检索结果-内蒙古大学图书馆

LVDiffusor: Distilling Functional Rearrangement Priors From Large Models Into Diffusor

IEEE robotics AND automation LETTERS 2024年第10期9卷 8258-8265页

作者： Zeng, Yiming Wu, Mingdong Yang, Long Zhang, Jiyao Ding, Hao Cheng, Hui Dong, Hao Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510275 Peoples R China Peking Univ Sch CS Hyperplane Lab Beijing 100871 Peoples R China Peking Univ Natl Key Lab Multimedia Informat Proc Beijing 100871 Peoples R China Beijing Acad Artificial Intelligence Beijing 100084 Peoples R China

Object rearrangement, a fundamental challenge in robotics, demands versatile strategies to handle diverse objects, configurations, and functional needs. To achieve this, the AI robot needs to learn functional rearrangement priors to specify precise goals that meet the functional requirements. Previous methods typically learn such priors from either laborious human annotations or manually designed heuristics, which limits scalability and generalization. In this letter, we propose a novel approach that leverages large models to distill functional rearrangement priors. Specifically, our approach collects diverse arrangement examples using both LLMs and VLMs and then distills the examples into a diffusion model. During test time, the learned diffusion model is conditioned on the initial configuration and guides the positioning of objects to meet functional requirements. In this way, we balance zero-shot generalization with time efficiency. Extensive experiments in multiple domains, including real-world scenarios, demonstrate the effectiveness of our approach in generating compatible goals for object rearrangement tasks, significantly outperforming baseline methods.

关键词： AI-enabled robotics deep learning methods big data in robotics and automation AI-enabled robotics deep learning methods big data in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Language Models as Zero-Shot Trajectory Generators

引用

IEEE robotics AND automation LETTERS 2024年第7期9卷 6728-6735页

作者： Kwon, Teyun Di Palo, Norman Johns, Edward Imperial Coll London Robot Learning Lab London SW7 2AZ England

Large Language Models (LLMs) have recently shown promise as high-level planners for robots when given access to a selection of low-level skills. However, it is often assumed that LLMs do not possess sufficient knowledge to be used for the low-level trajectories themselves. In this work, we address this assumption thoroughly, and investigate if an LLM (GPT-4) can directly predict a dense sequence of end-effector poses for manipulation tasks, when given access to only object detection and segmentation vision models. We designed a single, task-agnostic prompt, without any in-context examples, motion primitives, or external trajectory optimisers. Then we studied how well it can perform across 30 real-world language-based tasks, such as "open the bottle cap" and "wipe the plate with the sponge", and we investigated which design choices in this prompt are the most important. Our conclusions raise the assumed limit of LLMs for robotics, and we reveal for the first time that LLMs do indeed possess an understanding of low-level robot control sufficient for a range of common tasks, and that they can additionally detect failures and then re-plan trajectories accordingly.

关键词： Task analysis Robots Trajectory End effectors Codes Robot kinematics Object detection AI-based methods big data in robotics and automation deep learning in grasping and manipulation

来源：评论

学校读者我要写书评

暂无评论

DALL-E-Bot: Introducing Web-Scale Diffusion Models to robotics

引用

IEEE robotics AND automation LETTERS 2023年第7期8卷 3956-3963页

作者： Kapelyukh, Ivan Vosylius, Vitalis Johns, Edward Imperial Coll London Robot Learning Lab London SW7 2AZ England Imperial Coll London Dyson Robot Lab London SW7 2AZ England

We introduce the first work to explore web-scale diffusion models for robotics. DALL-E-Bot enables a robot to rearrange objects in a scene, by first inferring a text description of those objects, then generating an image representing a natural, human-like arrangement of those objects, and finally physically arranging the objects according to that goal image. We show that this is possible zero-shot using DALL-E, without needing any further example arrangements, data collection, or training. DALL-E-Bot is fully autonomous and is not restricted to a pre-defined set of objects or scenes, thanks to DALL-E's web-scale pre-training. Encouraging real-world results, with both human studies and objective metrics, show that integrating web-scale diffusion models into robotics pipelines is a promising direction for scalable, unsupervised robot learning.

关键词： AI-based methods big data in robotics and automation deep learning in grasping and manipulation

来源：评论

学校读者我要写书评

暂无评论

A Distributed Framework for Knowledge-Driven Root-Cause Analysis on Evolving Alarm data-An Industrial Case Study

引用

IEEE robotics AND automation LETTERS 2023年第6期8卷 3732-3739页

作者： Wilch, Jan Vogel-Heuser, Birgit Mager, Jens Cendelin, Rostislav Fett, Thomas Hsieh, Yu-Ming Cheng, Fan-Tien Tech Univ Munich Inst Automat & Informat Syst D-85748 Garching Germany Reifenhauser Reicofil GmbH Co KG D-53844 Troisdorf Germany Natl Cheng Kung Univ Acad Innovat Semicond & Sustainable Mfg Tainan 701401 Taiwan Natl Cheng Kung Univ Inst Mfg Informat & Syst Tainan 701401 Taiwan

Root-cause Analysis (RCA) of alarms is a well-established research area in automated Production Systems (aPS). Many RCA algorithms have been proposed and successfully evaluated and new ones are being developed. Recently, researchers focus on the incorporation of formalized information about the technical process in the analysis to gather further evidence for common root causes. In industrial applications, alarm data are usually preprocessed to accommodate for use case-specific properties and prepare subsequent analysis steps. Consequently, this letter proposes a generalized RCA framework, for which an arbitrary number of preprocessing, data-driven RCA, and postprocessing algorithms can be selected, to support varying use cases. The framework was successfully evaluated in an industrial case study, using 1.8 million alarms recorded over 450 days from an industrial nonwoven production plant and analyzed using formalized information from process documentation and expert interviews. Seven preprocessing algorithms, one data-driven RCA algorithm, and nine postprocessing algorithms typical for continuous and hybrid technical processes were realized in an otherwise entirely use case-agnostic implementation.

关键词： Manufacturing Computer architecture Cloud computing Reliability Production systems Process control Manuals Software architecture for robotic and automation big data in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Variable Rate Compression for Raw 3D Point Clouds 39

Variable Rate Compression for Raw 3D Point Clouds

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Al Muzaddid, Md Ahmed Beksi, William J. Univ Texas Arlington Dept Comp Sci & Engn Arlington TX 76019 USA

ISBN: (纸本)9781728196817

In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data. The majority of learning-based point cloud compression methods work on a downsampled representation of the data. Moreover, many existing techniques require training multiple networks for different compression rates to generate consolidated point clouds of varying quality. In contrast, our network is capable of explicitly processing point clouds and generating a compressed description at a comprehensive range of bitrates. Furthermore, our approach ensures that there is no loss of information as a result of the voxelization process and the density of the point cloud does not affect the encoder/decoder performance. An extensive experimental evaluation shows that our model obtains state-of-the-art results, it is computationally efficient, and it can work directly with point cloud data thus avoiding an expensive voxelized representation.

关键词： RGB-D Perception Deep Learning for Visual Perception big data in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

LaND: Learning to Navigate From Disengagements

引用

IEEE robotics AND automation LETTERS 2021年第2期6卷 1872-1879页

作者： Kahn, Gregory Abbeel, Pieter Levine, Sergey Univ Calif Berkeley Berkeley CA 94710 USA

Consistently testing autonomous mobile robots in real world scenarios is a necessary aspect of developing autonomous navigation systems. Each time the human safety monitor disengages the robot's autonomy system due to the robot performing an undesirable maneuver, the autonomy developers gain insight into how to improve the autonomy system. However, we believe that these disengagements not only show where the system fails, which is useful for troubleshooting, but also provide a direct learning signal by which the robot can learn to navigate. We present a reinforcement learning approach for learning to navigate from disengagements, or LaND. LaND learns a neural network model that predicts which actions lead to disengagements given the current sensory observation, and then at test time plans and executes actions that avoid disengagements. Our results demonstrate LaND can successfully learn to navigate in diverse, real world sidewalk environments, outperforming both imitation learning and reinforcement learning approaches. Videos, code, and other material are available on our website https://***/view/sidewalk-learning.

关键词： big data in robotics and automation field robots machine learning for robot control

来源：评论

学校读者我要写书评

暂无评论

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

引用

IEEE robotics AND automation LETTERS 2021年第2期6卷 1312-1319页

作者： Kahn, Gregory Abbeel, Pieter Levine, Sergey Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94710 USA

Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can he insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns about physical navigational affordances from experience. Our reinforcement learning approach, which we call BADGR , is an end-to-end learning-based mobile robot navigation system that can be trained with autonomously-labeled off-policy data gathered in real-world environments, without any simulation or human supervision. BADGR can navigate in real-world urban and off-road environments with geometrically distracting obstacles. It can also incorporate terrain preferences, generalize to novel environments, and continue to improve autonomously by gathering more data. Videos, code, and other supplemental material are available on our website https://***/view/badgr

关键词： big data in robotics and automation reinforcement learning autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Vision Perception-based Adaptive Pushing Assisted Grasping Network for Dense Clutters

Vision Perception-based Adaptive Pushing Assisted Grasping N...

引用

第43届中国控制会议

作者： Xinqi Liu Runqi Chai Shuo Wang Senchun Chai Yuanqing Xia State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of Sciences

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

During the execution of a robotic grasping task,the task may fail due to the close proximity of multiple objects if grasping is the only motion ***-prehensile manipulations,such as pushing,can be used to rearrange objects and benefit *** pushing actions with different speeds,distances,and routines may result in better *** this study,we propose a vision perception-based Adaptive Pushing Assisted Grasping Network(APAGN) system for generating a sequence of actions that includes grasping and adaptive *** can perceive the scene and then predict the locations of objects after an adaptive push,which adjusts the force and direction of pushing based on expected *** achieve a more efficient calculation,an Action Selector of APAGN is designed to choose the object with the highest expected outcome before making a *** value of pushing actions is estimated based on how they benefit grasping,which breaks the limitation of manually designed *** show that APAGN might achieve higher action efficiency than baseline methods,especially in cluttered environments.

关键词： Reinforcement Learning Vision Perception big data in robotics and automation robotics Control

来源：评论

学校读者我要写书评

暂无评论

Long-Short Term Spatiotemporal Tensor Prediction for Passenger Flow Profile

引用

IEEE robotics AND automation LETTERS 2020年第4期5卷 5010-5017页

作者： Li, Ziyue Yan, Hao Zhang, Chen Tsung, Fugee Hong Kong Univ Sci & Technol Dept Ind Engn & Decis Analyt Hong Kong Peoples R China Arizona State Univ Sch Comp Informat & Decis Syst Engn Tempe AZ 85281 USA Tsinghua Univ Ind Engn Beijing 100084 Peoples R China

Spatiotemporal data are very common in many applications, such as manufacturing systems and transportation systems. Given the intrinsic complex spatial and temporal correlations of such data, short-term and long-term prediction for spatiotemporal data is often very challenging. Most of the traditional statistical models fail to preserve innate features in data alongside their complex correlations. In this paper, we focus on a tensor-based prediction method and propose several practical techniques to improve both long-term and short-term prediction accuracy. For long-term prediction, we propose the "tensor decomposition + 2-Dimensional Auto-Regressive Moving Average (2D-ARMA)" model, and an effective way to update prediction in real-time;For short-term prediction, we propose to conduct tensor completion based on tensor clustering to avoid oversimplification and ensure accuracy. A case study based on the metro passenger flow data is conducted to demonstrate the improved performance.

关键词： Intelligent transportation system probability and statistical methods big data in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor data

引用

IEEE robotics AND automation LETTERS 2020年第2期5卷 3509-3516页

作者： Liu, Boyi Wang, Lujia Liu, Ming Xu, Cheng-Zhong Chinese Acad Sci Shenzhen Inst Adv Technol Cloud Comp Lab Shenzhen 518000 Peoples R China Univ Chinese Acad Sci Shenzhen 518000 Peoples R China Hong Kong Univ Sci & Technol Dept ECE Hong Kong Peoples R China Univ Macau Macau 999078 Peoples R China

Humans are capable of learning a new behavior by observing others to perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So, how can robots achieve this? To address the issue, we present a novel framework named FIL. It provides a heterogeneous knowledge fusion mechanism for cloud robotic systems. Then, a knowledge fusion algorithm in FIL is proposed. It enables the cloud to fuse heterogeneous knowledge from local robots and generate guide models for robots with service requests. After that, we introduce a knowledge transfer scheme to facilitate local robots acquiring knowledge from the cloud. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning in accuracy and efficiency. Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a self-driving task for robots (cars). The experimental results demonstrate that the shared model generated by FIL increases imitation learning efficiency of local robots in cloud robotic systems.

关键词： Cloud computing Robot sensing systems Task analysis Fuses Microstrip Computational modeling big data in robotics and automation deep learning in robotics and automation motion and path planning

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

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

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：