检索结果-内蒙古大学图书馆

Risk-Aware Motion Planning for a Limbed Robot with Stochastic Gripping Forces Using Nonlinear Programming

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shirai, Yuki Lin, Xuan Tanaka, Yusuke Mehta, Ankur Hong, Dennis Robotics and Mechanisms Laboratory Department of Mechanical and Aerospace Engineering University of California Los AngelesCA90095 United States Laboratory for Embedded Machines and Ubiquitous Robotics Department of Electrical and Computer Engineering University of California Los AngelesCA90095 United States

We present a motion planning algorithm with probabilistic guarantees for limbed robots with stochastic gripping forces. Planners based on deterministic models with a worst-case uncertainty can be conservative and inflexible to consider the stochastic behavior of the contact, especially when a gripper is installed. Our proposed planner enables the robot to simultaneously plan its pose and contact force trajectories while considering the risk associated with the gripping forces. Our planner is formulated as a nonlinear programming problem with chance constraints, which allows the robot to generate a variety of motions based on different risk bounds. To model the gripping forces as random variables, we employ Gaussian Process regression. We validate our proposed motion planning algorithm on an 11.5 kg six-limbed robot for two-wall climbing. Our results show that our proposed planner generates various trajectories (e.g., avoiding low friction terrain under the low risk bound, choosing an unstable but faster gait under the high risk bound) by changing the probability of risk based on various specifications. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

Extensions of the open-source framework Aerostack 3.0 for the development of more interactive flights between UAVs

学校读者我要写书评

暂无评论

Extensions of the open-source framework Aerostack 3.0 for th...

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Wojciech Giernacki Jacek Cieślak Martin Molina Pascual Campoy Institute of Robotics and Machine Intelligence Faculty of Control Robotics and Electrical Engineering Poznan University of Technology Poznań Poland Department of Artificial Intelligence Technical University of Madrid (UPM) Madrid Spain Computer Vision and Aerial Robotics (CVAR) Centre for Automation and Robotics Technical University of Madrid (UPM) Madrid Spain

ISBN: (数字)9781728142784

ISBN: (纸本)9781728142791

The basis for properly verified R&D works is to provide reliable prototyping tools at three most important stages: computer simulation, laboratory tests and real-world experiments. In the laboratory-limited conditions, particular importance is attributed to the first two stages, especially in the context of the safety development of autonomous flights of unmanned aerial vehicle (UAV) groups in various missions. The open-source framework Aerostack support those needs and its effectiveness has been proven in the International Micro Air Vehicle Indoor Competitions (IMAV 2013, 2016, 2017) and Mohammed Bin Zayed International robotics Challenge (MBZIRC 2020). In the paper, the exemplary functionalities for the new version of Aerostack Version 3.0 Distribution Sirocco (Aerial robotics framework for the industry), extended additionally with a library of new behaviors, are presented. The mission of UAVs can be developed fast and effectively in order to conduct test flights with real drones in lab, before one will decide to fly autonomously outdoor. The representative results obtained for low-cost *** 2.0 UAV models in two missions, are presented. The first mission is autonomous patrolling the area by a pair of UAVs, the second - intercepting the intruder in guarded area by the guard UAV.

关键词： Robots Trajectory Drones Libraries Software computer architecture

Reference design for closed loop system optimization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Balula, Samuel Liniger, Alex Rupenyan, Alisa Lygeros, John Automatic Control Laboratory Department of Electrical Engineering and Information Technology ETH Zurich Switzerland Inspire AG ETH Zurich Switzerland Computer Vision Lab Department of Electrical Engineering and Information Technology ETH Zurich Switzerland

An optimization-based method for improving the productivity of precision machine tools is proposed, where the reference path is computed in local coordinates, and information about the machine tool performance is learned from experimental data. The optimization yields a modified reference that is tracked by the existing low-level controller. The method is tested in simulation for a biaxial positioning system. The positioning system is modelled as double integrator, and the controller characteristic is modelled from experimental data using a least-squares fit. Simulation results show that the method is effective in designing optimal references even for challenging geometries such as sharp corners. The application of this procedure allows the retrofit of the control of existing machines with minimal overhead, by providing a modified reference file to track. Copyright © 2020, The Authors. All rights reserved.

关键词： Closed loop systems

Propagating confidences through cNNs for sparse data regression 29

学校读者我要写书评

暂无评论

Propagating confidences through cNNs for sparse data regress...

29th British Machine vision Conference, BMVC 2018

作者： Eldesokey, Abdelrahman Felsberg, Michael Khan, Fahad Shahbaz Computer Vision Laboratory Department of Electrical Engineering Linkoping University Linkoping Sweden Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates

In most computer vision applications, convolutional neural networks (CNNs) operate on dense image data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open problem with numerous applications in autonomous driving, robotics, and surveillance. To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. Furthermore, we propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. Comprehensive experiments are performed on the KITTI depth benchmark and the results clearly demonstrate that the proposed approach achieves superior performance while requiring three times fewer parameters than the state-of-the-art methods. Moreover, our approach produces a continuous pixel-wise confidence map enabling information fusion, state inference, and decision support. © 2018. The copyright of this document resides with its authors.

关键词： Convolution

Camera Exposure Control for Robust Robot vision with Noise-Aware Image Quality Assessment

学校读者我要写书评

暂无评论

Camera Exposure Control for Robust Robot Vision with Noise-A...

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Ukcheol Shin Jinsun Park Gyumin Shim Francois Rameau In So Kweon Robotics and Computer Vision Laboratory School of Electrical Engineering KAIST Daejeon Republic of Korea

In this paper, we propose a noise-aware exposure control algorithm for robust robot vision. Our method aims to capture best-exposed images, which can boost the performance of various computer vision and robotics tasks. For this purpose, we carefully design an image quality metric that captures complementary quality attributes and ensures light-weight computation. Specifically, our metric consists of a combination of image gradient, entropy, and noise metrics. The synergy of these measures allows the preservation of sharp edges and rich texture in the image while maintaining a low noise level. Using this novel metric, we propose a real-time and fully automatic exposure and gain control technique based on the Nelder-Mead method. To illustrate the effectiveness of our technique, a large set of experimental results demonstrates the higher qualitative and quantitative performance compared with conventional approaches.

关键词：

Towards to robust and generalized medical image segmentation framework

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Yurong Zhang, Hui Wang, Yaonan Liu, Lizhu Wu, Q.M. Jonathan Yang, Yimin National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Hunan Changsha410082 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B3P4 Canada Department of Computer Science Lakehead University Vector Institute TorontoM5G 1M1 Canada

—To mitigate the radiologist’s workload, computer-aided diagnosis with the capability to review and analyze medical images is gradually deployed. Deep learning-based region of interest segmentation is among the most exciting use cases. However, this paradigm is restricted in real-world clinical applications due to the poor robustness and generalization. The issue is more sinister with a lack of training data. In this paper, we address the challenge from the representation learning point of view. We investigate that the collapsed representations, as one of the main reasons which caused poor robustness and generalization, could be avoided through transfer learning. Therefore, we propose a novel two-stage framework for robust generalized segmentation. In particular, an unsupervised Tile-wise AutoEncoder (T-AE) pretraining architecture is coined to learn meaningful representation. Furthermore, this learned prior knowledge is transferred to the segmentation benchmark. Coupled with an image reconstruction network, the representation keeps to be decoded, encouraging the model to capture more semantic features. Experiments of lung segmentation on multi chest X-ray datasets are conducted. Empirically, the comprehensive results demonstrate the superior generalization capability of the proposed framework on unseen domains in terms of high performance and robustness to corruption, especially under the scenario of the limited training data. © 2021, CC BY.

关键词： computer aided diagnosis

Efficient MedSAMs: Segment Anything in Medical Images on Laptop

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Jun Li, Feifei Kim, Sumin Asakereh, Reza Le, Bao-Hiep Nguyen-Vu, Dang-Khoa Pfefferle, Alexander Wei, Muxin Gao, Ruochen Lyu, Donghang Yang, Songxiao Purucker, Lennart Marinov, Zdravko Staring, Marius Lu, Haisheng Dao, Thuy Thanh Ye, Xincheng Li, Zhi Brugnara, Gianluca Vollmuth, Philipp Foltyn-Dumitru, Martha Cho, Jaeyoung Mahmutoglu, Mustafa Ahmed Bendszus, Martin Pflüger, Irada Rastogi, Aditya Ni, Dong Yang, Xin Zhou, Guang-Quan Wang, Kaini Heller, Nicholas Papanikolopoulos, Nikolaos Weight, Christopher Tong, Yubing Udupa, Jayaram K. Patrick, Cahill J. Wang, Yaqi Zhang, Yifan Contijoch, Francisco McVeigh, Elliot Ye, Xin He, Shucheng Haase, Robert Pinetz, Thomas Radbruch, Alexander Krause, Inga Kobler, Erich He, Jian Tang, Yucheng Yang, Haichun Huo, Yuankai Luo, Gongning Kushibar, Kaisar Amankulov, Jandos Toleshbayev, Dias Mukhamejan, Amangeldi Egger, Jan Pepe, Antonio Gsaxner, Christina Luijten, Gijs Fujita, Shohei Kikuchi, Tomohiro Wiestler, Benedikt Kirschke, Jan S. de la Rosa, Ezequiel Bolelli, Federico Lumetti, Luca Grana, Costantino Xie, Kunpeng Wu, Guomin Puladi, Behrus Martín-Isla, Carlos Lekadir, Karim Campello, Victor M. Shao, Wei Brisbane, Wayne Jiang, Hongxu Wei, Hao Yuan, Wu Li, Shuangle Zhou, Yuyin Wang, Bo AI Collaborative Centre University Health Network Department of Laboratory Medicine and Pathobiology University of Toronto Vector Institute Toronto Canada Peter Munk Cardiac Centre University Health Network Toronto Canada Toronto General Hospital Research Institute University Health Network Department of Computer Science University of Toronto University Health Network Vector Institute Toronto Canada University of Science Vietnam National University Ho Chi Minh City Viet Nam Institute of Computer Science University of Freiburg Freiburg Germany School of Medicine and Health Harbin Institute of Technology Harbin China Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Department of System and Control Engineering School of Engineering Institute of Science Tokyo Formerly Tokyo Institute of Technology Tokyo Japan Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia School of Cyberspace Hangzhou Dianzi University Hangzhou China Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Radiology and Clinical AI Department of Neuroradiology University Hospital Bonn Germany School of Biomedical Engineering Shenzhen University Shenzhen China School of Biological Science and Medical Engineering Southeast University Nanjing China Department of Urology Cleveland Clinic Cleveland United States Department of Computer Science University of Minnesota Minneapolis United St

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. © 2024, CC BY-NC-SA.

关键词： Open source software

Camera exposure control for robust robot vision with noise-aware image quality assessment

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shin, Ukcheol Park, Jinsun Shim, Gyumin Rameau, Francois Kweon, In So Robotics and Computer Vision Laboratory School of Electrical Engineering KAIST Daejeon34141 Korea Republic of

In this paper, we propose a noise-aware exposure control algorithm for robust robot vision. Our method aims to capture the best-exposed image which can boost the performance of various computer vision and robotics tasks. For this purpose, we carefully design an image quality metric which captures complementary quality attributes and ensures light-weight computation. Specifically, our metric consists of a combination of image gradient, entropy, and noise metrics. The synergy of these measures allows preserving sharp edge and rich texture in the image while maintaining a low noise level. Using this novel metric, we propose a real-time and fully automatic exposure and gain control technique based on the Nelder-Mead method. To illustrate the effectiveness of our technique, a large set of experimental results demonstrates higher qualitative and quantitative performances when compared with conventional approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： computer vision

Deep reinforcement learning with linear quadratic regulator regions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Fernandez, Gabriel I. Togashi, Colin Hong, Dennis W. Yang, Lin F. Robotics & Mechanisms Laboratory Mechanical & Aerospace Engineering Department University of California Los AngelesCA United States Department of Electrical & Computer Engineering University of California Los AngelesCA United States

Practitioners often rely on compute-intensive domain randomization to ensure reinforcement learning policies trained in simulation can robustly transfer to the real world. Due to unmodeled nonlinearities in the real system, however, even such simulated policies can still fail to perform stably enough to acquire experience in real environments. In this paper we propose a novel method that guarantees a stable region of attraction for the output of a policy trained in simulation, even for highly nonlinear systems. Our core technique is to use "bias-shifted" neural networks for constructing the controller and training the network in the simulator. The modified neural networks not only capture the nonlinearities of the system but also provably preserve linearity in a certain region of the state space and thus can be tuned to resemble a linear quadratic regulator that is known to be stable for the real system. We have tested our new method by transferring simulated policies for a swing-up inverted pendulum to real systems and demonstrated its efficacy. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning