检索结果-内蒙古大学图书馆

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

作者： David Blanco-Mulero Gokhan Alcan Fares J. Abu-Dakka Ville Kyrki School of Electrical Engineering Aalto University Finland Munich Institute of Robotics and Machine Intelligence Technische Universität München München Germany Intelligent Robotics Group EEA Aalto University Espoo Finland

Pre-defined manipulation primitives are widely used for cloth manipulation. However, cloth properties such as its stiffness or density can highly impact the performance of these primitives. Although existing solutions have tackled the parameterisation of pick and place locations, the effect of factors such as the velocity or trajectory of quasi-static and dynamic manipulation primitives has been neglected. Choosing appropriate values for these parameters is crucial to cope with the range of materials present in house-hold cloth objects. To address this challenge, we introduce the Quasi-Dynamic Parameterisable (QDP) method, which optimises parameters such as the motion velocity in addition to the pick and place positions of quasi-static and dynamic manipulation primitives. In this work, we leverage the framework of Sequential Reinforcement Learning to decouple sequentially the parameters that compose the primitives. To evaluate the effectiveness of the method, we focus on the task of cloth unfolding with a robotic arm in simulation and real-world experiments. Our results in simulation show that by deciding the optimal parameters for the primitives the performance can improve by 20% compared to sub-optimal ones. Real-world results demonstrate the advantage of modifying the velocity and height of manipulation primitives for cloths with different mass, stiffness, shape, and size. Supplementary material, videos, and code, can be found at https://***/view/qdp-srl.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SRI-Graph: A Novel Scene-Robot Interaction Graph for Robust Scene Understanding

SRI-Graph: A Novel Scene-Robot Interaction Graph for Robust ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Dong Yang Xiao Xu Mengchen Xiong Edwin Babaians Eckehard Steinbach Department of Computer Engineering School of Computation Information and Technology Chair of Media Technology (LMT) and Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich (TUM) Germany

We propose a novel scene-robot interaction graph (SRI-Graph) that exploits the known position of a mobile manipulator for robust and accurate scene understanding. Compared to the state-of-the-art scene graph approaches, the proposed SRI-Graph captures not only the relationships between the objects, but also the relationships between the robot manipulator and objects with which it interacts. To improve the detection accuracy of spatial relationships, we leverage the 3D position of the mobile manipulator in addition to RGB images. The manipulator's ego information is crucial for a successful scene understanding when the relationships are visually uncertain. The proposed model is validated for a real-world 3D robot-assisted feeding task. We release a new dataset named 3DRF-Pos for training and validation. We also develop a tool, named LabelImg-Rel, as an extension of the open-sourced image annotation tool LabelImg for a convenient annotation in robot-environment interaction scenarios * . Our experimental results using the Movo platform show that SRI-Graph outperforms the state-of-the-art approach and improves detection accuracy by up to 9.83%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mcrood: Multi-Class Radar Out-Of-Distribution Detection

Mcrood: Multi-Class Radar Out-Of-Distribution Detection

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sabri Mustafa Kahya Muhammet Sami Yavuz Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Technical University of Munich School of Computation Information and Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Infineon Technologies AG

Out-of-distribution (OOD) detection has recently received special attention due to its critical role in safely deploying modern deep learning (DL) architectures. This work proposes a reconstruction-based multi-class OOD detector that operates on radar range doppler images (RDIs). The detector aims to classify any moving object other than a person sitting, standing, or walking as OOD. We also provide a simple yet effective pre-processing technique to detect minor human body movements like breathing. The simple idea is called respiration detector (RESPD) and eases the OOD detection, especially for human sitting and standing classes. On our dataset collected by 60GHz short-range FMCW Radar, we achieve AUROCs of 97.45%, 92.13%, and 96.58% for sitting, standing, and walking classes, respectively. We perform extensive experiments and show that our method outperforms state-of-the-art (SOTA) OOD detection methods. Also, our pipeline performs 24 times faster than the second-best method and is very suitable for real-time processing.

关键词： Legged locomotion Pipelines Neural networks Radar detection Detectors Signal processing Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Intelligent Vision-Assisted Obstacle Avoidance and Unknown Seasonal Products Navigation in Farmer's Market for the Visually Impaired

SSRN

引用

SSRN 2023年

作者： Liu, Mei Chen, Yunhua Djoulde, Aristide He, Mengfan Rao, Jinjun Giernacki, Wojciech Wang, Zhiming Chen, Jinbo Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China Institute of Robotics and Machine Intelligence Faculty of Control Robotics and Electrical Engineering Poznan University of Technology Piotrowo 3a Poznan60-965 Poland

Abstract: Shopping at a farmer's market is a considerable daily challenge for the visually impaired. General indoor obstacle avoidance and navigation algorithms are not fully applicable to the crowded and dynamic shopping environment of farmer's market. To overcome these challenges and provide precise assistance to visually impaired, this paper proposes an intelligent vision-assisted (IVA) algorithm for navigating narrow and crowded farmer's market aisles. The algorithm employs a pedestrian detection camera based on deep learning as the hardware to intelligently detect the type and number of pedestrians in front, and guides a navigation robot to adopt corresponding obstacle avoidance strategies in time according to the detection results. Different from general obstacle avoidance methods, IVA doesn't have issues of guiding robot to make frequent turns and change routes when avoiding obstacles in a crowded and narrow environment, making it more suitable for the visually impaired. Additionally, this paper proposes an unknown seasonal product navigation (USPN) algorithm for robots to automatically search for navigation information that has changed. When used in conjunction with a camera driven by deep learning, USPN successfully guided a navigation robot to identify the names and coordinates of newly listed products. Compared with general navigation algorithms, USPN can guide robots to update product information timely and intelligently. Experimental tests conducted in a farmer's market demonstrated that IVA is more intelligent and efficient than the dynamic window approach (DWA) in obstacle avoidance performance, and it is more suitable for guiding the visually impaired;furthermore, USPN successfully guides the robot to automatically acquire products information that changes with the seasons, and the acquired product categories and locations are precise. Particularly, IVA and USPN can be used as references when designing guide robots for use in public spaces like super

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Motor-Cognitive Effects of Virtual Reality Myoelectric Control Training

Motor-Cognitive Effects of Virtual Reality Myoelectric Contr...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： M. Issa T. Spiegeler Castañeda P. Capsi-Morales C. Piazza Department of Computer Engineering School of Computation Information and Technology Technical University of Munich Munich Germany Munich Institute of Robotics and Machine Intelligence Technical University of Munich Munich Germany

Learning the advanced functionalities of modern myoelectric prostheses can be challenging and highly cognitive demanding for naive users. While virtual reality (VR) has recently emerged as a promising tool for neurorehabilitation, it is important to consider also the cognitive load aspect of the training process, for a more realistic assessment of users’ capabilities. This study aims to investigate the correlation between functional performance and cognitive demand when learning a myoelectric control method in an immersive virtual reality environment for training and assessment. The developed virtual training environment simulated activities of daily living, while the assessments included standard tests, as well as a motor-cognitive dual-task methodology that combined both aspects. The study was conducted with 10 able-bodied participants, who controlled a virtual multi-grip prosthesis using a conventional myoelectric control strategy that requires muscle co-activation to switch between power and precision grasp. Performance in terms of functionalities, cognitive load, and user perception was assessed before and after training. Results show that VR training led to an immediate improvement in functionalities, enabling fast object manipulation, and highlighting the importance of including cognitive evaluation in the training progress.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees

Physics-Model-Regulated Deep Reinforcement Learning Towards ...

引用

IEEE Conference on Decision and Control

作者： Hongpeng Cao Yanbing Mao Lui Sha Marco Caccamo Hongpeng Cao is with School of Engineering and Design Technical University of Munich Munich Germany Yanbing Mao is with Engineering Technology Division Wayne State University Detroit MI USA Department of Computer Science University of Illinois at Urbana-Champaign Urbana IL USA School of Engineering and Design and Institute of Robotics and Machine Intelligence Technical University of Munich Munich Germany

Deep reinforcement learning (DRL) has demonstrated impressive success in solving complex control tasks by synthesizing control policies from data. However, the safety and stability of applying DRL to safety-critical systems remain a primary concern and challenging problem. To address the problem, we propose the Phy-DRL: a novel physics-model-regulated deep reinforcement learning framework. The Phy-DRL is novel in two architectural designs: a physics-model-regulated reward and residual control, which integrates physics-model-based control and data-driven control. The concurrent designs enable the Phy-DRL the mathematically provable safety and stability guarantees. Finally, the effectiveness of the Phy-DRL is validated by an inverted pendulum system. Additionally, the experimental results demonstrate that the Phy-DRL features remarkably accelerated training and enlarged reward.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HPF-SLAM: An Efficient Visual SLAM System Leveraging Hybrid Point Features

HPF-SLAM: An Efficient Visual SLAM System Leveraging Hybrid ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Xin Su Sebastian Eger Adam Misik Dong Yang Rastin Pries Eckehard Steinbach Department of Computer Engineering School of Computation Information and Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Chair of Media Technology Technical University of Munich Germany Siemens Technology Munich Germany Nokia Munich Germany

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Visual SLAM is an essential tool in diverse applications such as robot perception and extended reality, where feature-based methods are prevalent due to their accuracy and robustness. However, existing methods employ either hand-crafted or solely learnable point features and are thus limited by the feature attributes. In this paper, we propose incorporating hybrid point features efficiently into a single system. By integrating hand-crafted and learnable features, we seek to capitalize on their complementary attributes in both key-point identification and descriptor expressiveness. To this purpose, we design a pre-processing module, which includes extraction, inter-class processing, and post-processing of hybrid point features. We present an efficient matching approach to exclusively perform the data association within the same class of features. Moreover, we design a Hybrid Bag-of-Words (H-BoW) model to deal with hybrid point features in matching and loop-closure-detection. By integrating the proposed framework into a modern feature-based system, we introduce HPF-SLAM. We evaluate the system on EuRoC-MAV and TUM-RGBD benchmarks. The experimental results show that our method consistently surpasses the baseline at comparable speed.

关键词： Visualization Simultaneous localization and mapping Accuracy Extended reality Semantics Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CITR: A Coordinate-Invariant Task Representation for Robotic Manipulation

CITR: A Coordinate-Invariant Task Representation for Robotic...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Peter So Rafael I. Cabral Muchacho Robin Jeanne Kirschner Abdalla Swikir Luis Figueredo Fares J. Abu-Dakka Sami Haddadin Munich Institute of Robotics and Machine Intelligence TUM Germany Division of Robotics Perception and Learning KTH Royal Institute of Technology Sweden Department of Electrical and Electronic Engineering Omar Al-Mukhtar University (OMU) Libya School of Computer Science University of Nottingham UK Electronic and Informatics Department Faculty of Engineering Mondragon Unibertsitatea Spain

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

The basis for robotics skill learning is an adequate representation of manipulation tasks based on their physical properties. As manipulation tasks are inherently invariant to the choice of reference frame, an ideal task representation would also exhibit this property. Nevertheless, most robotic learning approaches use unprocessed, coordinate-dependent robot state data for learning new skills, thus inducing challenges regarding the interpretability and transferability of the learned *** this paper, we propose a transformation from spatial measurements to a coordinate-invariant feature space, based on the pairwise inner product of the input measurements. We describe and mathematically deduce the concept, establish the task fingerprints as an intuitive image-based representation, experimentally collect task fingerprints, and demonstrate the usage of the representation for task classification. This representation motivates further research on data-efficient and transferable learning methods for online manipulation task classification and task-level perception.

关键词： Learning systems Coordinate measuring machines Robot kinematics Taxonomy Fingerprint recognition Mathematical models Libraries

来源：评论

学校读者我要写书评

暂无评论

Deeper Introspective SLAM: How to Avoid Tracking Failures Over Longer Routes?

Deeper Introspective SLAM: How to Avoid Tracking Failures Ov...

引用

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

作者： Kanwal Naveed Muhammad Latif Anjum Wajahat Hussain Donghwan Lee Robotics & Machine Intelligence (ROMI) Lab School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology Islamabad Pakistan Reinforcement Learning Research Lab School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon South Korea

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Large scale active exploration has recently revealed limitations of visual SLAM’s tracking ability. Active view planning methods based on reinforcement learning have been proposed to improve visual tracking *** this work, we expose the limitations of deep reinforcement learning-based visual SLAM over longer routes. We demonstrate that additional modalities (depth, scene layout) offer little improvement. Furthermore, reward shaping is not the main reason behind the shortsightedness of the state-of-the-art visual SLAM tracker. We propose a novel video vision transformer-based architecture that improves the farsightedness of the visual tracker, which results in the completion of longer routes with efficient *** of 60 challenging routes, our approach manages to complete 56 routes, which is a three-fold improvement over the state-of-the-art active view mapping (DI-SLAM) baseline. Interestingly, ORB-SLAM3 was unable to complete a single route without tracking failure. Our code is available at https://***/w935spuz.

关键词： Visualization Simultaneous localization and mapping Codes Layout Transformers Deep reinforcement learning Robustness Planning Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Towards Safe Robot Use with Edged or Pointed Objects: A Surrogate Study Assembling a Human Hand Injury Protection Database

Towards Safe Robot Use with Edged or Pointed Objects: A Surr...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Robin Jeanne Kirschner Carina M. Micheler Yangcan Zhou Sebastian Siegner Mazin Hamad Claudio Glowalla Jan Neumann Nader Rajaei Rainer Burgkart Sami Haddadin Chair for Robotics and Systems Intelligence Munich Institute of Robotics and Machine Intelligence Technical University of Munich Munich Germany Department of Orthopaedics and Sports Orthopaedics Klinikum Rechts der Isar TUM School of Medicine Technical University of Munich Munich Germany Institute for Machine Tools and Industrial Management TUM School of Engineering and Design Technical University of Munich Garching Near Munich Germany Endoprothetikzentrum der Maximalversorgung BG Hospital Murnau Murnau Germany Department of Diagnostic and Interventional Radiology Klinikum Rechts der Isar TUM School of Medicine Technical University of Munich Munich Germany

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

The use of pointed or edged tools or objects is one of the most challenging aspects of today’s application of physical human-robot interaction (pHRI). One reason for this is that the severity of harm caused by such edged or pointed impactors is less well studied than for blunt impactors. Consequently, the standards specify well-reasoned force and pressure thresholds for blunt impactors and advise avoiding any edges and corners in contacts. Nevertheless, pointed or edged impactor geometries cannot be completely ruled out in real pHRI applications. For example, to allow edged or pointed tools such as screwdrivers near human operators, the knowledge of injury severity needs to be extended so that robot integrators can perform well-reasoned, time-efficient risk assessments. In this paper, we provide the initial datasets on injury prevention for the human hand based on drop tests with surrogates for the human hand, namely pig claws and chicken drumsticks. We then demonstrate the ease and efficiency of robot use using the dataset for contact on two examples. Finally, our experiments provide a set of injuries that may also be expected for human subjects under certain robot mass-velocity constellations in collisions. To extend this work, testing on human samples and a collaborative effort from research institutes worldwide is needed to create a comprehensive human injury avoidance database for any pHRI scenario and thus for safe pHRI applications including edged and pointed geometries.

关键词： Geometry Databases Collaboration Skin Collision avoidance Protection Injuries

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：