Pub Date : 2024-10-24DOI: 10.1109/LRA.2024.3486212
Pedro Arias-Perez;Alvika Gautam;Miguel Fernandez-Cortizas;David Perez-Saura;Srikanth Saripalli;Pascual Campoy
Recent advances have improved autonomous navigation and mapping under payload constraints, but current multi-robot inspection algorithms are unsuitable for nano-drones, due to their need for heavy sensors and high computational resources. To address these challenges, we introduce ExploreBug , a novel hybrid frontier range-bug algorithm designed to handle limited sensing capabilities for a swarm of nano-drones. This system includes three primary components: a mapping subsystem, an exploration subsystem, and a navigation subsystem. Additionally, an intra-swarm collision avoidance system is integrated to prevent collisions between drones. We validate the efficacy of our approach through extensive simulations and real-world exploration experiments, involving up to seven drones in simulations and three in real-world settings, across various obstacle configurations and with a maximum navigation speed of 0.75 m/s. Our tests prove that the algorithm efficiently completes exploration tasks, even with minimal sensing, across different swarm sizes and obstacle densities. Furthermore, our frontier allocation heuristic ensures an equal distribution of explored areas and paths traveled by each drone in the swarm. We publicly release the source code of the proposed system to foster further developments in mapping and exploration using autonomous nano drones.
{"title":"Exploring Unstructured Environments Using Minimal Sensing on Cooperative Nano-Drones","authors":"Pedro Arias-Perez;Alvika Gautam;Miguel Fernandez-Cortizas;David Perez-Saura;Srikanth Saripalli;Pascual Campoy","doi":"10.1109/LRA.2024.3486212","DOIUrl":"https://doi.org/10.1109/LRA.2024.3486212","url":null,"abstract":"Recent advances have improved autonomous navigation and mapping under payload constraints, but current multi-robot inspection algorithms are unsuitable for nano-drones, due to their need for heavy sensors and high computational resources. To address these challenges, we introduce \u0000<italic>ExploreBug</i>\u0000, a novel hybrid frontier range-bug algorithm designed to handle limited sensing capabilities for a swarm of nano-drones. This system includes three primary components: a mapping subsystem, an exploration subsystem, and a navigation subsystem. Additionally, an intra-swarm collision avoidance system is integrated to prevent collisions between drones. We validate the efficacy of our approach through extensive simulations and real-world exploration experiments, involving up to seven drones in simulations and three in real-world settings, across various obstacle configurations and with a maximum navigation speed of 0.75 m/s. Our tests prove that the algorithm efficiently completes exploration tasks, even with minimal sensing, across different swarm sizes and obstacle densities. Furthermore, our frontier allocation heuristic ensures an equal distribution of explored areas and paths traveled by each drone in the swarm. We publicly release the source code of the proposed system to foster further developments in mapping and exploration using autonomous nano drones.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11202-11209"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10734219","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598642","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 : 2024-10-24DOI: 10.1109/LRA.2024.3486233
Bo Zhou;Jiajie Wu;Yan Pan;Chuanzhao Lu
The motion distortion in LiDAR scans caused by the robot's aggressive motion and environmental terrain features significantly impacts the positioning and mapping performance of 3D LiDAR odometry. Existing distortion correction solutions struggle to balance computational complexity and accuracy. In this letter, we propose an A daptive T emporal I nterval-based C ontinuous- T ime L iDAR-only O dometry (ATI-CTLO), which is based on straightforward and efficient linear interpolation. Our method can flexibly adjust the temporal intervals between control nodes according to the motion dynamics and environmental degeneracy. This adaptability enhances performance across various motion states and improves the algorithms robustness in degenerate, particularly feature-sparse, environments. We validated our method's effectiveness on multiple datasets across different platforms, achieving comparable accuracy to state-of-the-art LiDAR-only odometry methods. Notably, in situations involving aggressive motion and sparse features, our method outperforms existing LiDAR-only methods.
{"title":"ATI-CTLO: Adaptive Temporal Interval-Based Continuous-Time LiDAR-Only Odometry","authors":"Bo Zhou;Jiajie Wu;Yan Pan;Chuanzhao Lu","doi":"10.1109/LRA.2024.3486233","DOIUrl":"https://doi.org/10.1109/LRA.2024.3486233","url":null,"abstract":"The motion distortion in LiDAR scans caused by the robot's aggressive motion and environmental terrain features significantly impacts the positioning and mapping performance of 3D LiDAR odometry. Existing distortion correction solutions struggle to balance computational complexity and accuracy. In this letter, we propose an \u0000<bold>A</b>\u0000daptive \u0000<bold>T</b>\u0000emporal \u0000<bold>I</b>\u0000nterval-based \u0000<bold>C</b>\u0000ontinuous-\u0000<bold>T</b>\u0000ime \u0000<bold>L</b>\u0000iDAR-only \u0000<bold>O</b>\u0000dometry (ATI-CTLO), which is based on straightforward and efficient linear interpolation. Our method can flexibly adjust the temporal intervals between control nodes according to the motion dynamics and environmental degeneracy. This adaptability enhances performance across various motion states and improves the algorithms robustness in degenerate, particularly feature-sparse, environments. We validated our method's effectiveness on multiple datasets across different platforms, achieving comparable accuracy to state-of-the-art LiDAR-only odometry methods. Notably, in situations involving aggressive motion and sparse features, our method outperforms existing LiDAR-only methods.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11162-11169"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598621","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 : 2024-10-24DOI: 10.1109/LRA.2024.3486178
Hojin Lee;Youngim Nam;Sanghun Lee;Cheolhyeon Kwon
Autonomous racing confronts significant challenges in safely overtaking Opponent Vehicles (OVs) that exhibit uncertain trajectories, stemming from unknown driving policies. To address these challenges, this study proposes heterogeneous kernel metrics for Deep Kernel Learning (DKL), designed to robustly capture the diverse driving policies of OVs, and carry out precise trajectory predictions along with the associated uncertainties. A key virtue of the proposed kernel metrics lies in their ability to align similar driving policies and disjoin dissimilar ones in an unsupervised manner, given the observed interactions between the Ego Vehicle (EV) and OVs. The efficacy of the proposed method is substantiated through experimental studies on a 1/10th scale racecar platform, demonstrating improved prediction accuracy and thereby safely overtaking against OVs. Furthermore, our method is computationally efficient for onboard computing units, affirming its viability in fast-paced racing environments.
自动赛车在安全超越对手车辆（OV）时面临着巨大挑战，因为未知的驾驶策略会导致对手车辆的轨迹不确定。为了应对这些挑战，本研究提出了用于深度核学习（DKL）的异构核指标，旨在稳健地捕捉 OV 的各种驾驶策略，并对相关的不确定性进行精确的轨迹预测。所提出的内核指标的一个主要优点在于，考虑到所观察到的自我车辆（EV）与 OV 之间的相互作用，它们能够以无监督的方式调整相似的驾驶策略并分离不相似的策略。通过在 1/10 比例的赛车平台上进行实验研究，证明了所提方法的有效性，证明了预测准确性的提高，从而实现了对 OV 的安全超车。此外，我们的方法对于车载计算单元来说计算效率高，这肯定了它在快节奏赛车环境中的可行性。
{"title":"Kernel-Based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous Racing","authors":"Hojin Lee;Youngim Nam;Sanghun Lee;Cheolhyeon Kwon","doi":"10.1109/LRA.2024.3486178","DOIUrl":"https://doi.org/10.1109/LRA.2024.3486178","url":null,"abstract":"Autonomous racing confronts significant challenges in safely overtaking Opponent Vehicles (OVs) that exhibit uncertain trajectories, stemming from unknown driving policies. To address these challenges, this study proposes heterogeneous kernel metrics for Deep Kernel Learning (DKL), designed to robustly capture the diverse driving policies of OVs, and carry out precise trajectory predictions along with the associated uncertainties. A key virtue of the proposed kernel metrics lies in their ability to align similar driving policies and disjoin dissimilar ones in an unsupervised manner, given the observed interactions between the Ego Vehicle (EV) and OVs. The efficacy of the proposed method is substantiated through experimental studies on a 1/10th scale racecar platform, demonstrating improved prediction accuracy and thereby safely overtaking against OVs. Furthermore, our method is computationally efficient for onboard computing units, affirming its viability in fast-paced racing environments.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11050-11057"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565503","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 : 2024-10-24DOI: 10.1109/LRA.2024.3486231
Shiyu Feng;Ahmad Abuaish;Patricio A. Vela
This paper extends the gap-based navigation technique Potential Gap with safety guarantees at the local planning level for a kinematic planar nonholonomic robot model, leading to Safer Gap . It relies on a subset of navigable free space from the robot to a gap, denoted the keyhole region. The region is defined by the union of the largest collision-free disc centered on the robot and a collision-free trapezoidal region directed through the gap. Safer Gap first generates Bézier-based collision-free paths within the keyhole regions. The keyhole region of the top scoring path is encoded by a shallow neural network-based zeroing barrier function (ZBF) synthesized in real-time. Nonlinear Model Predictive Control (NMPC) with Keyhole ZBF constraints and output tracking of the Bézier path, synthesizes a safe kinematically feasible trajectory. The Potential Gap projection operator serves as a last action to enforce safety if the NMPC optimization fails to converge to a solution within the prescribed time. Simulation and experimental validation of Safer Gap confirm its collision-free navigation properties.
本文对基于间隙的导航技术 "潜在间隙"（Potential Gap）进行了扩展，为运动学平面非全局机器人模型提供了局部规划层面的安全保证，从而实现了 "更安全的间隙"（Safer Gap）。它依赖于从机器人到间隙的可导航自由空间子集，表示为钥匙孔区域。该区域由以机器人为中心的最大无碰撞圆盘和穿过间隙的无碰撞梯形区域的结合体定义。Safer Gap 首先在锁孔区域内生成基于贝塞尔的无碰撞路径。得分最高路径的锁孔区域由实时合成的基于浅层神经网络的归零障碍函数（ZBF）编码。非线性模型预测控制（NMPC）利用锁孔 ZBF 约束和贝塞尔路径的输出跟踪，合成出安全的运动学可行轨迹。如果 NMPC 优化未能在规定时间内收敛到一个解决方案，潜在间隙投影算子将作为最后的行动，以确保安全。Safer Gap 的仿真和实验验证证实了其无碰撞导航特性。
{"title":"Safer Gap: Safe Navigation of Planar Nonholonomic Robots With a Gap-Based Local Planner","authors":"Shiyu Feng;Ahmad Abuaish;Patricio A. Vela","doi":"10.1109/LRA.2024.3486231","DOIUrl":"https://doi.org/10.1109/LRA.2024.3486231","url":null,"abstract":"This paper extends the gap-based navigation technique \u0000<italic>Potential Gap</i>\u0000 with safety guarantees at the local planning level for a kinematic planar nonholonomic robot model, leading to \u0000<italic>Safer Gap</i>\u0000. It relies on a subset of navigable free space from the robot to a gap, denoted the keyhole region. The region is defined by the union of the largest collision-free disc centered on the robot and a collision-free trapezoidal region directed through the gap. \u0000<italic>Safer Gap</i>\u0000 first generates Bézier-based collision-free paths within the keyhole regions. The keyhole region of the top scoring path is encoded by a shallow neural network-based zeroing barrier function (ZBF) synthesized in real-time. Nonlinear Model Predictive Control (NMPC) with \u0000<italic>Keyhole ZBF</i>\u0000 constraints and output tracking of the Bézier path, synthesizes a safe kinematically feasible trajectory. The \u0000<italic>Potential Gap</i>\u0000 projection operator serves as a last action to enforce safety if the NMPC optimization fails to converge to a solution within the prescribed time. Simulation and experimental validation of \u0000<italic>Safer Gap</i>\u0000 confirm its collision-free navigation properties.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11034-11041"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565543","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 : 2024-10-24DOI: 10.1109/LRA.2024.3486235
Yulin Li;Chunxin Zheng;Kai Chen;Yusen Xie;Xindong Tang;Michael Yu Wang;Jun Ma
In this work, we propose a trajectory optimization approach for robot navigation in cluttered 3D environments. We represent the robot's geometry as a semialgebraic set defined by polynomial inequalities such that robots with general shapes can be suitably characterized. We exploit the collision-free space directly to construct a graph of free regions, search for the reference path, and allocate each waypoint on the trajectory to a specific region. Then, we incorporate a uniform scaling factor for each free region and formulate a Sums-of-Squares (SOS) optimization problem whose optimal solutions reveal the containment relationship between robots and the free space. The SOS optimization problem is further reformulated to a semidefinite program (SDP), and the collision-free constraints are shown to be equivalent to limiting the scaling factor along the entire trajectory. Next, to solve the trajectory optimization problem with the proposed safety constraints, we derive a guiding direction for updating the robot configuration to decrease the minimum scaling factor by calculating the gradient of the Lagrangian at the primal-dual optimum of the SDP. As a result, this seamlessly facilitates the use of gradient-based methods in efficient solving of the trajectory optimization problem. Through a series of simulations and real-world experiments, the proposed trajectory optimization approach is validated in various challenging scenarios, and the results demonstrate its effectiveness in generating collision-free trajectories in dense and intricate environments.
{"title":"Collision-Free Trajectory Optimization in Cluttered Environments Using Sums-of-Squares Programming","authors":"Yulin Li;Chunxin Zheng;Kai Chen;Yusen Xie;Xindong Tang;Michael Yu Wang;Jun Ma","doi":"10.1109/LRA.2024.3486235","DOIUrl":"https://doi.org/10.1109/LRA.2024.3486235","url":null,"abstract":"In this work, we propose a trajectory optimization approach for robot navigation in cluttered 3D environments. We represent the robot's geometry as a semialgebraic set defined by polynomial inequalities such that robots with general shapes can be suitably characterized. We exploit the collision-free space directly to construct a graph of free regions, search for the reference path, and allocate each waypoint on the trajectory to a specific region. Then, we incorporate a uniform scaling factor for each free region and formulate a Sums-of-Squares (SOS) optimization problem whose optimal solutions reveal the containment relationship between robots and the free space. The SOS optimization problem is further reformulated to a semidefinite program (SDP), and the collision-free constraints are shown to be equivalent to limiting the scaling factor along the entire trajectory. Next, to solve the trajectory optimization problem with the proposed safety constraints, we derive a guiding direction for updating the robot configuration to decrease the minimum scaling factor by calculating the gradient of the Lagrangian at the primal-dual optimum of the SDP. As a result, this seamlessly facilitates the use of gradient-based methods in efficient solving of the trajectory optimization problem. Through a series of simulations and real-world experiments, the proposed trajectory optimization approach is validated in various challenging scenarios, and the results demonstrate its effectiveness in generating collision-free trajectories in dense and intricate environments.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11026-11033"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565553","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 : 2024-10-24DOI: 10.1109/LRA.2024.3486208
R. G. Goswami;H. Sinha;P. V. Amith;J. Hari;P. Krishnamurthy;J. Rizzo;F. Khorrami
Navigation of an agent, such as a person with blindness or low vision, in an unfamiliar environment poses substantial difficulties, even in scenarios where prior maps, like floor plans, are available. It becomes essential first to determine the agent's pose in the environment. The task's complexity increases when the agent also needs directions for exploring the environment to reduce uncertainty in the agent's position. This problem of active global localization typically involves finding a transformation to match the agent's sensor-generated map to the floor plan while providing a series of point-to-point directions for effective exploration. Current methods fall into two categories: learning-based, requiring extensive training for each environment, or non-learning-based, which generally depend on prior knowledge of the agent's initial position, or the use of floor plan maps created with the same sensor modality as the agent. Addressing these limitations, we introduce a novel system for real-time, active global localization and navigation for persons with blindness and low vision. By generating semantically informed real-time goals, our approach enables local exploration and the creation of a 2D semantic point cloud for effective global localization. Moreover, it dynamically corrects for odometry drift using the architectural floor plan, independent of the agent's global position and introduces a new method for real-time loop closure on reversal. Our approach's effectiveness is validated through multiple real-world indoor experiments, also highlighting its adaptability and ease of extension to any mobile robot.
{"title":"Floor Plan Based Active Global Localization and Navigation Aid for Persons With Blindness and Low Vision","authors":"R. G. Goswami;H. Sinha;P. V. Amith;J. Hari;P. Krishnamurthy;J. Rizzo;F. Khorrami","doi":"10.1109/LRA.2024.3486208","DOIUrl":"https://doi.org/10.1109/LRA.2024.3486208","url":null,"abstract":"Navigation of an agent, such as a person with blindness or low vision, in an unfamiliar environment poses substantial difficulties, even in scenarios where prior maps, like floor plans, are available. It becomes essential first to determine the agent's pose in the environment. The task's complexity increases when the agent also needs directions for exploring the environment to reduce uncertainty in the agent's position. This problem of \u0000<italic>active global localization</i>\u0000 typically involves finding a transformation to match the agent's sensor-generated map to the floor plan while providing a series of point-to-point directions for effective exploration. Current methods fall into two categories: learning-based, requiring extensive training for each environment, or non-learning-based, which generally depend on prior knowledge of the agent's initial position, or the use of floor plan maps created with the same sensor modality as the agent. Addressing these limitations, we introduce a novel system for real-time, active global localization and navigation for persons with blindness and low vision. By generating semantically informed real-time goals, our approach enables local exploration and the creation of a 2D semantic point cloud for effective global localization. Moreover, it dynamically corrects for odometry drift using the architectural floor plan, independent of the agent's global position and introduces a new method for real-time loop closure on reversal. Our approach's effectiveness is validated through multiple real-world indoor experiments, also highlighting its adaptability and ease of extension to any mobile robot.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11058-11065"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565558","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 : 2024-10-24DOI: 10.1109/LRA.2024.3486236
Xiaofeng Guo;Guanqi He;Jiahe Xu;Mohammadreza Mousaei;Junyi Geng;Sebastian Scherer;Guanya Shi
Aerial manipulation has gained interest in completing high-altitude tasks that are challenging for human workers, such as contact inspection and defect detection, etc. Previous research has focused on maintaining static contact points or forces. This letter addresses a more general and dynamic task: simultaneously tracking time-varying contact force in the surface normal direction and motion trajectories on tangential surfaces. We propose a pipeline that includes a contact-aware trajectory planner to generate dynamically feasible trajectories, and a hybrid motion-force controller to track such trajectories. We demonstrate the approach in an aerial calligraphy task using a novel sponge pen design as the end-effector, whose stroke width is positively related to the contact force. Additionally, we develop a touchscreen interface for flexible user input. Experiments show our method can effectively draw diverse letters, achieving an IoU of 0.59 and an end-effector position (force) tracking RMSE of 2.9 cm (0.7N).
{"title":"Flying Calligrapher: Contact-Aware Motion and Force Planning and Control for Aerial Manipulation","authors":"Xiaofeng Guo;Guanqi He;Jiahe Xu;Mohammadreza Mousaei;Junyi Geng;Sebastian Scherer;Guanya Shi","doi":"10.1109/LRA.2024.3486236","DOIUrl":"https://doi.org/10.1109/LRA.2024.3486236","url":null,"abstract":"Aerial manipulation has gained interest in completing high-altitude tasks that are challenging for human workers, such as contact inspection and defect detection, etc. Previous research has focused on maintaining static contact points or forces. This letter addresses a more general and dynamic task: simultaneously tracking time-varying contact force in the surface normal direction and motion trajectories on tangential surfaces. We propose a pipeline that includes a contact-aware trajectory planner to generate dynamically feasible trajectories, and a hybrid motion-force controller to track such trajectories. We demonstrate the approach in an aerial calligraphy task using a novel sponge pen design as the end-effector, whose stroke width is positively related to the contact force. Additionally, we develop a touchscreen interface for flexible user input. Experiments show our method can effectively draw diverse letters, achieving an IoU of 0.59 and an end-effector position (force) tracking RMSE of 2.9 cm (0.7N).","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11194-11201"},"PeriodicalIF":4.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598676","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 : 2024-10-21DOI: 10.1109/LRA.2024.3484160
Xiaojie Diao;Juncai Long;Jituo Li;Chengdi Zhou;Huixu Dong;Guodong Lu
Deformable organisms in nature inspire the design of shape-shifting robots, including soft robots, bionic robots and physical human-robot interfaces. However, to achieve multi-objective shape imitation and multi-form transformation, shape-shifting robots often require complex actuation systems, control strategies, and inverse design algorithms. In this letter, we propose a robotic morphing interface with reprogrammable stiffness (RoMI-RS) based on machine learning. RoMI-RS uses a circular elastic bilayer as the base, which can produce isotropic deformation under pneumatic actuation. By repeatedly attaching and detaching high-stiffness limiting layers to the surface of the base, the stiffness distribution can be reprogrammed, guiding anisotropic deformation. Thus, without changing the base material or actuation mechanism, RoMI-RS can precisely mimic various static shapes and dynamic movements. To address the nonlinear coupling of soft materials and pneumatic actuation, we employed a data-driven approach to inversely design limiting layer arrangements (i.e., the stiffness distribution of RoMI-RS) in the form of images. Hence, our proposed pneumatic RoMI-RS not only responds quickly and deforms reversibly but also allows users to intuitively and rapidly reconfigure target shapes. We also demonstrate the applications of RoMI-RS in shape-shifting robotics, particularly in soft grippers and physical human-robot interfaces, verifying its deformation flexibility and adaptability.
{"title":"Design and Shape Control of Robotic Morphing Interface With Reprogrammable Stiffness Based on Machine Learning","authors":"Xiaojie Diao;Juncai Long;Jituo Li;Chengdi Zhou;Huixu Dong;Guodong Lu","doi":"10.1109/LRA.2024.3484160","DOIUrl":"https://doi.org/10.1109/LRA.2024.3484160","url":null,"abstract":"Deformable organisms in nature inspire the design of shape-shifting robots, including soft robots, bionic robots and physical human-robot interfaces. However, to achieve multi-objective shape imitation and multi-form transformation, shape-shifting robots often require complex actuation systems, control strategies, and inverse design algorithms. In this letter, we propose a robotic morphing interface with reprogrammable stiffness (RoMI-RS) based on machine learning. RoMI-RS uses a circular elastic bilayer as the base, which can produce isotropic deformation under pneumatic actuation. By repeatedly attaching and detaching high-stiffness limiting layers to the surface of the base, the stiffness distribution can be reprogrammed, guiding anisotropic deformation. Thus, without changing the base material or actuation mechanism, RoMI-RS can precisely mimic various static shapes and dynamic movements. To address the nonlinear coupling of soft materials and pneumatic actuation, we employed a data-driven approach to inversely design limiting layer arrangements (i.e., the stiffness distribution of RoMI-RS) in the form of images. Hence, our proposed pneumatic RoMI-RS not only responds quickly and deforms reversibly but also allows users to intuitively and rapidly reconfigure target shapes. We also demonstrate the applications of RoMI-RS in shape-shifting robotics, particularly in soft grippers and physical human-robot interfaces, verifying its deformation flexibility and adaptability.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10930-10937"},"PeriodicalIF":4.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565560","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 : 2024-10-21DOI: 10.1109/LRA.2024.3484133
Yian Qian;Lijin Fang;Jiqian Xu;Tangzhong Song;Guanghui Liu
We propose a robot dynamic model to improve the accuracy of the identification, by introducing a friction model that takes into account the joint loads. Firstly, we analyze torque transfer in robot joints, assigning a physical meaning to motor inertia parameters. Then, we enhance the traditional friction model in identification by accounting for joint loads, presenting a new friction model with loads. Next, we employ a one-step method to directly identify both basic dynamic parameters and physical dynamic parameters of the robot. Experimental validation is conducted using a Rokea XMate3pro 7-DOF robot. Results demonstrate that our proposed dynamic model achieves higher accuracy in dynamic identification. It effectively describes the jitter phenomenon caused by motor torque when joints change the direction of motion. Furthermore, in identifying parameters for physical feasibility, our model outperforms traditional approaches by better fitting the dynamic of end joints.
{"title":"One-Step Identification of Robot Physical Dynamic Parameters Considering the Velocity-Load Friction Model","authors":"Yian Qian;Lijin Fang;Jiqian Xu;Tangzhong Song;Guanghui Liu","doi":"10.1109/LRA.2024.3484133","DOIUrl":"https://doi.org/10.1109/LRA.2024.3484133","url":null,"abstract":"We propose a robot dynamic model to improve the accuracy of the identification, by introducing a friction model that takes into account the joint loads. Firstly, we analyze torque transfer in robot joints, assigning a physical meaning to motor inertia parameters. Then, we enhance the traditional friction model in identification by accounting for joint loads, presenting a new friction model with loads. Next, we employ a one-step method to directly identify both basic dynamic parameters and physical dynamic parameters of the robot. Experimental validation is conducted using a Rokea XMate3pro 7-DOF robot. Results demonstrate that our proposed dynamic model achieves higher accuracy in dynamic identification. It effectively describes the jitter phenomenon caused by motor torque when joints change the direction of motion. Furthermore, in identifying parameters for physical feasibility, our model outperforms traditional approaches by better fitting the dynamic of end joints.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10890-10897"},"PeriodicalIF":4.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517904","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 : 2024-10-21DOI: 10.1109/LRA.2024.3484182
Yongjian Zhu;Hao Cheng;Feitian Zhang
Miniature robotic blimps, as one type of lighter-than-air aerial vehicles, have attracted increasing attention in the science and engineering community for their enhanced safety, extended endurance, and quieter operation compared to quadrotors. Accurately modeling the dynamics of these robotic blimps poses a significant challenge due to the complex aerodynamics stemming from their large lifting bodies. Traditional first-principle models have difficulty obtaining accurate aerodynamic parameters and often overlook high-order nonlinearities, thus coming to their limit in modeling the motion dynamics of miniature robotic blimps. To tackle this challenge, this letter proposes the Auto-tuning Blimp-oriented Neural Ordinary Differential Equation method (ABNODE), a data-driven approach that integrates first-principle and neural network modeling. Spiraling motion experiments of robotic blimps are conducted, comparing the ABNODE with first-principle and other data-driven benchmark models, the results of which demonstrate the effectiveness of the proposed method.
{"title":"Data-Driven Dynamics Modeling of Miniature Robotic Blimps Using Neural ODEs With Parameter Auto-Tuning","authors":"Yongjian Zhu;Hao Cheng;Feitian Zhang","doi":"10.1109/LRA.2024.3484182","DOIUrl":"https://doi.org/10.1109/LRA.2024.3484182","url":null,"abstract":"Miniature robotic blimps, as one type of lighter-than-air aerial vehicles, have attracted increasing attention in the science and engineering community for their enhanced safety, extended endurance, and quieter operation compared to quadrotors. Accurately modeling the dynamics of these robotic blimps poses a significant challenge due to the complex aerodynamics stemming from their large lifting bodies. Traditional first-principle models have difficulty obtaining accurate aerodynamic parameters and often overlook high-order nonlinearities, thus coming to their limit in modeling the motion dynamics of miniature robotic blimps. To tackle this challenge, this letter proposes the Auto-tuning Blimp-oriented Neural Ordinary Differential Equation method (ABNODE), a data-driven approach that integrates first-principle and neural network modeling. Spiraling motion experiments of robotic blimps are conducted, comparing the ABNODE with first-principle and other data-driven benchmark models, the results of which demonstrate the effectiveness of the proposed method.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10986-10993"},"PeriodicalIF":4.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565511","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：