检索结果-内蒙古大学图书馆

学校读者我要写书评

暂无评论

Safe Value Functions

arXiv 2021年

作者： Massiani, Pierre-François Heim, Steve Solowjow, Friedrich Trimpe, Sebastian The Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen52068 Germany The Intelligent Control Systems Group Max Planck Institute for Intelligent Systems Stuttgart70569 Germany The Biomimetic Robotics Lab Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge02139 United States

Safety constraints and optimality are important but sometimes conflicting criteria for controllers. Although these criteria are often solved separately with different tools to maintain formal guarantees, it is also common practice in reinforcement learning to simply modify reward functions by penalizing failures, with the penalty treated as a mere heuristic. We rigorously examine the relationship of both safety and optimality to penalties, and formalize sufficient conditions for safe value functions (SVFs): value functions that are both optimal for a given task, and enforce safety constraints. We reveal this structure by examining when rewards preserve viability under optimal control, and show that there always exists a finite penalty that induces a safe value function. This penalty is not unique, but upper-unbounded: larger penalties do not harm optimality. Although it is often not possible to compute the minimum required penalty, we reveal clear structure of how the penalty, rewards, discount factor, and dynamics interact. This insight suggests practical, theory-guided heuristics to design reward functions for control problems where safety is important. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

Joint Counting, Detection and Re-Identification for Multi-Object Tracking

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ren, Weihong Wu, Denglu Cao, Hui Chen, Xi'ai Han, Zhi Liu, Honghai The School of Mechanical Engineering and Automation State Key Lab of Robotics and Systems Harbin Institute of Technology Shenzhen518055 China The Shenzhen Duorou Intelligent System Co. Ltd. Shenzhen518055 China The School of Electrical Engineering Xi’an Jiaotong University Xi’an710049 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Science Beijing110169 China

The recent trend in 2D multiple object tracking (MOT) is jointly solving detection and tracking, where object detection and appearance feature (or motion) are learned simultaneously. Despite competitive performance, in crowded scenes, joint detection and tracking usually fail to find accurate object associations due to missed or false detections. In this paper, we jointly model counting, detection and re-identification in an end-to-end framework, named CountingMOT, tailored for crowded scenes. By imposing mutual object-count constraints between detection and counting, the CountingMOT tries to find a balance between object detection and crowd density map estimation, which can help it to recover missed detections or reject false detections. Our approach is an attempt to bridge the gap of object detection, counting, and re-Identification. This is in contrast to prior MOT methods that either ignore the crowd density and thus are prone to failure in crowded scenes, or depend on local correlations to build a graphical relationship for matching targets. The proposed MOT tracker can perform online and real-time tracking, and achieves the state-of-the-art results on public benchmarks MOT16 (MOTA of 79.7%), MOT17 (MOTA of 81.3%) and MOT20 (MOTA of 78.9%). Source code is available at https://***/weihong9/CountingMOT. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Fundus-Image-Based Retinal Vascular Analysis in Myopic Eyes 42

学校读者我要写书评

暂无评论

Fundus-Image-Based Retinal Vascular Analysis in Myopic Eyes

42nd Chinese Control Conference, CCC 2023

作者： Shen, Jichen Zou, Haohan Wang, Yan Liu, Jinchao Yu, Ningbo College of Artificial Intelligence Nankai University Tianjin300350 China Clinical College of Ophthalmology Tianjin Medical University Tianjin300070 China Tianjin Key Lab of Ophthalmology and Visual Science Tianjin Eye Institute Tianjin Eye Hospital Nankai University Affiliated Eye Hospital Tianjin300020 China Nankai University Eye Institute Nankai University Tianjin300350 China Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin300350 China Engineering Research Center of Trusted Behavior Intelligence Ministry of Education Nankai University Tianjin300350 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

ISBN: (纸本)9789887581543

Myopia is prevalent worldwide and it is of great significance to prevent, control and intervene myopia in an early stage. The etiopathogenesis of myopia remains unclear and needs further research. Fundus photographs can show biomarkers and lesions of the retina in a non-invasive way directly. To discover some potential changes in myopic eyes, we extracted the retinal vascular features from vessel segmented results, and calculated the Spearman correlation coefficients between the retinal vascular features and the spherical refractive errors. The Kruskal-Wallis test was applied to explore the difference exists in the characteristics of retinal vessels among the mild, moderate and high myopia groups. The statistical analysis results indicated that the higher the degrees of myopia, the smaller the retinal vessels. This study found vascular changes in myopic eyes through fundus images, which could help to explain the mechanism of myopia and the damage caused by myopia. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Ophthalmology

A deep learning approach to diagnosing multiple sclerosis from smartphone data

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Schwab, Patrick Karlen, Walter Mobile Health Systems Lab Institute of Robotics and Intelligent Systems Department of Health Sciences and Technology Eth Zurich

Multiple sclerosis (MS) affects the central nervous system with a wide range of symptoms. MS can, for example, cause pain, changes in mood and fatigue, and may impair a person's movement, speech and visual functions. Diagnosis of MS typically involves a combination of complex clinical assessments and tests to rule out other diseases with similar symptoms. New technologies, such as smartphone monitoring in free-living conditions, could potentially aid in objectively assessing the symptoms of MS by quantifying symptom presence and intensity over long periods of time. Here, we present a deep-learning approach to diagnosing MS from smartphone-derived digital biomarkers that uses a novel combination of a multilayer perceptron with neural soft attention to improve learning of patterns in long-term smartphone monitoring data. Using data from a cohort of 774 participants, we demonstrate that our deep-learning models are able to distinguish between people with and without MS with an area under the receiver operating characteristic curve of 0.88 (95% CI: 0.70, 0.88). Our experimental results indicate that digital biomarkers derived from smartphone data could in the future be used as additional diagnostic criteria for MS. Copyright © 2020, The Authors. All rights reserved.

关键词： Smartphones

GraspME - Grasp manifold estimator

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hager, Janik Bauer, Ruben Toussaint, Marc Mainprice, Jim Machine Learning and Robotics Lab IPVS University of Stuttgart Germany Max Planck Institute for Intelligent Systems IS-MPI Tübingen/Stuttgart Germany Technische Universität Berlin TUB Germany

In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images. To perform manipulation tasks autonomously it is crucial for robots to have such graspability models of the surrounding objects. Grasp manifolds have the advantage of providing continuously infinitely many grasps, which is not the case when using other grasp representations such as predefined grasp points. For instance, this property can be leveraged in motion optimization to define goal sets as implicit surface constraints in the robot configuration space. In this work, we restrict ourselves to the case of estimating possible end-effector positions directly from 2D camera images. To this extend, we define grasp manifolds via a set of keypoints and locate them in images using a Mask R-CNN [1] backbone. Using learned features allows to generalize to different view angle, with potentially noisy images, and objects that were not part of the training set. We rely on simulation data only and perform experiments on simple and complex objects, including unseen ones. Our framework achieves an inference speed of 11.5 fps on a GPU, an average precision for keypoint estimation of 94.5% and a mean pixel distance of only 1.29. This shows that we can estimate the objects very well via bounding boxes and segmentation masks as well as approximate the correct grasp manifold's keypoint coordinates. © 2021, CC BY-NC-ND.

关键词： Cameras

Gesture Recognition Based on Attention and Dilated Causal Convolution

学校读者我要写书评

暂无评论

Gesture Recognition Based on Attention and Dilated Causal Co...

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Zhou, Xin Liu, Jiaqing Huai, Yaping Ye, Jiancong Wang, Can Wu, Xinyu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China Department of Rehabilitation Medicine Shenzhen Longhua District Central Hospital Shenzhen518000 China University of Science and Technology of China China University of Chinese Academy of Sciences China South China University of Technology China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

In recent years, based on surface electromyography (sEMG), great progress has been made in gesture recognition tasks, which is significant to the study of computer interaction and prosthesis control. Prior to this, many researches have focused on feature selection and time series modeling of data. However, it is difficult and complicated to manually perform feature extraction and feature selection on data. Besides, most of the time series modeling is based on recurrent neural networks with memory cell, that is, Long Short-term Memory (LSTM). Even though LSTM has memory gate, but cannot completely records historical information. In this paper, to address the above problems, we propose a Temporal Convolutional Network based on Attention mechanism (ATCN), in which Attention is used to characterize temporal features, and dilated causal convolution to capture more historical information. ATCN achieves 95.26% accuracy with this method on the public dataset NinaPro DB2, which exceeds the state-of-the-art accuracy of 5%. The experiments show that this approach is feasible and effective for gesture recognition tasks. Our contributions are as follows: Firstly, Attention mechanism is introduced into the field of prosthetic control. Then, ATCN is proposed for gesture recognition. Finally, ATCN achieves better results than LSTM on multiple public datasets. © 2022 IEEE.

关键词： Long short-term memory

A system for traded control teleoperation of manipulation tasks using intent prediction from hand gestures

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Oh, Yoojin Schäfer, Tim Rüther, Benedikt Toussaint, Marc Mainprice, Jim Machine Learning and Robotics Lab IPVS University of Stuttgart Germany Max Planck Institute for Intelligent Systems MPI-IS Tübingen/Stuttgart Germany Technische Universität Berlin TUB Germany

This paper presents a teleoperation system that includes robot perception and intent prediction from hand gestures. The perception module identifies the objects present in the robot workspace and the intent prediction module which object the user likely wants to grasp. This architecture allows the approach to rely on traded control instead of direct control: we use hand gestures to specify the goal objects for a sequential manipulation task, the robot then autonomously generates a grasping or a retrieving motion using trajectory optimization. The perception module relies on the model-based tracker to precisely track the 6D pose of the objects and makes use of a state of the art learning-based object detection and segmentation method, to initialize the tracker by automatically detecting objects in the scene. Goal objects are identified from user hand gestures using a trained a multi-layer perceptron classifier. After presenting all the components of the system and their empirical evaluation, we present experimental results comparing our pipeline to a direct traded control approach (i.e., one that does not use prediction) which shows that using intent prediction allows to bring down the overall task execution time. © 2021, CC BY-NC-ND.

关键词： Forecasting

A Unified Perception Benchmark for Capacitive Proximity Sensing Towards Safe Human-Robot Collaboration (HRC)

学校读者我要写书评

暂无评论

A Unified Perception Benchmark for Capacitive Proximity Sens...

IEEE International Conference on robotics and Automation (ICRA)

作者： Serkan Ergun Yitao Ding Hosam Alagi Christian Schöffmann Barnaba Ubezio Gergely Soti Michael Rathmair Stephan Mühlbacher-Karrer Ulrike Thomas Björn Hein Michael Hofbaur Hubert Zangl Institute of Smart Systems Technologies Klagenfurt University (AAU) Klagenfurt am Wörthersee Austria Lab of Robotics and Human-Machine-Interaction Chemnitz University of Technology (TUC) Chemnitz Germany Institute for Anthropomatics and Robotics - Intelligent Process Automation and Robotics Lab (IAR - IPR) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Joanneum Research Robotics (Jr) Institute of Robotics and Mechatronics Klagenfurt am Wörthersee Austria Karlsruhe University of Applied Sciences

During the co-presence of human workers and robots, measures are required to avoid injuries from undesired contacts. Capacitive Proximity Sensors (CPSs) offer a cost-effective solution to cover the entire robot manipulator with fast close-range perception for HRC tasks, closing the perception gap between tactile detection and mid-range perception. CPSs do not suffer from occlusion and compared to pure tactile or force sensing, they react earlier and allow increasing the operating speed of Collaborative Robots (Cobots) while still maintaining safety. However, since capacitive coupling to obstacles varies with their distance, shape and material properties, the projection from capacitance to actual distances is a general problem. In this work, we propose an universal benchmark test procedure for fellow researchers to evaluate their CPSs. Considering ISO/TS 15066 for Power and Force Limiting (PFL) as a reference, we derive the requirements for the specified body regions and propose a method for determining the operation speed to comply with PFL based on a pre-defined detection threshold. Finally, the benchmark test procedure is evaluated on three different concepts of CPSs from the contributed researchers, demonstrating the general applicability.

关键词： Shape Force Collaboration Benchmark testing Robot sensing systems Manipulators Sensors

Learning efficient constraint graph sampling for robotic sequential manipulation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ortiz-Haro, Joaquim Hartmann, Valentin N. Oguz, Ozgur S. Toussaint, Marc Machine Learning & Robotics Lab. University of Stuttgart Germany Max Planck Institute for Intelligent Systems Germany Learning and Intelligent Systems Lab. TU Berlin Germany

Efficient sampling from constraint manifolds, and thereby generating a diverse set of solutions for feasibility problems, is a fundamental challenge. We consider the case where a problem is factored, that is, the underlying nonlinear program is decomposed into differentiable equality and inequality constraints, each of which depends only on some variables. Such problems are at the core of efficient and robust sequential robot manipulation planning. Naive sequential conditional sampling of individual variables, as well as fully joint sampling of all variables at once (e.g., leveraging optimization methods), can be highly inefficient and non-robust. We propose a novel framework to learn how to break the overall problem into smaller sequential sampling problems. Specifically, we leverage Monte-Carlo Tree Search to learn assignment orders for the variable-subsets, in order to minimize the computation time to generate feasible full samples. This strategy allows us to efficiently compute a set of diverse valid robot configurations for mode-switches within sequential manipulation tasks, which are waypoints for subsequent trajectory optimization or sampling-based motion planning algorithms. We show that the learning method quickly converges to the best sampling strategy for a given problem, and outperforms user-defined orderings or fully joint optimization, while providing a higher sample diversity. © 2020, CC BY.

关键词： Constraint theory