Applying the prediction system developed in this study to human-robot collaborative control may enable interventions that maintain the SoA.
直观的远程操作使操作员能够体现远程机器人，在控制过程中提供机器人是自己身体一部分的感觉。代入感（SoA），即控制机器人的感觉，有助于增强远程操作过程中的动力和代入感。然而，远程操作中的时变通信延迟可能会削弱这种代入感。我们提出了一种视觉引导系统，以协助操作，同时在远程操作具有时变延迟的机器人时保持较高的 SoA，从而提高定位精度。在所提出的系统中，根据熟练操作员的倾倒任务训练出的递归神经网络（RNN）模型会在新手操作员输入之前 500 毫秒预测输入位置，并将其作为末端执行器目标位置实时直观地呈现出来。时变延迟实验证实，建议的方法提供了根据操作员的实时输入在时间和空间上插值的目标位置可视化表示，引导操作员与熟练操作员的轨迹保持一致。与其他条件相比，即使在时变延迟的情况下，所提出的方法也能显著提高任务性能，同时保持较高的 SoA。将本研究中开发的预测系统应用于人机协作控制，可以实现保持 SoA 的干预。
{"title":"RNN-Based Visual Guidance for Enhanced Sense of Agency in Teleoperation With Time-Varying Delays","authors":"Tomoya Morita;Simon Armleder;Yaonan Zhu;Hiroto Iino;Tadayoshi Aoyama;Gordon Cheng;Yasuhisa Hasegawa","doi":"10.1109/LRA.2024.3495591","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495591","url":null,"abstract":"Intuitive teleoperation enables operators to embody remote robots, providing the sensation that the robot is part of their own body during control. The sense of agency (SoA), i.e., the feeling of controlling the robot, contributes to enhanced motivation and embodiment during teleoperation. However, the SoA can be diminished by time-varying communication delays associated with teleoperation. We propose a visual guidance system to assist operations while maintaining a high SoA when teleoperating robots with time-varying delays, thereby improving positioning accuracy. In the proposed system, a recurrent neural network (RNN) model, trained on the pouring tasks of skilled operators, predicts the input position 500 ms ahead of the input from the novice operator and visually presents it in real-time as the end-effector target position. Experiments with time-varying delays confirmed that the proposed method provides a visual representation of the target position interpolated in time and space from the real-time input of the operator, guiding the operator to align with the trajectory of the skilled operator. The proposed method significantly improves task performance even under time-varying delays while maintaining a high SoA compared with other conditions. Applying the prediction system developed in this study to human-robot collaborative control may enable interventions that maintain the SoA.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11537-11544"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10750248","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LRA.2024.3495580
Kazuma Takai;Kazuya Murakami;Jun Shintake
Soft robotics, a field dedicated to the development of robots using flexible and compliant materials, has undergone significant progress in recent years, offering a wide range of potential applications. However, most soft robots are fabricated using synthetic elastomeric materials, contributing to environmental pollution and degradation. A potential solution to this problem involves integrating biodegradability into the designs of soft robots, facilitating their degradation through microbial activity and subsequent integration into the soil. However, to achieve this functionality, biodegradable soft robotic elements must be developed. This paper presents biodegradable dielectric elastomer actuators (DEAs) and sensors (DESs). These devices feature a soft dielectric membrane with compliant electrodes on both sides, enabling them to function as both electrostatic actuators and capacitive sensors. Natural rubber and gelatin-based elastomeric materials are employed for the dielectric membrane and electrodes, respectively. Using these materials and established fabrication processes, experimental biodegradable DEA and DES samples are fabricated and characterized. The DEA with a circular actuator configuration demonstrates a voltage-controllable areal strain of up to 15.4% and presents stable operation over 1,000 actuation cycles. The DEA with a bending actuator configuration exhibits a voltage-controllable bending angle of up to 17.4°. The DES demonstrates a linear response for strains up to 200%, with a gauge factor of 0.85, and maintains stability over 10,000 strain cycles. The observed characteristics of the DEAs and DES align well with theoretical predictions, highlighting the potential applicability of biodegradable DEAs and DESs as promising elements for sustainable and environmentally friendly soft robots.
软体机器人技术是一个致力于开发使用柔性和顺应性材料的机器人的领域，近年来取得了重大进展，提供了广泛的潜在应用。然而，大多数软体机器人都是使用合成弹性材料制造的，这会造成环境污染和退化。解决这一问题的潜在办法是将生物降解性融入软体机器人的设计中，通过微生物活动促进其降解，然后融入土壤。然而，要实现这一功能，必须开发可生物降解的软体机器人元件。本文介绍了可生物降解的介电弹性体致动器（DEA）和传感器（DES）。这些装置的特点是软介电薄膜的两侧都有顺应性电极，使其既能用作静电致动器，又能用作电容式传感器。介电膜和电极分别采用天然橡胶和明胶基弹性材料。利用这些材料和成熟的制造工艺，制造出了可生物降解的 DEA 和 DES 实验样品，并对其进行了表征。采用圆形致动器配置的 DEA 可实现高达 15.4% 的电压可控面积应变，并可在 1,000 个致动周期内稳定运行。采用弯曲致动器配置的 DEA 的电压可控弯曲角度高达 17.4°。DES 的线性响应应变高达 200%，测量系数为 0.85，并在 10,000 次应变循环中保持稳定。观察到的 DEA 和 DES 的特性与理论预测非常吻合，凸显了可生物降解的 DEA 和 DES 作为可持续和环境友好型软机器人元件的潜在适用性。
{"title":"Biodegradable Dielectric Elastomer Actuators and Sensors","authors":"Kazuma Takai;Kazuya Murakami;Jun Shintake","doi":"10.1109/LRA.2024.3495580","DOIUrl":"https://doi.org/10.1109/LRA.2024.3495580","url":null,"abstract":"Soft robotics, a field dedicated to the development of robots using flexible and compliant materials, has undergone significant progress in recent years, offering a wide range of potential applications. However, most soft robots are fabricated using synthetic elastomeric materials, contributing to environmental pollution and degradation. A potential solution to this problem involves integrating biodegradability into the designs of soft robots, facilitating their degradation through microbial activity and subsequent integration into the soil. However, to achieve this functionality, biodegradable soft robotic elements must be developed. This paper presents biodegradable dielectric elastomer actuators (DEAs) and sensors (DESs). These devices feature a soft dielectric membrane with compliant electrodes on both sides, enabling them to function as both electrostatic actuators and capacitive sensors. Natural rubber and gelatin-based elastomeric materials are employed for the dielectric membrane and electrodes, respectively. Using these materials and established fabrication processes, experimental biodegradable DEA and DES samples are fabricated and characterized. The DEA with a circular actuator configuration demonstrates a voltage-controllable areal strain of up to 15.4% and presents stable operation over 1,000 actuation cycles. The DEA with a bending actuator configuration exhibits a voltage-controllable bending angle of up to 17.4°. The DES demonstrates a linear response for strains up to 200%, with a gauge factor of 0.85, and maintains stability over 10,000 strain cycles. The observed characteristics of the DEAs and DES align well with theoretical predictions, highlighting the potential applicability of biodegradable DEAs and DESs as promising elements for sustainable and environmentally friendly soft robots.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11730-11737"},"PeriodicalIF":4.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","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：