检索结果-内蒙古大学图书馆

Mediterranean Electrotechnical Conference (MELECON)

作者： Diego Fernandez Prado Prashanth Ramachandrareddy Eckehard Steinbach Technical University of Munich / School of Computation Information and Technology / Chair of Media Technology and Munich Institute of Robotics and Machine Intelligence (MIRMI) Munich Germany

ISBN: (数字)9798350387025

ISBN: (纸本)9798350387032

Programming autonomous behavior in machines and robots traditionally requires a specific set of skills and knowledge. On the other hand, human experts can demonstrate the desired task even if they do not know how to program the necessary behavior in a machine or robot. The purpose of Learning from Demonstration (LfD) is to efficiently learn a desired behavior by imitating the teacher. LfD is considered a key technology for applications in manufacturing, elder care, and the service industry. These applications require efficient, intuitive ways to teach robots the motions they need to perform. In recent times there has been a renewed interest in robot teleoperation, since it allows workers to accomplish their tasks remotely from home office or anywhere in the world. Unfortunately, network conditions play a significant role in the stability of teleoperated systems, and factors such as delays or reduced bandwidth can be decisive in the successful completion of even the simplest tasks. In this work, we present a method to teach insertion skills from teleoperated demonstrations that combines visual and haptic information. Both streams of data are decoupled, which allows for easier provision of Quality of Service (QoS) under adverse network conditions. Additionally, a user study of the impact of bandwidth limitation on the visual part of the remote teaching is presented, where the results show that a reduction in bandwidth leads to increased demonstration time and lower accuracy. A weighting strategy to limit the harm of the network conditions is successfully applied, reducing the median error in the demonstrated insertion pose by approximately 20%.

关键词： Visualization Service robots Bandwidth Quality of service Programming Haptic interfaces Recording

来源：评论

学校读者我要写书评

暂无评论

ADAPTING LEARNED IMAGE CODECS TO SCREEN CONTENT VIA ADJUSTABLE TRANSFORMATIONS

arXiv

引用

arXiv 2024年

作者： Dogaroglu, H. Burak Koyuncu, A. Burakhan Boev, Atanas Alshina, Elena Steinbach, Eckehard School of Computation Information and Technology TU Munich Germany Huawei Munich Research Center Germany Munich Institute of Robotics and Machine Intelligence Germany

As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications. To improve the performance of LICs for screen content (SC) images without breaking backwards compatibility, we propose to introduce parameterized and invertible linear transformations into the coding pipeline without changing the underlying baseline codec's operation flow. We design two neural networks to act as prefilters and postfilters in our setup to increase the coding efficiency and help with the recovery from coding artifacts. Our end-to-end trained solution achieves up to 10% bitrate savings on SC compression compared to the baseline LICs while introducing only 1% extra parameters. Copyright © 2024, The Authors. All rights reserved.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Latent Action Priors for Locomotion with Deep Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Hausdörfer, Oliver von Rohr, Alexander Lefort, Éric Schoellig, Angela P. The Technical University of Munich Germany TUM School of Computation Information and Technology Department of Computer Engineering Learning Systems and Robotics Lab Germany Munich Institute of Robotics and Machine Intelligence Germany

Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of the learning algorithms, the resulting solutions are often brittle and appear unnatural. This is especially true for learning direct joint-level torque control, as inductive biases are difficult to integrate into the learning process. We propose an inductive bias for learning locomotion that is especially useful for torque control: latent actions learned from a small dataset of expert demonstrations. This prior allows the policy to directly leverage knowledge contained in the expert’s actions and facilitates more efficient exploration. We observe that the agent is not restricted to the reward levels of the demonstration, and performance in transfer tasks is improved significantly. Latent action priors combined with style rewards for imitation leads to a closer replication of the expert’s behavior. Videos and code are available at https://***/view/ latent-action-priors. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Control-Barrier-Aided Teleoperation with Visual-Inertial SLAM for Safe MAV Navigation in Complex Environments

Control-Barrier-Aided Teleoperation with Visual-Inertial SLA...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Siqi Zhou Sotiris Papatheodorou Stefan Leutenegger Angela P. Schoellig Learning Systems and Robotics Lab School of Computation Information and Technology Technical University of Munich Munich Institute of Robotics and Machine Intelligence (MIRMI) Smart Robotics Lab School of Computation Information and Technology Technical University of Munich Department of Computing Smart Robotics Lab Imperial College London

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In this paper, we consider a Micro Aerial Vehicle (MAV) system teleoperated by a non-expert and introduce a perceptive safety filter that leverages Control Barrier Functions (CBFs) in conjunction with Visual-Inertial Simultaneous Localization and Mapping (VI-SLAM) and dense 3D occupancy mapping to guarantee safe navigation in complex and unstructured environments. Our system relies solely on onboard IMU measurements, stereo infrared images, and depth images and autonomously corrects teleoperated inputs when they are deemed unsafe. We define a point in 3D space as unsafe if it satisfies either of two conditions: (i) it is occupied by an obstacle, or (ii) it remains unmapped. At each time step, an occupancy map of the environment is updated by the VI-SLAM by fusing the onboard measurements, and a CBF is constructed to parameterize the (un)safe region in the 3D space. Given the CBF and state feedback from the VI-SLAM module, a safety filter computes a certified reference that best matches the teleoperation input while satisfying the safety constraint encoded by the CBF. In contrast to existing perception-based safe control frameworks, we directly close the perception-action loop and demonstrate the full capability of safe control in combination with real-time VI-SLAM without any external infrastructure or prior knowledge of the environment. We verify the efficacy of the perceptive safety filter in real-time MAV experiments using exclusively onboard sensing and computation and show that the teleoperated MAV is able to safely navigate through unknown environments despite arbitrary inputs sent by the teleoperator.

关键词： Teleoperators State feedback Three-dimensional displays Simultaneous localization and mapping Navigation Real-time systems Time measurement

来源：评论

学校读者我要写书评

暂无评论

TReCiM: Lower Power and Temperature-Resilient Multibit 2FeFET-1T Compute-in-Memory Design 24

TReCiM: Lower Power and Temperature-Resilient Multibit 2FeFE...

引用

43rd International Conference on Computer-Aided Design, ICCAD 2024

作者： Zhou, Yifei Kämpfe, Thomas Ni, Kai Amrouch, Hussam Zhuo, Cheng Yin, Xunzhao Zhejiang University Hangzhou China Fraunhofer IPMS Dresden Germany Department of Electrical Engineering University of Notre Dame Notre Dame United States Technical University of Munich TUM School of Computation Information and Technology Munich Institute of Robotics and Machine Intelligence Munich Germany Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province China

ISBN: (纸本)9798400710773

Compute-in-memory (CiM) emerges as a promising solution to solve hardware challenges in artificial intelligence (AI) and the Internet of Things (IoT), particularly addressing the"memory wall" issue. By utilizing nonvolatile memory (NVM) devices in a crossbar structure, CiM efficiently accelerates multiply-accumulate (MAC) computations, the crucial operations in neural networks and other AI models. Among various NVM devices, Ferroelectric FET (FeFET) is particularly appealing for ultra-low-power CiM arrays due to its CMOS compatibility, voltage-driven write/read mechanisms and high ION/IOFF ratio. Moreover, subthreshold-operated FeFETs, which operate at scaling voltages in the subthreshold region, can further minimize the power consumption of CiM array. However, subthreshold-FeFETs are susceptible to temperature drift, resulting in computation accuracy degradation. Existing solutions exhibit weak temperature resilience at larger array size and only support 1-bit. In this paper, we propose TReCiM, an ultra-low-power temperature-resilient multibit 2FeFET-1T CiM design that reliably performs MAC operations in the subthreshold-FeFET region with temperature ranging from 0°C to 85°C at scale. We benchmark our design using NeuroSim framework in the context of VGG-8 neural network architecture running the CIFAR-10 dataset. Benchmarking results suggest that when considering temperature drift impact, our proposed TReCiM array achieves 91.31% accuracy, with 1.86% accuracy improvement compared to existing 1-bit 2T-1FeFET CiM array. Furthermore, our proposed design achieves 48.03 TOPS/W energy efficiency at system level, comparable to existing designs with smaller technology feature sizes. © 2024 Copyright is held by the owner/author(s).

关键词： MISFET devices

来源：评论

学校读者我要写书评

暂无评论

Informed Circular Fields for Global Reactive Obstacle Avoidance of Robotic Manipulators

arXiv

引用

arXiv 2022年

作者： Becker, Marvin Caspers, Philipp Hattendorf, Tom Lilge, Torsten Haddadin, Sami Müller, Matthias A. Institut of Automatic Control Leibniz University Hannover Germany Munich School of Robotics and Machine Intelligence and Robotics and System Intelligence Technical University Munich Germany

In this paper a global reactive motion planning framework for robotic manipulators in complex dynamic environments is presented. In particular, the circular field predictions (CFP) planner from Becker et al. (2021) is extended to ensure obstacle avoidance of the whole structure of a robotic manipulator. Towards this end, a motion planning framework is developed that leverages global information about promising avoidance directions from arbitrary configuration space motion planners, resulting in improved global trajectories while reactively avoiding dynamic obstacles and decreasing the required computational power. The resulting motion planning framework is tested in multiple simulations with complex and dynamic obstacles and demonstrates great potential compared to existing motion planning approaches. © 2022, CC BY.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

FARE: A Deep Learning-Based Framework for Radar-Based Face Recognition and Out-of-Distribution Detection

FARE: A Deep Learning-Based Framework for Radar-Based Face R...

引用

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

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

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this work, we propose a novel pipeline for face recognition and out-of-distribution (OOD) detection using shortrange FMCW radar. The proposed system utilizes RangeDoppler and micro Range-Doppler Images. The architecture features a primary path (PP) responsible for the classification of in-distribution (ID) faces, complemented by intermediate paths (IPs) dedicated to OOD detection. The network is trained in two stages: first, the PP is trained using triplet loss to optimize ID face classification. In the second stage, the PP is frozen, and the IPs—comprising simple linear autoen-coder networks—are trained specifically for OOD detection. Using our dataset generated with a 60 GHz FMCW radar, our method achieves an ID classification accuracy of 99.30% and an OOD detection AUROC of 96.91%.

关键词： Training Accuracy Face recognition Pipelines Radar detection Radar Smart homes Signal processing Reliability Speech processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Robotic Assistance for Human Activities through Human-Object Interaction Segment Prediction

Enhanced Robotic Assistance for Human Activities through Hum...

引用

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

作者： Yuankai Wu Rayene Messaoud Arne-Christoph Hildebrandt Marco Baldini Driton Salihu Constantin Patsch Eckehard Steinbach Chair of Media Technology and Munich Institute of Robotics and Machine Intelligence School of Computation Information and Technology Technical University of Munich Germany Mobile Robotics Department Asea Brown Boveri (ABB) Group

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Robotic assistance is a current research topic with high application value and multiple challenges. Assistive robots are used in various scenarios, such as production lines, operating tables, and elderly care. While providing effective assistance, most of the assistance tasks that current robots can perform are limited to predefined tasks. This limitation arises from the insufficiency of the current robot perception system to forecast future human activities. To address this issue, we propose a novel 2-stage robotic assistant for human activities through future human-object interaction (HOI) segment prediction. Unlike previous work focusing on predefined or short-term tasks, our robotic assistant can make predictions for future assistance according to human habits. In the first stage, we propose a visual-based human-object interaction segment prediction method to predict human activities, which enables the robotic system to infer human intention. Moreover, we define the robotic executable tasks as an interactive tuple to keep the robotic assistance normatively consistent with human activity. Meanwhile, a graph convolutional network with geometric features that can predict human-object interaction segments is proposed to provide target manipulation and target object for the assistive robot. In the second stage, we present a mobile task completion process including visual navigation, object localization and grasping. The perception stage is evaluated on the MPHOI dataset and custom-collected SPHOI dataset. Finally, we evaluate our comprehensive framework through real-time experimentation.

关键词： Location awareness Visualization Navigation Production Predictive models Assistive robots Real-time systems Older adults Robots Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Geometric Slosh-Free Tracking for Robotic Manipulators

Geometric Slosh-Free Tracking for Robotic Manipulators

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Jon Arrizabalaga Lukas Pries Riddhiman Laha Runkang Li Sami Haddadin Markus Ryll Autonomous Aerial Systems School of Engineering and Design Technical University of Munich Germany Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This work focuses on the agile transportation of liquids with robotic manipulators. In contrast to existing methods that are either computationally heavy, system/container specific or dependant on a singularity-prone pendulum model, we present a real-time slosh-free tracking technique. This method solely requires the reference trajectory and the robot’s kinematic constraints to output kinematically feasible joint space commands. The crucial element underlying this approach consists on mimicking the end-effector’s motion through a virtual quadrotor, which is inherently slosh-free and differentially flat, thereby allowing us to calculate a slosh-free reference orientation. Through the utilization of a cascaded proportional-derivative (PD) controller, this slosh-free reference is transformed into task space acceleration commands, which, following the resolution of a Quadratic Program (QP) based on Resolved Acceleration Control (RAC), are translated into a feasible joint configuration. The validity of the proposed approach is demonstrated by simulated and real-world experiments on a 7 DoF Franka Emika Panda robot.

关键词： Liquids Tracking Transportation Kinematics Aerospace electronics Real-time systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

HypCAD: Geometry-Enhanced Hyperbolic Contrastive Learning for CAD Model Retrieval

HypCAD: Geometry-Enhanced Hyperbolic Contrastive Learning fo...

引用

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

作者： Adam Misik Driton Salihu Xin Su Heike Brock Eckehard Steinbach Siemens Technology Munich Germany School of Computation Information and Technology Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich Munich Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Retrieving CAD models for real-world object scans enhances object-level mapping, providing a nuanced spatial understanding crucial for precise interactions in robotics or mixed reality. Commonly, CAD model retrieval is performed by matching features learned in Euclidean space. However, learning discriminative features in Euclidean space faces significant challenges, primarily due to its flat nature and the wide variety of CAD models with different levels of detail. To address the limitations of Euclidean space and improve CAD model retrieval, this paper introduces HypCAD, a contrastive learning framework in hyperbolic space. We present a novel geometry-enhanced hyperbolic distance and utilize a three-component contrastive learning loss to learn hyperbolic feature representations for the CAD model retrieval task. We demonstrate HypCAD’s superior retrieval accuracy through comparisons with baseline contrastive learning methods on both the synthetic ShapeNet dataset and the real-world Scan2CAD dataset.

关键词： Solid modeling Accuracy Mixed reality Contrastive learning Signal processing Feature extraction Acoustics Speech processing Robots Faces

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：