检索结果-内蒙古大学图书馆

Motion Switching With Sensory and Instruction Signals by Designing Dynamical Systems Using deep Neural Network

IEEE robotics AND automation LETTERS 2018年第4期3卷 3481-3488页

作者： Suzuki, Kanata Mori, Hiroki Ogata, Tetsuya Fujitsu Labs Ltd Artificial Intelligence Labs Kawasaki Kanagawa 2118588 Japan Waseda Univ Sch Fundamental Sci & Engn Dept Intermedia Art & Sci Tokyo 5650871 Japan Natl Inst Adv Ind Sci & Technol Artificial Intelligence Res Ctr Tokyo 1350064 Japan

To ensure that a robot is able to accomplish an extensive range of tasks, it is necessary to achieve a flexible combination of multiple behaviors. This is because the design of task motions suited to each situation would become increasingly difficult as the number of situations and the types of tasks performed by them increase. To handle the switching and combination of multiple behaviors, we propose a method to design dynamical systems based on point attractors that accept (i) "instruction signals" for instruction driven switching We incorporate the (ii) "instruction phase" to form a point attractor and divide the target task into multiple sub tasks. By forming an instruction phase that consists of point attractors, the model embeds a subtask in the form of trajectory dynamics that can be manipulated using sensory and instruction signals. Our model comprises two deep neural networks: A convolutional autoencoder and a multiple time-scale recurrent neural network. In this study, we apply the proposed method to manipulate soft materials. To evaluate our model, we design a cloth-folding task that consists of four subtasks and three patterns of instruction signals, which indicate the direction of motion. The results depict that the robot can perform the required task by combining subtasks based on sensory and instruction signals. And, our model determined the relations among these signals using its internal dynamics.

关键词： deep learning in robotics and automation Al-based methods humanoid robots

来源：评论

学校读者我要写书评

暂无评论

3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 3145-3152页

作者： Ben-Shabat, Yizhak Lindenbaum, Michael Fischer, Anath Techion Israel Inst Technol Dept Mech Engn IL-3200003 Haifa Israel Techion Israel Inst Technol Dept Comp Sci IL-3200003 Haifa Israel

Modern robotic systems are often equipped with a direct three-dimensional (3-D) data acquisition device, e.g., LiDAR, which provides a rich 3-D point cloud representation of the surroundings. This representation is commonly used for obstacle avoidance and mapping. Here, we propose a new approach for using point clouds for another critical robotic capability, semantic understanding of the environment (i.e., object classification). Convolutional neural networks (CNNs), that perform extremely well for object classification in 2-D images, are not easily extendible to 3-D point clouds analysis. It is not straightforward due to point clouds' irregular format and a varying number of points. The common solution of transforming the point cloud data into a 3-D voxel grid needs to address severe accuracy versus memory size tradeoffs. In this letter, we propose a novel, intuitively interpretable, 3-D point cloud representation called 3-D modified Fisher vectors. Our representation is hybrid as it combines a coarse discrete grid structure with continuous generalized Fisher vectors. Using the grid enables us to design a new CNN architecture for real-time point cloud classification. In a series of performance analysis experiments, we demonstrate competitive results or even better than state of the art on challenging benchmark datasets while maintaining robustness to various data corruptions.

关键词： deep learning in robotics and automation recognition computer vision for transportation computer vision for other robotic applications

来源：评论

学校读者我要写书评

暂无评论

GapFlyt: Active Vision Based Minimalist Structure-Less Gap Detection For Quadrotor Flight

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 2799-2806页

作者： Sanket, Nitin J. Singh, Chahat deep Ganguly, Kanishka Fermueller, Cornelia Aloimonos, Yiannis Univ Maryland Inst Adv Comp Studies College Pk MD 20742 USA

Although quadrotors, and aerial robots in general, are inherently active agents, their perceptual capabilities in literature so far have been mostly passive in nature. Researchers and practitioners today use traditional computer vision algorithms with the aim of building a representation of general applicability: a 3-D reconstruction of the scene. Using this representation, planning tasks are constructed and accomplished to allow the quadrotor to demonstrate autonomous behavior. These methods are inefficient as they are not task driven and such methodologies are not utilized by flying insects and birds. Such agents have been solving the problem of navigation and complex control for ages without the need to build a 3-D map and are highly task driven. In this letter, we propose this framework of bioinspired perceptual design for quadrotors. We use this philosophy to design a minimalist sensorimotor framework for a quadrotor to fly through unknown gaps without an explicit 3-D reconstruction of the scene using only a monocular camera and onboard sensing. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with different settings and window shapes, achieving a success rate of 85% at 2.5 ms(-1) even with a minimum tolerance of just 5 cm. To best of our knowledge, this is the first letter that addresses the problem of gap detection of an unknown shape and location with a monocular camera and onboard sensing.

关键词： Active vision gap detection quadrotor visual servoing deep learning in robotics and automation optical flow tracking collision avoidance computer vision for automation aerial systems: perception and autonomy visual tracking and visual-based navigation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised deep Homography: A Fast and Robust Homography Estimation Model

引用

IEEE robotics AND automation LETTERS 2018年第3期3卷 2346-2353页

作者： Ty Nguyen Chen, Steven W. Shivakumar, Shreyas S. Taylor, Camillo Jose Kumar, Vijay Univ Penn Gen Robot Automat Sensing & Percept Lab Philadelphia PA 19104 USA

Homography estimation between multiple aerial images can provide relative pose estimation for collaborative autonomous exploration and monitoring. The usage on a robotic system requires a fast and robust homography estimation algorithm. In this letter, we propose an unsupervised learning algorithm that trains a deep convolutional neural network to estimate planar homographies. We compare the proposed algorithm to traditional-feature-based and direct methods, as well as a corresponding supervised learning algorithm. Our empirical results demonstrate that compared to traditional approaches, the unsupervised algorithm achieves faster inference speed, while maintaining comparable or better accuracy and robustness to illumination variation. In addition, our unsupervised method has superior adaptability and performance compared to the corresponding supervised deep learning method. Our image dataset and a Tensorflow implementation of our work are available at https://***/tynguyen/unsuperviseddeepHomographyRAL2018.

关键词： Computer vision for automation deep learning in robotics and automation computer vision for other robotic applications image alignment deep homography

来源：评论

学校读者我要写书评

暂无评论

Re³: Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects

引用

IEEE robotics AND automation LETTERS 2018年第2期3卷 788-795页

作者： Gordon, Daniel Farhadi, Ali Fox, Dieter Univ Washington Paul G Allen Sch Comp Sci Seattle WA 98195 USA Allen Inst Artificial Intelligence Seattle WA 98103 USA

Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time. A tracker must be able to modify its underlying model and adapt to new observations. We present Re-3, a real-time deep object tracker capable of incorporating temporal information into its model. Rather than focusing on a limited set of objects or training a model at test-time to track a specific instance, we pretrain our generic tracker on a large variety of objects and efficiently update on the fly;Re-3 simultaneously tracks and updates the appearance model with a single forward pass. This lightweight model is capable of tracking objects at 150 FPS while attaining competitive results on challenging benchmarks. We also show that our method handles temporary occlusion better than other comparable trackers using experiments that directly measure performance on sequences with occlusion.

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

来源：评论

学校读者我要写书评

暂无评论

More Than a Feeling: learning to Grasp and Regrasp Using Vision and Touch

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 3300-3307页

作者： Calandra, Roberto Owens, Andrew Jayaraman, Dinesh Lin, Justin Yuan, Wenzhen Malik, Jitendra Adelson, Edward H. Levine, Sergey Univ Calif Dept Elect Engn & Comp Sci Berkeley CA 94720 USA MIT 77 Massachusetts Ave Cambridge MA 02139 USA

For humans, the process of grasping an object relies heavily on rich tactile feedback. Most recent robotic grasping work, however, has been based only on visual input, and thus cannot easily benefit from feedback after initiating contact. In this letter, we investigate how a robot can learn to use tactile information to iteratively and efficiently adjust its grasp. To this end, we propose an end-to-end action-conditional model that learns regrasping policies from raw visuo-tactile data. This model-a deep, multimodal convolutional network-predicts the outcome of a candidate grasp adjustment, and then executes a grasp by iteratively selecting the most promising actions. Our approach requires neither calibration of the tactile sensors nor any analytical modeling of contact forces, thus reducing the engineering effort required to obtain efficient grasping policies. We train our model with data from about 6450 grasping trials on a two-finger gripper equipped with GelSight high-resolution tactile sensors on each finger. Across extensive experiments, our approach outperforms a variety of baselines at 1) estimating grasp adjustment outcomes, 2) selecting efficient grasp adjustments for quick grasping, and 3) reducing the amount of force applied at the fingers, while maintaining competitive performance. Finally, we study the choices made by our model and show that it has successfully acquired useful and interpretable grasping behaviors.

关键词： deep learning in robotics and automation grasping perception for grasping and manipulation force and tactile sensing

来源：评论

学校读者我要写书评

暂无评论

Sample Efficient learning of Path Following and Obstacle Avoidance Behavior for Quadrotors

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 3852-3859页

作者： Stevsic, Stefan Nageli, Tobias Alonso-Mora, Javier Hilliges, Otmar Swiss Fed Inst Technol Adv Interact Technol Lab Dept Comp Sci CH-8092 Zurich Switzerland Delft Univ Technol Dept Cognit Robot NL-2628 CD Delft Netherlands

In this letter, we propose an algorithm for the training of neural network control policies for quadrotors. The learned control policy computes control commands directly from sensor inputs and is, hence, computationally efficient. An imitation learning algorithm produces a policy that reproduces the behavior of a supervisor. The supervisor provides demonstrations of path following and collision avoidance maneuvers. Due to the generalization ability of neural networks, the resulting policy performs local collision avoidance, while following a global reference path. The algorithm uses a time-free model-predictive path-following controller as a supervisor. The controller generates demonstrations by following few example paths. This enables an easy-to-implement learning algorithm that is robust to errors of the model used in the model-predictive controller. The policy is trained on the real quadrotor, which requires collision-free exploration around the example path. An adapted version of the supervisor is used to enable exploration. Thus, the policy can be trained from a relatively small number of examples on the real quadrotor, making the training sample efficient.

关键词： Collision avoidance deep learning in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

How to Train a CAT: learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change

引用

IEEE robotics AND automation LETTERS 2018年第3期3卷 2447-2454页

作者： Clement, Lee Kelly, Jonathan Univ Toronto Inst Aerosp Studies Space & Terr Autonomous Robot Syst Lab Toronto ON M3H 5T6 Canada

Direct visual localization has recently enjoyed a resurgence in popularity with the increasing availability of cheap mobile computing power. The competitive accuracy and robustness of these algorithms compared to state-of-the-art feature-based methods, as well as their natural ability to yield dense maps, makes them an appealing choice for a variety of mobile robotics applications. However, direct methods remain brittle in the face of appearance change due to their underlying assumption of photometric consistency, which is commonly violated in practice. In this letter, we propose to mitigate this problem by training deep convolutional encoder-decoder models to transform images of a scene such that they correspond to a previously seen canonical appearance. We validate our method in multiple environments and illumination conditions using high-fidelity synthetic RGB-D datasets, and integrate the trained models into a direct visual localization pipeline, yielding improvements in visual odometry accuracy through time-varying illumination conditions, as well as improved metric relocalization performance under illumination change, where conventional methods normally fail. We further provide a preliminary investigation of transfer learning from synthetic to real environments in a localization context.

关键词： deep learning in robotics and automation visual learning visual-based navigation localization

来源：评论

学校读者我要写书评

暂无评论

Geometric Correspondence Network for Camera Motion Estimation

引用

IEEE robotics AND automation LETTERS 2018年第2期3卷 1010-1017页

作者： Tang, Jiexiong Folkesson, John Jensfelt, Patric KTH Royal Inst Technol Ctr Autonomous Syst SE-10044 Stockholm Sweden

In this paper, we propose a new learning scheme for generating geometric correspondences to be used for visual odometry. A convolutional neural network (CNN) combined with a recurrent neural network (RNN) are trained together to detect the location of keypoints as well as to generate corresponding descriptors in one unified structure. The network is optimized by warping points from source frame to reference frame, with a rigid body transform. Essentially, learning from warping. The overall training is focused on movements of the camera rather than movements within the image, which leads to better consistency in the matching and ultimately better motion estimation. Experimental results show that the proposed method achieves better results than both related deep learning and hand crafted methods. Furthermore, as a demonstration of the promise of our method we use a naive SLAM implementation based on these keypoints and get a performance on par with ORB-SLAM.

关键词： Visual-based navigation SLAM deep learning in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

VLocNet++: deep Multitask learning for Semantic Visual Localization and Odometry

引用

IEEE robotics AND automation LETTERS 2018年第4期3卷 4407-4414页

作者： Radwan, Noha Valada, Abhinav Burgard, Wolfram Univ Freiburg Dept Comp Sci D-79110 Freiburg Germany

Semantic understanding and localization are fundamental enablers of robot autonomy that have been tackled as disjoint problems for the most part. While deep learning has enabled recent breakthroughs across a wide spectrum of scene understanding tasks, its applicability to state estimation tasks has been limited due to the direct formulation that renders it incapable of encoding scene-specific constrains. In this letter, we propose the VLocNet++ architecture that employs a multitask learning approach to exploit the inter-task relationship between learning semantics, regressing 6-DoF global pose and odometry, for the mutual benefit of each of these tasks. Our network overcomes the aforementioned limitation by simultaneously embedding geometric and semantic knowledge of the world into the pose regression network. We propose a novel adaptive weighted fusion layer to aggregate motion-specific temporal information and to fuse semantic features into the localization stream based on region activations. Furthermore, we propose a self-supervised warping technique that uses the relative motion to warp intermediate network representations in the segmentation stream for learning consistent semantics. Finally, we introduce a first-of-a-kind urban outdoor localization dataset with pixel-level semantic labels and multiple loops for training deep networks. Extensive experiments on the challenging Microsoft 7-Scenes benchmark and our deepLoc dataset demonstrate that our approach exceeds the state-of-the-art outperforming local feature-based methods while simultaneously performing multiple tasks and exhibiting substantial robustness in challenging scenarios.

关键词： deep learning in robotics and automation visual learning localization

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：