Pub Date : 2025-01-13DOI: 10.1109/LRA.2025.3528225
Praveen Kumar Ranjan;Abhinav Sinha;Yongcan Cao
In this paper, we address the problem of enclosing an arbitrarily moving target in three dimensions by a single pursuer while ensuring the pursuer's safety by preventing collisions with the target. The proposed guidance strategy steers the pursuer to a safe region of space surrounding and excluding the target, allowing it to maintain a certain distance from the latter while offering greater flexibility in positioning and converging to any orbit within this safe zone. We leverage the concept of the Lyapunov Barrier Function as a powerful tool to constrain the distance between the pursuer and the target within asymmetric bounds, thereby ensuring the pursuer's safety within the predefined region. Further, we demonstrate the effectiveness of the proposed guidance law in managing arbitrarily maneuvering targets and other uncertainties (such as vehicle/autopilot dynamics and external disturbances) by enabling the pursuer to consistently achieve stable global enclosing behaviors by switching between stable enclosing trajectories within the safe region whenever necessary, even in response to aggressive target maneuvers. To attest to the merits of our work, we conduct experimental tests with various plant models, including a high-fidelity quadrotor model within Software-in-the-loop (SITL) simulations, encompassing various challenging target maneuver scenarios and requiring only relative information for successful execution.
{"title":"3D Guidance Law for Flexible Target Enclosing With Inherent Safety","authors":"Praveen Kumar Ranjan;Abhinav Sinha;Yongcan Cao","doi":"10.1109/LRA.2025.3528225","DOIUrl":"https://doi.org/10.1109/LRA.2025.3528225","url":null,"abstract":"In this paper, we address the problem of enclosing an arbitrarily moving target in three dimensions by a single pursuer while ensuring the pursuer's safety by preventing collisions with the target. The proposed guidance strategy steers the pursuer to a safe region of space surrounding and excluding the target, allowing it to maintain a certain distance from the latter while offering greater flexibility in positioning and converging to any orbit within this safe zone. We leverage the concept of the Lyapunov Barrier Function as a powerful tool to constrain the distance between the pursuer and the target within asymmetric bounds, thereby ensuring the pursuer's safety within the predefined region. Further, we demonstrate the effectiveness of the proposed guidance law in managing arbitrarily maneuvering targets and other uncertainties (such as vehicle/autopilot dynamics and external disturbances) by enabling the pursuer to consistently achieve stable global enclosing behaviors by switching between stable enclosing trajectories within the safe region whenever necessary, even in response to aggressive target maneuvers. To attest to the merits of our work, we conduct experimental tests with various plant models, including a high-fidelity quadrotor model within Software-in-the-loop (SITL) simulations, encompassing various challenging target maneuver scenarios and requiring only relative information for successful execution.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 2","pages":"2088-2095"},"PeriodicalIF":4.6,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992991","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}
Object-goal navigation is a highly challenging task where an agent must navigate to a target solely based on visual observations. Current reinforcement learning-based methods for object-goal navigation face two major challenges: first, the agent lacks sufficient perception of environmental context information, resulting in an absence of rich visual representations; second, in complex environments or confined spaces, the agent tends to stop exploring novel states, becoming trapped in a deadlock from which it cannot escape. To address these issues, we propose a novel Multi-View Visual Transformer (MVVT) navigation model, which consists of two components: a multi-view visual observation representation module and an episode state constraint-based policy learning module. In the visual observation representation module, we expand the input image perspective to five views to enable the agent to learn rich spatial context relationships of the environment, which provides content-rich feature information for subsequent policy learning. In the policy learning module, we help the agent escape deadlock by constraining the correlation of highly related states within an episode, which promotes the exploration of novel states and achieves efficient navigation. We validate our method in the AI2-Thor environment, and experimental results show that our approach outperforms current state-of-the-art methods across all metrics, with a particularly notable improvement in success rate by 2.66% and SPL metric by 16.5%.
{"title":"Multi-View Spatial Context and State Constraints for Object-Goal Navigation","authors":"Chong Lu;Meiqin Liu;Zhirong Luan;Yan He;Badong Chen","doi":"10.1109/LRA.2025.3529324","DOIUrl":"https://doi.org/10.1109/LRA.2025.3529324","url":null,"abstract":"Object-goal navigation is a highly challenging task where an agent must navigate to a target solely based on visual observations. Current reinforcement learning-based methods for object-goal navigation face two major challenges: first, the agent lacks sufficient perception of environmental context information, resulting in an absence of rich visual representations; second, in complex environments or confined spaces, the agent tends to stop exploring novel states, becoming trapped in a deadlock from which it cannot escape. To address these issues, we propose a novel Multi-View Visual Transformer (MVVT) navigation model, which consists of two components: a multi-view visual observation representation module and an episode state constraint-based policy learning module. In the visual observation representation module, we expand the input image perspective to five views to enable the agent to learn rich spatial context relationships of the environment, which provides content-rich feature information for subsequent policy learning. In the policy learning module, we help the agent escape deadlock by constraining the correlation of highly related states within an episode, which promotes the exploration of novel states and achieves efficient navigation. We validate our method in the AI2-Thor environment, and experimental results show that our approach outperforms current state-of-the-art methods across all metrics, with a particularly notable improvement in success rate by 2.66% and SPL metric by 16.5%.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 3","pages":"2207-2214"},"PeriodicalIF":4.6,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106593","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 : 2025-01-13DOI: 10.1109/LRA.2025.3529319
Xiao Li;Xieyuanli Chen;Ruibin Guo;Yujie Wu;Zongtan Zhou;Fangwen Yu;Huimin Lu
Vision-based ego-velocity estimation is a fundamental problem in robot state estimation. However, the constraints of frame-based cameras, including motion blur and insufficient frame rates in dynamic settings, readily lead to the failure of conventional velocity estimation techniques. Mammals exhibit a remarkable ability to accurately estimate their ego-velocity during aggressive movement. Hence, integrating this capability into robots shows great promise for addressing these challenges. In this letter, we propose a brain-inspired framework for linear-angular velocity estimation, dubbed NeuroVE. The NeuroVE framework employs an event camera to capture the motion information and implements spiking neural networks (SNNs) to simulate the brain's spatial cells' function for velocity estimation. We formulate the velocity estimation as a time-series forecasting problem. To this end, we design an Astrocyte Leaky Integrate-and-Fire (ALIF) neuron model to encode continuous values. Additionally, we have developed an Astrocyte Spiking Long Short-term Memory (ASLSTM) structure, which significantly improves the time-series forecasting capabilities, enabling an accurate estimate of ego-velocity. Results from both simulation and real-world experiments indicate that NeuroVE has achieved an approximate 60% increase in accuracy compared to other SNN-based approaches.
{"title":"NeuroVE: Brain-Inspired Linear-Angular Velocity Estimation With Spiking Neural Networks","authors":"Xiao Li;Xieyuanli Chen;Ruibin Guo;Yujie Wu;Zongtan Zhou;Fangwen Yu;Huimin Lu","doi":"10.1109/LRA.2025.3529319","DOIUrl":"https://doi.org/10.1109/LRA.2025.3529319","url":null,"abstract":"Vision-based ego-velocity estimation is a fundamental problem in robot state estimation. However, the constraints of frame-based cameras, including motion blur and insufficient frame rates in dynamic settings, readily lead to the failure of conventional velocity estimation techniques. Mammals exhibit a remarkable ability to accurately estimate their ego-velocity during aggressive movement. Hence, integrating this capability into robots shows great promise for addressing these challenges. In this letter, we propose a brain-inspired framework for linear-angular velocity estimation, dubbed NeuroVE. The NeuroVE framework employs an event camera to capture the motion information and implements spiking neural networks (SNNs) to simulate the brain's spatial cells' function for velocity estimation. We formulate the velocity estimation as a time-series forecasting problem. To this end, we design an Astrocyte Leaky Integrate-and-Fire (ALIF) neuron model to encode continuous values. Additionally, we have developed an Astrocyte Spiking Long Short-term Memory (ASLSTM) structure, which significantly improves the time-series forecasting capabilities, enabling an accurate estimate of ego-velocity. Results from both simulation and real-world experiments indicate that NeuroVE has achieved an approximate 60% increase in accuracy compared to other SNN-based approaches.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 3","pages":"2375-2382"},"PeriodicalIF":4.6,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106609","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 : 2025-01-09DOI: 10.1109/LRA.2025.3527762
Jiaqiang Yang;Danyang Qin;Huapeng Tang;Sili Tao;Haoze Bie;Lin Ma
Visual self-localization technology is essential for unmanned aerial vehicles (UAVs) to achieve autonomous navigation and mission execution in environments where global navigation satellite system (GNSS) signals are unavailable. This technology estimates the UAV's geographic location by performing cross-view matching between UAV and satellite images. However, significant viewpoint differences between UAV and satellite images result in poor accuracy for existing cross-view matching methods. To address this, we integrate the DINOv2 model with UAV visual localization tasks and propose a DINOv2-based UAV visual self-localization method. Considering the inherent differences between pre-trained models and cross-view matching tasks, we propose a global-local feature adaptive enhancement method (GLFA). This method leverages Transformer and multi-scale convolutions to capture long-range dependencies and local spatial information in visual images, improving the model's ability to recognize key discriminative landmarks. In addition, we propose a cross-enhancement method based on a spatial pyramid (CESP), which constructs a multi-scale spatial pyramid to cross-enhance features, effectively improving the ability of the features to perceive multi-scale spatial information. Experimental results demonstrate that the proposed method achieves impressive scores of 86.27% in R@1 and 88.87% in SDM@1 on the DenseUAV public benchmark dataset, providing a novel solution for UAV visual self-localization.
{"title":"DINOv2-Based UAV Visual Self-Localization in Low-Altitude Urban Environments","authors":"Jiaqiang Yang;Danyang Qin;Huapeng Tang;Sili Tao;Haoze Bie;Lin Ma","doi":"10.1109/LRA.2025.3527762","DOIUrl":"https://doi.org/10.1109/LRA.2025.3527762","url":null,"abstract":"Visual self-localization technology is essential for unmanned aerial vehicles (UAVs) to achieve autonomous navigation and mission execution in environments where global navigation satellite system (GNSS) signals are unavailable. This technology estimates the UAV's geographic location by performing cross-view matching between UAV and satellite images. However, significant viewpoint differences between UAV and satellite images result in poor accuracy for existing cross-view matching methods. To address this, we integrate the DINOv2 model with UAV visual localization tasks and propose a DINOv2-based UAV visual self-localization method. Considering the inherent differences between pre-trained models and cross-view matching tasks, we propose a global-local feature adaptive enhancement method (GLFA). This method leverages Transformer and multi-scale convolutions to capture long-range dependencies and local spatial information in visual images, improving the model's ability to recognize key discriminative landmarks. In addition, we propose a cross-enhancement method based on a spatial pyramid (CESP), which constructs a multi-scale spatial pyramid to cross-enhance features, effectively improving the ability of the features to perceive multi-scale spatial information. Experimental results demonstrate that the proposed method achieves impressive scores of 86.27% in R@1 and 88.87% in SDM@1 on the DenseUAV public benchmark dataset, providing a novel solution for UAV visual self-localization.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 2","pages":"2080-2087"},"PeriodicalIF":4.6,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992990","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 : 2025-01-09DOI: 10.1109/LRA.2025.3527757
Xiaozhu Lin;Xiaopei Liu;Yang Wang
The pursuit of agile and efficient underwater robots, especially bio-mimetic robotic fish, has been impeded by challenges in creating motion controllers that are able to fully exploit their hydrodynamic capabilities. This letter addresses these challenges by introducing a novel, model-free, end-to-end control framework that leverages Deep Reinforcement Learning (DRL) to enable agile and energy-efficient swimming of robotic fish. Unlike existing methods that rely on predefined trigonometric swimming patterns like Central Pattern Generators (CPG), our approach directly outputs low-level actuator commands without strong constraints, enabling the robotic fish to learn agile swimming behaviors. In addition, by integrating a high-performance Computational Fluid Dynamics (CFD) simulator with innovative sim-to-real strategies, such as normalized density calibration and servo response calibration, the proposed framework significantly mitigates the sim-to-real gap, facilitating direct transfer of control policies to real-world environments without fine-tuning. Comparative experiments demonstrate that our method achieves faster swimming speeds, smaller turn-around radii, and reduced energy consumption compared to the state-of-the-art swimming controllers. Furthermore, the proposed framework shows promise in addressing complex tasks, paving the way for more effective deployment of robotic fish in real aquatic environments.
{"title":"Learning Agile Swimming: An End-to-End Approach Without CPGs","authors":"Xiaozhu Lin;Xiaopei Liu;Yang Wang","doi":"10.1109/LRA.2025.3527757","DOIUrl":"https://doi.org/10.1109/LRA.2025.3527757","url":null,"abstract":"The pursuit of agile and efficient underwater robots, especially bio-mimetic robotic fish, has been impeded by challenges in creating motion controllers that are able to fully exploit their hydrodynamic capabilities. This letter addresses these challenges by introducing a novel, model-free, end-to-end control framework that leverages Deep Reinforcement Learning (DRL) to enable agile and energy-efficient swimming of robotic fish. Unlike existing methods that rely on predefined trigonometric swimming patterns like Central Pattern Generators (CPG), our approach directly outputs low-level actuator commands without strong constraints, enabling the robotic fish to learn agile swimming behaviors. In addition, by integrating a high-performance Computational Fluid Dynamics (CFD) simulator with innovative sim-to-real strategies, such as normalized density calibration and servo response calibration, the proposed framework significantly mitigates the sim-to-real gap, facilitating direct transfer of control policies to real-world environments without fine-tuning. Comparative experiments demonstrate that our method achieves faster swimming speeds, smaller turn-around radii, and reduced energy consumption compared to the state-of-the-art swimming controllers. Furthermore, the proposed framework shows promise in addressing complex tasks, paving the way for more effective deployment of robotic fish in real aquatic environments.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 2","pages":"1992-1999"},"PeriodicalIF":4.6,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992983","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}
Teleoperation offers the possibility of enabling robots to replace humans in operating within hazardous environments. While it provides greater adaptability to unstructured settings than full autonomy, it also imposes significant burdens on human operators, leading to operational errors. To address this challenge, shared control, a key aspect of human-robot collaboration methods, has emerged as a promising alternative. By integrating direct teleoperation with autonomous control, shared control ensures both efficiency and stability. In this letter, we introduce a shared control framework for human-robot collaborative tele-grasping in clutter with five-fingered robotic hands. During teleoperation, the operator's intent to reach the target object is detected in real-time. Upon successful detection, continuous and smooth grasping plans are generated, allowing the robot to seamlessly take over control and achieve natural, collision-free grasping. We validate the proposed framework through fundamental component analysis and experiments on real-world platforms, demonstrating the superior performance of this framework in reducing operator workload and enabling effective grasping in clutter.
{"title":"Human-Robot Collaborative Tele-Grasping in Clutter With Five-Fingered Robotic Hands","authors":"Yayu Huang;Dongxuan Fan;Dashun Yan;Wen Qi;Guoqiang Deng;Zhihao Shao;Yongkang Luo;Daheng Li;Zhenghan Wang;Qian Liu;Peng Wang","doi":"10.1109/LRA.2025.3527278","DOIUrl":"https://doi.org/10.1109/LRA.2025.3527278","url":null,"abstract":"Teleoperation offers the possibility of enabling robots to replace humans in operating within hazardous environments. While it provides greater adaptability to unstructured settings than full autonomy, it also imposes significant burdens on human operators, leading to operational errors. To address this challenge, shared control, a key aspect of human-robot collaboration methods, has emerged as a promising alternative. By integrating direct teleoperation with autonomous control, shared control ensures both efficiency and stability. In this letter, we introduce a shared control framework for human-robot collaborative tele-grasping in clutter with five-fingered robotic hands. During teleoperation, the operator's intent to reach the target object is detected in real-time. Upon successful detection, continuous and smooth grasping plans are generated, allowing the robot to seamlessly take over control and achieve natural, collision-free grasping. We validate the proposed framework through fundamental component analysis and experiments on real-world platforms, demonstrating the superior performance of this framework in reducing operator workload and enabling effective grasping in clutter.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 3","pages":"2215-2222"},"PeriodicalIF":4.6,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106594","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}
Accurate tire modeling is crucial for optimizing autonomous racing vehicles, as State-of-the-Art (SotA) model-based techniques rely on precise knowledge of the vehicle's parameters, yet system identification in dynamic racing conditions is challenging due to varying track and tire conditions. Traditional methods require extensive operational ranges, often impractical in racing scenarios. Machine Learning (ML)-based methods, while improving performance, struggle with generalization and depend on accurate initialization. This paper introduces a novel on-track system identification algorithm, incorporating a Neural Network (NN) for error correction, which is then employed for traditional system identification with virtually generated data. Crucially, the process is iteratively reapplied, with tire parameters updated at each cycle, leading to notable improvements in accuracy in tests on a scaled vehicle. Experiments show that it is possible to learn a tire model without prior knowledge with only 30 seconds of driving data, and 3 seconds of training time. This method demonstrates greater one-step prediction accuracy than the baseline Nonlinear Least Squares (NLS) method under noisy conditions, achieving a 3.3x lower Root Mean Square Error (RMSE), and yields tire models with comparable accuracy to traditional steady-state system identification. Furthermore, unlike steady-state methods requiring large spaces and specific experimental setups, the proposed approach identifies tire parameters directly on a race track in dynamic racing environments.
{"title":"Learning-Based On-Track System Identification for Scaled Autonomous Racing in Under a Minute","authors":"Onur Dikici;Edoardo Ghignone;Cheng Hu;Nicolas Baumann;Lei Xie;Andrea Carron;Michele Magno;Matteo Corno","doi":"10.1109/LRA.2025.3527336","DOIUrl":"https://doi.org/10.1109/LRA.2025.3527336","url":null,"abstract":"Accurate tire modeling is crucial for optimizing autonomous racing vehicles, as State-of-the-Art (SotA) model-based techniques rely on precise knowledge of the vehicle's parameters, yet system identification in dynamic racing conditions is challenging due to varying track and tire conditions. Traditional methods require extensive operational ranges, often impractical in racing scenarios. Machine Learning (ML)-based methods, while improving performance, struggle with generalization and depend on accurate initialization. This paper introduces a novel on-track system identification algorithm, incorporating a Neural Network (NN) for error correction, which is then employed for traditional system identification with virtually generated data. Crucially, the process is iteratively reapplied, with tire parameters updated at each cycle, leading to notable improvements in accuracy in tests on a scaled vehicle. Experiments show that it is possible to learn a tire model without prior knowledge with only 30 seconds of driving data, and 3 seconds of training time. This method demonstrates greater one-step prediction accuracy than the baseline Nonlinear Least Squares (NLS) method under noisy conditions, achieving a 3.3x lower Root Mean Square Error (RMSE), and yields tire models with comparable accuracy to traditional steady-state system identification. Furthermore, unlike steady-state methods requiring large spaces and specific experimental setups, the proposed approach identifies tire parameters directly on a race track in dynamic racing environments.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 2","pages":"1984-1991"},"PeriodicalIF":4.6,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992982","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 : 2025-01-08DOI: 10.1109/LRA.2025.3527338
Alper Ahmetoglu;Erhan Oztop;Emre Ugur
Discovering the symbols and rules that can be used in long-horizon planning from a robot's unsupervised exploration of its environment and continuous sensorimotor experience is a challenging task. The previous studies proposed learning symbols from single or paired object interactions and planning with these symbols. In this work, we propose a system that learns rules with discovered object and relational symbols that encode an arbitrary number of objects and the relations between them, converts those rules to Planning Domain Description Language (PDDL), and generates plans that involve affordances of the arbitrary number of objects to achieve tasks. We validated our system with box-shaped objects in different sizes and showed that the system can develop a symbolic knowledge of pick-up, carry, and place operations, taking into account object compounds in different configurations, such as boxes would be carried together with a larger box that they are placed on. We also compared our method with other symbol learning methods and showed that planning with the operators defined over relational symbols gives better planning performance compared to the baselines.
{"title":"Symbolic Manipulation Planning With Discovered Object and Relational Predicates","authors":"Alper Ahmetoglu;Erhan Oztop;Emre Ugur","doi":"10.1109/LRA.2025.3527338","DOIUrl":"https://doi.org/10.1109/LRA.2025.3527338","url":null,"abstract":"Discovering the symbols and rules that can be used in long-horizon planning from a robot's unsupervised exploration of its environment and continuous sensorimotor experience is a challenging task. The previous studies proposed learning symbols from single or paired object interactions and planning with these symbols. In this work, we propose a system that learns rules with discovered object and relational symbols that encode an arbitrary number of objects and the relations between them, converts those rules to Planning Domain Description Language (PDDL), and generates plans that involve affordances of the arbitrary number of objects to achieve tasks. We validated our system with box-shaped objects in different sizes and showed that the system can develop a symbolic knowledge of pick-up, carry, and place operations, taking into account object compounds in different configurations, such as boxes would be carried together with a larger box that they are placed on. We also compared our method with other symbol learning methods and showed that planning with the operators defined over relational symbols gives better planning performance compared to the baselines.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 2","pages":"1968-1975"},"PeriodicalIF":4.6,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992980","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 : 2025-01-08DOI: 10.1109/LRA.2025.3527282
Seunghoon Yoo;Hyunjun Park;Youngsu Cha
This letter presents a novel cable-driven hybrid origami-inspired actuator with load-bearing capability. In contrast to conventional origami, the hybrid origami layer of the actuator is characterized by resilient hinges and rigid facets. The layers are bonded and assembled with the motors that apply tension via wires to generate a motion. The actuator exhibits high blocking force performance while preserving the large deformability of the conventional origami. To analyze the structure, a mathematical model is built using origami kinematics and elastic analysis. A hybrid origami tower with multiple layers is also suggested to show feasibility as a robot manipulator.
{"title":"Design and Analysis of a Hybrid Actuator With Resilient Origami-Inspired Hinges","authors":"Seunghoon Yoo;Hyunjun Park;Youngsu Cha","doi":"10.1109/LRA.2025.3527282","DOIUrl":"https://doi.org/10.1109/LRA.2025.3527282","url":null,"abstract":"This letter presents a novel cable-driven hybrid origami-inspired actuator with load-bearing capability. In contrast to conventional origami, the hybrid origami layer of the actuator is characterized by resilient hinges and rigid facets. The layers are bonded and assembled with the motors that apply tension via wires to generate a motion. The actuator exhibits high blocking force performance while preserving the large deformability of the conventional origami. To analyze the structure, a mathematical model is built using origami kinematics and elastic analysis. A hybrid origami tower with multiple layers is also suggested to show feasibility as a robot manipulator.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 3","pages":"2128-2135"},"PeriodicalIF":4.6,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993207","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 : 2025-01-08DOI: 10.1109/LRA.2025.3527344
Yang Xu;Qiucan Huang;Shaojie Shen;Huan Yin
Radar SLAM is robust in challenging conditions, such as fog, dust, and smoke, but suffers from the sparsity and noisiness of radar sensing, including speckle noise and multipath effects. This study provides a performance-enhanced radar SLAM system by incorporating point uncertainty. The basic system is a radar-inertial odometry system that leverages velocity-aided radar points and high-frequency inertial measurements. We first propose to model the uncertainty of radar points in polar coordinates by considering the nature of radar sensing. Then, the proposed uncertainty model is integrated into the data association module and incorporated for back-end state estimation. Real-world experiments on both public and self-collected datasets validate the effectiveness of the proposed models and approaches. The findings highlight the potential of incorporating point uncertainty to improve the radar SLAM system.
{"title":"Incorporating Point Uncertainty in Radar SLAM","authors":"Yang Xu;Qiucan Huang;Shaojie Shen;Huan Yin","doi":"10.1109/LRA.2025.3527344","DOIUrl":"https://doi.org/10.1109/LRA.2025.3527344","url":null,"abstract":"Radar SLAM is robust in challenging conditions, such as fog, dust, and smoke, but suffers from the sparsity and noisiness of radar sensing, including speckle noise and multipath effects. This study provides a performance-enhanced radar SLAM system by incorporating point uncertainty. The basic system is a radar-inertial odometry system that leverages velocity-aided radar points and high-frequency inertial measurements. We first propose to model the uncertainty of radar points in polar coordinates by considering the nature of radar sensing. Then, the proposed uncertainty model is integrated into the data association module and incorporated for back-end state estimation. Real-world experiments on both public and self-collected datasets validate the effectiveness of the proposed models and approaches. The findings highlight the potential of incorporating point uncertainty to improve the radar SLAM system.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 3","pages":"2168-2175"},"PeriodicalIF":4.6,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993205","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：