检索结果-内蒙古大学图书馆

Low-Level Control of a Quadrotor With deep Model-Based Reinforcement learning

IEEE robotics AND automation LETTERS 2019年第4期4卷 4224-4230页

作者： Lambert, Nathan O. Drewe, Daniel S. Yaconelli, Joseph Levine, Sergey Calandra, Roberto Pister, Kristofer S. J. Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA Univ Oregon Eugene OR 97403 USA Facebook AI Res Menlo Pk CA 94025 USA

Designing effective low-level robot controllers often entail platform-specific implementations that require manual heuristic parameter tuning, significant system knowledge, or long design times. With the rising number of robotic and mechatronic systems deployed across areas ranging from industrial automation to intelligent toys, the need for a general approach to generating low-level controllers is increasing. To address the challenge of rapidly generating low-level controllers, we argue for using model-based reinforcement learning (MBRL) trained on relatively small amounts of automatically generated (i.e., without system simulation) data. In this letter, we explore the capabilities of MBRL on a Crazyflie centimeter-scale quadrotor with rapid dynamics to predict and control at <= 50 Hz. To our knowledge, this is the first use of MBRL for controlled hover of a quadrotor using only on-board sensors, direct motor input signals, and no initial dynamics knowledge. Our controller leverages rapid simulation of a neural network forward dynamics model on a graphic processing unit enabled base station, which then transmits the best current action to the quadrotor firmware via radio. In our experiments, the quadrotor achieved hovering capability of up to 6 s with 3 min of experimental training data.

关键词： deep learning in robotics and automation aerial systems: mechanics and control

来源：评论

学校读者我要写书评

暂无评论

RSL-Net: Localising in Satellite Images From a Radar on the Ground

引用

IEEE robotics AND automation LETTERS 2020年第2期5卷 1087-1094页

作者： Tang, Tim Yuqing De Martini, Daniele Barnes, Dan Newman, Paul Univ Oxford Oxford Robot Inst Oxford OX1 2JD England

This letter is about localising a vehicle in an overhead image using FMCW radar mounted on a ground vehicle. FMCW radar offers extraordinary promise and efficacy for vehicle localisation. It is impervious to all weather types and lighting conditions. However the complexity of the interactions between millimetre radar wave and the physical environment makes it a challenging domain. Infrastructure-free large-scale radar-based localisation is in its infancy. Typically here a map is built and suitable techniques, compatible with the nature of sensor, are brought to bear. In this work we eschew the need for a radar-based map;instead we simply use an overhead image - a resource readily available everywhere. This letter introduces a method that not only naturally deals with the complexity of the signal type but does so in the context of cross modal processing.

关键词： Autonomous vehicle navigation deep learning in robotics and automation localization range sensing

来源：评论

学校读者我要写书评

暂无评论

learning to Segment Generic Handheld Objects Using Class-Agnostic deep Comparison and Segmentation Network

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 3844-3851页

作者： Chaudhary, Krishneel Wada, Kentaro Chen, Xiangyu Kimura, Kohei Okada, Kei Inaba, Masayuki Univ Tokyo Grad Sch Informat Sci & Technol JSK Lab Tokyo 1138656 Japan

learning unknown objects in the environment is important for detection and manipulation tasks. Prior to learning the unknown objects the ground-truth labels have to be provided. The data annotation or labeling can be achieved in a number of ways but the most widely used method is still manual annotation. Although manual annotation has shown superior performance, it limits robots' capabilities to known object instances and is also a time consuming task. This letter considers the aforementioned limitations and presents a method that allows robots to autonomously annotate objects from observations of human-object interactions. Specifically, we present a novel method that segments handheld objects in real-time using the class-agnostic deep comparison and segmentation network. The inputs to the network are the RGB-D data of known object template and a search space, and it outputs a pixel-wise label of the object and an objectness score. The score indicates the likelihood that the same object is present in both the inputs. The object template is manually initialized in the first frame and thereafter, the object is segmented and the template is updated online. The template is strategically updated using the likelihood score. The segmented object regions are accumulated as pseudo-ground-truth labels, which are used for object learning. The approach efficiently handles both rigid and highly deformable objects.

关键词： deep learning in robotics and automation visual tracking and segmentation

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Linear Motion Deblurring

引用

IEEE robotics AND automation LETTERS 2020年第2期5卷 2475-2482页

作者： Liu, Peidong Janai, Joel Pollefeys, Marc Sattler, Torsten Geiger, Andreas Swiss Fed Inst Technol Comp Vis & Geometry Grp Dept Comp Sci CH-8092 Zurich Switzerland Max Planck Inst Intelligent Syst Autonomous Vis Grp D-41296 Tubingen Germany Microsoft Mixed Real & Artificial Intelligence La CH-8001 Zurich Switzerland Chalmers Univ Technol Comp Vis & Med Image Anal Grp S-41296 Gothenburg Sweden

Motion blurry images challenge many computer vision algorithms, e.g., feature detection, motion estimation, or object recognition. deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this letter, we present a differentiable reblur model for self-supervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on sharp images for supervision. Our key insight is that motion cues obtained from consecutive images yield sufficient information to inform the deblurring task. We therefore formulate deblurring as an inverse rendering problem, taking into account the physical image formation process: we first predict two deblurred images from which we estimate the corresponding optical flow. Using these predictions, we re-render the blurred images and minimize the difference with respect to the original blurry inputs. We use both synthetic and real dataset for experimental evaluations. Our experiments demonstrate that self-supervised single image deblurring is really feasible and leads to visually compelling results. Both the code and datasets are available at https://***/ethliup/SelfDeblurhttps://***/ethliup/SelfDeblur.

关键词： Computer vision for automation deep learning in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

learning Navigation Behaviors End-to-End With AutoRL

引用

IEEE robotics AND automation LETTERS 2019年第2期4卷 2007-2014页

作者： Chiang, Hao-Tien Lewis Faust, Aleksandra Fiser, Marek Francis, Anthony Google AI Google Robot Mountain View CA 94043 USA

We learn end-to-end point-to-point and pathfollowing navigation behaviors that avoid moving obstacles. These policies receive noisy lidar observations and output robot linear and angular velocities. The policies are trained in small, static environments with AutoRL, an evolutionary automation layer around reinforcement learning (RL) that searches for a deep RL reward and neural network architecture with large-scale hyper-parameter optimization. AutoRL first finds a reward that maximizes task completion and then finds a neural network architecture that maximizes the cumulative of the found reward. Empirical evaluations, both in simulation and on-robot, show that AutoRL policies do not suffer from the catastrophic forgetfulness that plagues many other deep reinforcement learning algorithms, generalize to new environments and moving obstacles, are robust to sensor, actuator, and localization noise, and can serve as robust building blocks for larger navigation tasks. Our path-following and point-to-point policies are, respectively, 23% and 26% more successful than comparison methods across new environments.

关键词： Autonomous agents collision avoidance 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

Cross-Domain Motion Transfer via Safety-Aware Shared Latent Space Modeling

引用

IEEE robotics AND automation LETTERS 2020年第2期5卷 2634-2641页

作者： Choi, Sungjoon Kim, Joohyung Disney Res Glendale CA 91201 USA Univ Illinois Champaign IL 61820 USA

This letter presents a data-driven motion retargeting method with safety considerations. In particular, we focus on handling self-collisions while transferring poses between different domains. To this end, we first propose leveraged Wasserstein auto-encoders (LWAE) which leverage both positive and negative data where negative data consist of self-collided poses. Then, we extend this idea to multiple domains to have a shared latent space to perform motion retargeting. We also present an effective self-collision handling method based on solving inverse kinematics with augmented targets that is used to collect collision-free poses. The proposed method is extensively evaluated in a diverse set of motions from human subjects and an animation character where we show that incorporating negative data dramatically reduces self-collisions while preserving the quality of the original motion.

关键词： deep learning in robotics and automation motion and path planning collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Model for Trajectory Planning of Nonprehensile Manipulation Including Contact Model

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 3606-3613页

作者： Kutsuzawa, Kyo Sakaino, Sho Tsuji, Toshiaki Saitama Univ Grad Sch Sci & Engn Saitama 3388570 Japan Saitama Univ JST PRESTO Saitama 3388570 Japan

Nonprehensile manipulation is necessary for robots to operate in humans' daily lives. As nonprehensile manipulation should satisfy both kinematics and dynamics requirements simultaneously, it is difficult to manipulate objects along given paths. Previous studies have considered the problems with sequence-to-sequence models, which are neural networks for time-series conversion. However, they did not consider nonlinear contact models, such as friction models. When we train the seq2seq models using end-to-end backpropagation, training losses vanish owing to static friction. In this letter, we realize sequence-to-sequence models for trajectory planning of nonprehensile manipulation including contact models between the robots and target objects. This letter proposes a training curriculum that commences training without contact models to bring the seq2seq models outside of the gradient-vanishing zone. This letter discusses sliding manipulation, which includes a friction model between objects and tools, such as frying pans fixed onto the robots. We validated the proposed curriculum through a simulation. In addition, we observed that the trained seq2seq models could handle parameter fluctuations that did not exist during training.

关键词： deep learning in robotics and automation motion and path planning nonprehensile manipulation sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

learning Modular Robot Control Policies

引用

IEEE TRANSACTIONS ON robotics 2023年第5期39卷 4095-4113页

作者： Whitman, Julian Travers, Matthew Choset, Howie Carnegie Mellon Univ Robot Inst Pittsburgh PA 15213 USA

Modular robots can be rearranged into a new design, perhaps each day, to handle a wide variety of tasks by forming a customized robot for each new task. However, reconfiguring just the mechanism is not sufficient: each design also requires its own unique control policy. One could craft a policy from scratch for each new design, but such an approach is not scalable, especially given the large number of designs that can be generated from even a small set of modules. Instead, we create a modular policy framework where the policy structure is conditioned on the hardware arrangement, and use just one training process to create a policy that controls a wide variety of designs. Our approach leverages the fact that the kinematics of a modular robot can be represented as a design graph, with nodes as modules and edges as connections between them. Given a robot, its design graph is used to create a policy graph with the same structure, where each node contains a deep neural network, and modules of the same type share knowledge via shared parameters (e.g., all legs on a hexapod share the same network parameters). We developed a model-based reinforcement learning algorithm, interleaving model learning and trajectory optimization to train the policy. We show the modular policy generalizes to a large number of designs that were not seen during training without any additional learning. Finally, we demonstrate the policy controlling a variety of designs to locomote with both simulated and real robots.

关键词： Cellular and modular robots deep learning in robotics and automation legged robots model learning for control

来源：评论

学校读者我要写书评

暂无评论

iART: learning From Demonstration for Assisted Robotic Therapy Using LSTM

引用

IEEE robotics AND automation LETTERS 2020年第2期5卷 477-484页

作者： Pareek, Shrey Kesavadas, Thenkurussi Univ Illinois Dept Ind & Enterprise Syst Engn Champaign IL 61820 USA

In this letter, we present an intelligent Assistant for Robotic Therapy (iART), that provides robotic assistance during 3D trajectory tracking tasks. We propose a novel LSTM-based robot learning from demonstration (LfD) paradigm to mimic a therapist's assistance behavior. iART presents a trajectory agnostic LfD routine that can generalize learned behavior from a single trajectory to any 3D shape. Once the therapist's behavior has been learned, iART enables the patient to modify this behavior as per their preference. The system requires only a single demonstration of 2 minutes and exhibits a mean accuracy of 91.41% in predicting, and hence mimicking a therapist's assistance behavior. The system delivers stable assistance in realtime and successfully reproduces different types of assistance behaviors.

关键词： Rehabilitation robotics deep learning in robotics and automation learning from demonstration AI-based methods

来源：评论

学校读者我要写书评

暂无评论

Detect Globally, Label Locally: learning Accurate 6-DOF Object Pose Estimation by Joint Segmentation and Coordinate Regression

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 3960-3967页

作者： Nigam, Apurv Penate-Sanchez, Adrian Agapito, Lourdes UCL Dept Comp Sci London NW1 9HZ England ANI Technol Pvt Ltd Dehra Dun 248006 India Univ Oxford Oxford Robot Inst Oxford OX2 6NN England

Coordinate regression has established itself as one of the most successful current trends in model-based 6 degree of freedom (6-DOF) object pace estimation from a single image. The underlying idea is to train a system that can regress the three-dimensional coordinates of an object, given an input RGB or RGB-D image and known object geometry, followed by a robust procedure such as RANSAC to optimize the object pose. These coordinate regression based approaches exhibit state-of-the-art performance by using pixel-level cues to model the probability distribution of object parts within the image. However, they fail to capture global information at the object level to learn accurate foreground/background segmentation. In this letter, we show that combining global features for object segmentation and local features for coordinate regression results in pixel-accurate object boundary detections and consequently a substantial reduction in outliers and an increase in overall performance. We propose a deep architecture with an instance-level object segmentation network that exploits global image information for object/background segmentation and a pixel-level classification network for coordinate regression based on local features. We evaluate our approach on the standard ground-truth 6-DOF pose estimation benchmarks and show that our joint approach to accurate object segmentation and coordinate regression results in the state-of-the-art performance on both RGB and RGB-D 6-DOF pose estimation.

关键词： Object detection segmentation and categorization deep learning in robotics and automation

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：