2012 IEEE International Conference on Robotics and Automation最新文献_第10页

Sparse Spatial Coding: A novel approach for efficient and accurate object recognition 稀疏空间编码:一种高效、准确的目标识别新方法

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6224785

Gabriel L. Oliveira, Erickson R. Nascimento, A. W. Vieira, M. Campos

{"title":"Sparse Spatial Coding: A novel approach for efficient and accurate object recognition","authors":"Gabriel L. Oliveira, Erickson R. Nascimento, A. W. Vieira, M. Campos","doi":"10.1109/ICRA.2012.6224785","DOIUrl":"https://doi.org/10.1109/ICRA.2012.6224785","url":null,"abstract":"Successful state-of-the-art object recognition techniques from images have been based on powerful methods, such as sparse representation, in order to replace the also popular vector quantization (VQ) approach. Recently, sparse coding, which is characterized by representing a signal in a sparse space, has raised the bar on several object recognition benchmarks. However, one serious drawback of sparse space based methods is that similar local features can be quantized into different visual words. We present in this paper a new method, called Sparse Spatial Coding (SSC), which combines a sparse coding dictionary learning, a spatial constraint coding stage and an online classification method to improve object recognition. An efficient new off-line classification algorithm is also presented. We overcome the problem of techniques which make use of sparse representation alone by generating the final representation with SSC and max pooling, presented for an online learning classifier. Experimental results obtained on the Caltech 101, Caltech 256, Corel 5000 and Corel 10000 databases, show that, to the best of our knowledge, our approach supersedes in accuracy the best published results to date on the same databases. As an extension, we also show high performance results on the MIT-67 indoor scene recognition dataset.","PeriodicalId":246173,"journal":{"name":"2012 IEEE International Conference on Robotics and Automation","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115095701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 47

The jacobs robotics approach to object recognition and localization in the context of the ICRA'11 Solutions in Perception Challenge 在ICRA感知挑战11解决方案的背景下，雅各布斯机器人技术对物体识别和定位的方法

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6225335

N. Vaskevicius, K. Pathak, A. Ichim, A. Birk

引用次数: 26

k-IOS: Intersection of spheres for efficient proximity query k-IOS:用于高效接近查询的球体交集

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6224889

Xinyu Zhang, Young J. Kim

引用次数: 8

Development and control of a three DOF planar induction motor 平面三自由度感应电机的研制与控制

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6224612

M. Kumagai, R. Hollis

引用次数: 14

Active learning from demonstration for robust autonomous navigation 鲁棒自主导航演示中的主动学习

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6224757

David Silver, J. Bagnell, A. Stentz

引用次数: 56

Versatile distributed pose estimation and sensor self-calibration for an autonomous MAV 自主MAV的多用途分布式姿态估计和传感器自校准

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6225002

S. Weiss, Markus Achtelik, M. Chli, R. Siegwart

{"title":"Versatile distributed pose estimation and sensor self-calibration for an autonomous MAV","authors":"S. Weiss, Markus Achtelik, M. Chli, R. Siegwart","doi":"10.1109/ICRA.2012.6225002","DOIUrl":"https://doi.org/10.1109/ICRA.2012.6225002","url":null,"abstract":"In this paper, we present a versatile framework to enable autonomous flights of a Micro Aerial Vehicle (MAV) which has only slow, noisy, delayed and possibly arbitrarily scaled measurements available. Using such measurements directly for position control would be practically impossible as MAVs exhibit great agility in motion. In addition, these measurements often come from a selection of different onboard sensors, hence accurate calibration is crucial to the robustness of the estimation processes. Here, we address these problems using an EKF formulation which fuses these measurements with inertial sensors. We do not only estimate pose and velocity of the MAV, but also estimate sensor biases, scale of the position measurement and self (inter-sensor) calibration in real-time. Furthermore, we show that it is possible to obtain a yaw estimate from position measurements only. We demonstrate that the proposed framework is capable of running entirely onboard a MAV performing state prediction at the rate of 1 kHz. Our results illustrate that this approach is able to handle measurement delays (up to 500ms), noise (std. deviation up to 20 cm) and slow update rates (as low as 1 Hz) while dynamic maneuvers are still possible. We present a detailed quantitative performance evaluation of the real system under the influence of different disturbance parameters and different sensor setups to highlight the versatility of our approach.","PeriodicalId":246173,"journal":{"name":"2012 IEEE International Conference on Robotics and Automation","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123522691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 140

Underwater electro-navigation in the dark 黑暗中的水下电子导航

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6224836

V. Lebastard, F. Boyer, C. Chevallereau, N. Servagent

引用次数: 20

Compact covariance descriptors in 3D point clouds for object recognition 三维点云中用于目标识别的紧凑协方差描述子

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6224740

D. Fehr, A. Cherian, Ravishankar Sivalingam, S. Nickolay, V. Morellas, N. Papanikolopoulos

引用次数: 42

A compact two DOF magneto-elastomeric force sensor for a running quadruped 一种紧凑的二自由度磁弹性力传感器，用于奔跑的四足动物

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6225201

A. Ananthanarayanan, S. Foong, Sangbae Kim

引用次数: 25

Non-Gaussian belief space planning: Correctness and complexity 非高斯信念空间规划:正确性和复杂性

2012 IEEE International Conference on Robotics and Automation Pub Date : 2012-05-14 DOI: 10.1109/ICRA.2012.6225223

Robert Platt, L. Kaelbling, Tomas Lozano-Perez, Russ Tedrake

{"title":"Non-Gaussian belief space planning: Correctness and complexity","authors":"Robert Platt, L. Kaelbling, Tomas Lozano-Perez, Russ Tedrake","doi":"10.1109/ICRA.2012.6225223","DOIUrl":"https://doi.org/10.1109/ICRA.2012.6225223","url":null,"abstract":"We consider the partially observable control problem where it is potentially necessary to perform complex information-gathering operations in order to localize state. One approach to solving these problems is to create plans in belief-space, the space of probability distributions over the underlying state of the system. The belief-space plan encodes a strategy for performing a task while gaining information as necessary. Unlike most approaches in the literature which rely upon representing belief state as a Gaussian distribution, we have recently proposed an approach to non-Gaussian belief space planning based on solving a non-linear optimization problem defined in terms of a set of state samples [1]. In this paper, we show that even though our approach makes optimistic assumptions about the content of future observations for planning purposes, all low-cost plans are guaranteed to gain information in a specific way under certain conditions. We show that eventually, the algorithm is guaranteed to localize the true state of the system and to reach a goal region with high probability. Although the computational complexity of the algorithm is dominated by the number of samples used to define the optimization problem, our convergence guarantee holds with as few as two samples. Moreover, we show empirically that it is unnecessary to use large numbers of samples in order to obtain good performance.","PeriodicalId":246173,"journal":{"name":"2012 IEEE International Conference on Robotics and Automation","volume":"233 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121891954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 31