Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9812394
S. Sharan, Adithya K. Krishna, A. S. Rao, V. Gopi
Real-time video denoising finds applications in several fields like mobile robotics, satellite television, and surveillance systems. Traditional denoising approaches are more common in such systems than their deep learning-based counterparts despite their inferior performance. The large size and heavy computational requirements of neural network-based denoising models pose a serious impediment to their deployment in real-time applications. In this paper, we propose RepAr-Net, a simple yet efficient architecture for fast video de noising. We propose to use temporally separable encoders to generate feature maps called arsenals that can be cached for reuse. We also incorporate re-parameterizable blocks that improve the representative power of the network without affecting the run-time. We benchmark our model on the Set-8 and 2017 DAVIS-Test datasets. Our model achieves state-of-the-art results with up to 29.62% improvement in PSNR and a 50% decrease in run times over existing methods. Our codes are open-sourced at: github.com/spider-tronix/RepAr-Net.
{"title":"RepAr-Net: Re-Parameterized Encoders and Attentive Feature Arsenals for Fast Video Denoising","authors":"S. Sharan, Adithya K. Krishna, A. S. Rao, V. Gopi","doi":"10.1109/icra46639.2022.9812394","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9812394","url":null,"abstract":"Real-time video denoising finds applications in several fields like mobile robotics, satellite television, and surveillance systems. Traditional denoising approaches are more common in such systems than their deep learning-based counterparts despite their inferior performance. The large size and heavy computational requirements of neural network-based denoising models pose a serious impediment to their deployment in real-time applications. In this paper, we propose RepAr-Net, a simple yet efficient architecture for fast video de noising. We propose to use temporally separable encoders to generate feature maps called arsenals that can be cached for reuse. We also incorporate re-parameterizable blocks that improve the representative power of the network without affecting the run-time. We benchmark our model on the Set-8 and 2017 DAVIS-Test datasets. Our model achieves state-of-the-art results with up to 29.62% improvement in PSNR and a 50% decrease in run times over existing methods. Our codes are open-sourced at: github.com/spider-tronix/RepAr-Net.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129175768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9812380
Qianliang Wu, Yaqing Ding, Xinlei Qi, Jin Xie, Jian Yang
Multiple-camera systems have been widely used in self-driving cars, robots, and smartphones. In addition, they are typically also equipped with IMUs (inertial measurement units). Using the gravity direction extracted from the IMU data, the y-axis of the body frame of the multi-camera system can be aligned with this common direction, reducing the original three degree-of-freedom(DOF) relative rotation to a single DOF one. This paper presents a novel globally optimal solver to compute the relative pose of a generalized camera. Existing optimal solvers based on LM (Levenberg-Marquardt) method or SDP (semidefinite program) are either iterative or have high computational complexity. Our proposed optimal solver is based on minimizing the algebraic residual objective function. According to our derivation, using the least-squares algorithm, the original optimization problem can be converted into a system of two polynomials with only two variables. The proposed solvers have been tested on synthetic data and the KITTI benchmark. The experimental results show that the proposed methods have competitive robustness and accuracy compared with the existing state-of-the-art solvers.
{"title":"Globally Optimal Relative Pose Estimation for Multi-Camera Systems with Known Gravity Direction","authors":"Qianliang Wu, Yaqing Ding, Xinlei Qi, Jin Xie, Jian Yang","doi":"10.1109/icra46639.2022.9812380","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9812380","url":null,"abstract":"Multiple-camera systems have been widely used in self-driving cars, robots, and smartphones. In addition, they are typically also equipped with IMUs (inertial measurement units). Using the gravity direction extracted from the IMU data, the y-axis of the body frame of the multi-camera system can be aligned with this common direction, reducing the original three degree-of-freedom(DOF) relative rotation to a single DOF one. This paper presents a novel globally optimal solver to compute the relative pose of a generalized camera. Existing optimal solvers based on LM (Levenberg-Marquardt) method or SDP (semidefinite program) are either iterative or have high computational complexity. Our proposed optimal solver is based on minimizing the algebraic residual objective function. According to our derivation, using the least-squares algorithm, the original optimization problem can be converted into a system of two polynomials with only two variables. The proposed solvers have been tested on synthetic data and the KITTI benchmark. The experimental results show that the proposed methods have competitive robustness and accuracy compared with the existing state-of-the-art solvers.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126647662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811549
Hela Kadri, S. C. Dutilleul, P. Bon, R. Merzouki
In this paper, we consider the European Rail Traffic Management System (ERTMS) as a System-of-Systems (SoS) and propose modeling it using colored Petri nets. We formally control the European rail transport, while guaranteeing a set of cross-border security properties. This becomes an essential and challenging task since each of them have mainly developed safety and trackside rules regardless of its neighbors. The feature of this work lies in the approach that considers ERTMS Level 2 as an SoS and addresses the cross-border railway as a mode management problem. In addition, the aspects of mode activation/deactivation, starting state and handling of resource states common to multiple operating modes are taken into account in the proposed model.
{"title":"A Colored Petri Net Model for Control Problem of Border Crossing Under Constraints","authors":"Hela Kadri, S. C. Dutilleul, P. Bon, R. Merzouki","doi":"10.1109/icra46639.2022.9811549","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811549","url":null,"abstract":"In this paper, we consider the European Rail Traffic Management System (ERTMS) as a System-of-Systems (SoS) and propose modeling it using colored Petri nets. We formally control the European rail transport, while guaranteeing a set of cross-border security properties. This becomes an essential and challenging task since each of them have mainly developed safety and trackside rules regardless of its neighbors. The feature of this work lies in the approach that considers ERTMS Level 2 as an SoS and addresses the cross-border railway as a mode management problem. In addition, the aspects of mode activation/deactivation, starting state and handling of resource states common to multiple operating modes are taken into account in the proposed model.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126032124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811625
Dohee Lee, Qi Lu, T. Au
The objective of foraging robot swarms is to search for and collect resources in an unknown arena as quickly as possible. To avoid the congestion near the central collection zone, we previously proposed an extension to the multiple-place foraging in which robot chains are deployed dynamically so that foraging robots can deliver to the robot chains instead of the central collection zone. However, a robot chain can only reach one location at a time, and congestion can occur at the end of the robot chain. This paper presents an extension to dynamic robot chains called dynamic robot chain networks, which extends robot chains with branches, each of which reaches different resource clusters. We formulate the problem of finding the smallest dynamic robot chain networks as the Euclidean Steiner tree problem and explain how Steiner trees can be utilized to optimize the efficiency of the foraging operations. We implemented our foraging robot swarms in a simulator called ARGoS. Our experiments showed that dynamic robot chain networks can avoid obstacles and collect more resources when compared with the original robot chain design.
{"title":"Dynamic Robot Chain Networks for Swarm Foraging","authors":"Dohee Lee, Qi Lu, T. Au","doi":"10.1109/icra46639.2022.9811625","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811625","url":null,"abstract":"The objective of foraging robot swarms is to search for and collect resources in an unknown arena as quickly as possible. To avoid the congestion near the central collection zone, we previously proposed an extension to the multiple-place foraging in which robot chains are deployed dynamically so that foraging robots can deliver to the robot chains instead of the central collection zone. However, a robot chain can only reach one location at a time, and congestion can occur at the end of the robot chain. This paper presents an extension to dynamic robot chains called dynamic robot chain networks, which extends robot chains with branches, each of which reaches different resource clusters. We formulate the problem of finding the smallest dynamic robot chain networks as the Euclidean Steiner tree problem and explain how Steiner trees can be utilized to optimize the efficiency of the foraging operations. We implemented our foraging robot swarms in a simulator called ARGoS. Our experiments showed that dynamic robot chain networks can avoid obstacles and collect more resources when compared with the original robot chain design.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126797344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811736
Chao Zhao, Zhekai Tong, Juan Rojas, Jungwon Seo
We present a data-driven approach for effective bin picking from clutter. Recent bin picking solutions usually lead to a direct pinch grasp on a target object without addressing any other potential contact interaction in clutter. However, appropriate physical interaction can be essential to successful singulation and subsequent secure picking, the goal of bin picking. In this work, we contribute a framework that learns physically interactive actions for object picking end-to-end from a visual input in a self-supervised manner. The learned actions enable the robot to purposefully interact with a target object by performing a digging operation through the clutter. By leveraging a fully convolutional network (FCN), we predict picking success probabilities for a set of interactive action primitives that will in turn specify an optimal action to perform. The FCN is trained in a simulated environment through trial and error. Moreover, new datasets are collected using the latest network through iterative self-supervision. Extensive real-world bin picking experiments show the effectiveness and generalizability of the approach.
{"title":"Learning to Pick by Digging: Data-Driven Dig-Grasping for Bin Picking from Clutter","authors":"Chao Zhao, Zhekai Tong, Juan Rojas, Jungwon Seo","doi":"10.1109/icra46639.2022.9811736","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811736","url":null,"abstract":"We present a data-driven approach for effective bin picking from clutter. Recent bin picking solutions usually lead to a direct pinch grasp on a target object without addressing any other potential contact interaction in clutter. However, appropriate physical interaction can be essential to successful singulation and subsequent secure picking, the goal of bin picking. In this work, we contribute a framework that learns physically interactive actions for object picking end-to-end from a visual input in a self-supervised manner. The learned actions enable the robot to purposefully interact with a target object by performing a digging operation through the clutter. By leveraging a fully convolutional network (FCN), we predict picking success probabilities for a set of interactive action primitives that will in turn specify an optimal action to perform. The FCN is trained in a simulated environment through trial and error. Moreover, new datasets are collected using the latest network through iterative self-supervision. Extensive real-world bin picking experiments show the effectiveness and generalizability of the approach.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126832162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811912
Nathan Lichtlé, Eugene Vinitsky, Matthew Nice, Benjamin Seibold, D. Work, A. Bayen
Autonomous vehicle-based traffic smoothing con-trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I–24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4's and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.
{"title":"Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data","authors":"Nathan Lichtlé, Eugene Vinitsky, Matthew Nice, Benjamin Seibold, D. Work, A. Bayen","doi":"10.1109/icra46639.2022.9811912","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811912","url":null,"abstract":"Autonomous vehicle-based traffic smoothing con-trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I–24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4's and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114118132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811807
Bowen Weng, Hua Chen, W. Zhang
This paper studies the distributed multi-robot constrained navigation problem. While the multi-robot collision avoidance has been extensively studied in the literature with safety being the primary focus, the individual robot's destination convergence is not necessarily guaranteed. In particular, robots may get stuck in the local equilibria or periodic orbits of the multi-robot system, some of which are practically known as the deadlock and the livelock behaviors. Inspired by the combination of Control Lyapunov Function (CLF) and Control Barrier Function (CBF) for the nonlinear system's constrained stabilization, the authors present a guaranteed safe feedback control policy with improved convergence performance. The proposed Parametric CLF (PCLF) scheme adaptively determines the appropriate CLF parameterization within the in-stantaneous feasible action space. The algorithm also induces a conditional global asymptotic convergence guarantee for multi-robot system of single-integrator dynamics, and is empirically effective for nonlinear nonholonomic vehicle model. Empiri-cally, the proposed PCLF-CBF framework exhibits superior performance than state-of-the-art methods, including its de-generated counterpart of various CLF-CBF solutions.
{"title":"On the Convergence of Multi-robot Constrained Navigation: A Parametric Control Lyapunov Function Approach","authors":"Bowen Weng, Hua Chen, W. Zhang","doi":"10.1109/icra46639.2022.9811807","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811807","url":null,"abstract":"This paper studies the distributed multi-robot constrained navigation problem. While the multi-robot collision avoidance has been extensively studied in the literature with safety being the primary focus, the individual robot's destination convergence is not necessarily guaranteed. In particular, robots may get stuck in the local equilibria or periodic orbits of the multi-robot system, some of which are practically known as the deadlock and the livelock behaviors. Inspired by the combination of Control Lyapunov Function (CLF) and Control Barrier Function (CBF) for the nonlinear system's constrained stabilization, the authors present a guaranteed safe feedback control policy with improved convergence performance. The proposed Parametric CLF (PCLF) scheme adaptively determines the appropriate CLF parameterization within the in-stantaneous feasible action space. The algorithm also induces a conditional global asymptotic convergence guarantee for multi-robot system of single-integrator dynamics, and is empirically effective for nonlinear nonholonomic vehicle model. Empiri-cally, the proposed PCLF-CBF framework exhibits superior performance than state-of-the-art methods, including its de-generated counterpart of various CLF-CBF solutions.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121077984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9812101
Li Liu, Xing Cai, Ge Li, Thomas H. Li
Keypoint extraction including both keypoint detection and description is a fundamental step in a wide range of geometric multimedia applications. In recent years, many learning-based approaches for keypoint extraction emerge and achieve promising results. However, they usually design network architectures empirically and lack of considerations about the comprehensive performance, which leads to limited applications. In this paper, we propose a practical framework based on Neural Architecture Search (NAS) technology, DKNAS, which can search architectures automatically and maintain efficiency and effectiveness, simultaneously. To the best of our knowledge, the proposed framework is the first NAS framework for keypoint extraction. The evaluation on HPatches dataset shows that our method achieves state-of-the-art results in the metrics of repeatability, localization error, homography accuracy and matching scores. Besides, our model is applied to a traditional Simultaneous Localization and Mapping (SLAM) system, ORB-SLAM2, to replace the handcrafted keypoints. Experimental results demonstrate that the system adopting our model outperforms ORB-SLAM2 and some other deep keypoints enhanced systems.
{"title":"DKNAS: A Practical Deep Keypoint Extraction Framework Based on Neural Architecture Search","authors":"Li Liu, Xing Cai, Ge Li, Thomas H. Li","doi":"10.1109/icra46639.2022.9812101","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9812101","url":null,"abstract":"Keypoint extraction including both keypoint detection and description is a fundamental step in a wide range of geometric multimedia applications. In recent years, many learning-based approaches for keypoint extraction emerge and achieve promising results. However, they usually design network architectures empirically and lack of considerations about the comprehensive performance, which leads to limited applications. In this paper, we propose a practical framework based on Neural Architecture Search (NAS) technology, DKNAS, which can search architectures automatically and maintain efficiency and effectiveness, simultaneously. To the best of our knowledge, the proposed framework is the first NAS framework for keypoint extraction. The evaluation on HPatches dataset shows that our method achieves state-of-the-art results in the metrics of repeatability, localization error, homography accuracy and matching scores. Besides, our model is applied to a traditional Simultaneous Localization and Mapping (SLAM) system, ORB-SLAM2, to replace the handcrafted keypoints. Experimental results demonstrate that the system adopting our model outperforms ORB-SLAM2 and some other deep keypoints enhanced systems.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116236512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811738
I. Borisov, Evgenii E. Khornutov, D.V. Ivolga, N.A. Molchanov, I.A. Maksimov, S. Kolyubin
Anthropomorphic robotic grippers are required for robots, prostheses, and orthosis to enable manipulation of a priori unknown and variable-shape objects. It has to meet a wide range of sometimes contradictory requirements in terms of adaptivity, dexterity, high payload to weight ratio, robustness, aesthetics, compactness, lightweight, etc. Within this paper, we utilize the morphological computation approach to introduce design for anthropomorphic re-configurable underactuated grippers. The key to fingers' adaptivity is embedded passive variable length links and elastic elements at input joints. Based on this concept, we designed a palm-size five-finger gripper, where 14 DoFs, including thumb, are controlled by just 4 motors, such that it can perform both precision pinch and encompassing power grasps of various objects. The paper describes synthesized linkages for digits, hand design overview, control strategy, and test results of a physical prototype.
{"title":"Reconfigurable Underactuated Adaptive Gripper Designed by Morphological Computation *","authors":"I. Borisov, Evgenii E. Khornutov, D.V. Ivolga, N.A. Molchanov, I.A. Maksimov, S. Kolyubin","doi":"10.1109/icra46639.2022.9811738","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811738","url":null,"abstract":"Anthropomorphic robotic grippers are required for robots, prostheses, and orthosis to enable manipulation of a priori unknown and variable-shape objects. It has to meet a wide range of sometimes contradictory requirements in terms of adaptivity, dexterity, high payload to weight ratio, robustness, aesthetics, compactness, lightweight, etc. Within this paper, we utilize the morphological computation approach to introduce design for anthropomorphic re-configurable underactuated grippers. The key to fingers' adaptivity is embedded passive variable length links and elastic elements at input joints. Based on this concept, we designed a palm-size five-finger gripper, where 14 DoFs, including thumb, are controlled by just 4 motors, such that it can perform both precision pinch and encompassing power grasps of various objects. The paper describes synthesized linkages for digits, hand design overview, control strategy, and test results of a physical prototype.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115279434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811975
Guangyao Ding, Meiying Zhang, E. Li, Qi Hao
2D&3D object detection always suffers from a dramatic performance drop when transferring the model trained in the source domain to the target domain due to various domain shifts. In this paper, we propose a Joint Self-Training (JST) framework to improve 2D image and 3D point cloud detectors with aligned outputs simultaneously during the transferring. The proposed framework contains three novelties to overcome object biases and unstable self-training processes: 1) an anchor scaling scheme is developed to efficiently eliminate the object size biases without any modification on point clouds; 2) a 2D&3D bounding box alignment method is proposed to generate high-quality pseudo labels for the self-training process; 3) a model smoothing based training strategy is developed to reduce the training oscillation properly. Experiment results show that the proposed approach improves the performance of 2D and 3D detectors in the target domain simultaneously; especially the superior accuracy of 3D detection can be achieved on benchmark datasets over the state-of-the-art methods.
{"title":"JST: Joint Self-training for Unsupervised Domain Adaptation on 2D&3D Object Detection","authors":"Guangyao Ding, Meiying Zhang, E. Li, Qi Hao","doi":"10.1109/icra46639.2022.9811975","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811975","url":null,"abstract":"2D&3D object detection always suffers from a dramatic performance drop when transferring the model trained in the source domain to the target domain due to various domain shifts. In this paper, we propose a Joint Self-Training (JST) framework to improve 2D image and 3D point cloud detectors with aligned outputs simultaneously during the transferring. The proposed framework contains three novelties to overcome object biases and unstable self-training processes: 1) an anchor scaling scheme is developed to efficiently eliminate the object size biases without any modification on point clouds; 2) a 2D&3D bounding box alignment method is proposed to generate high-quality pseudo labels for the self-training process; 3) a model smoothing based training strategy is developed to reduce the training oscillation properly. Experiment results show that the proposed approach improves the performance of 2D and 3D detectors in the target domain simultaneously; especially the superior accuracy of 3D detection can be achieved on benchmark datasets over the state-of-the-art methods.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"26 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120988412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：