2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)最新文献_第4页

Teaching a Robot to Grasp Real Fish by Imitation Learning from a Human Supervisor in Virtual Reality 在虚拟现实中，通过向人类监督者模仿学习来教机器人抓取真鱼

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8593954

Jonatan S. Dyrstad, Elling Ruud Øye, Annette Stahl, J. R. Mathiassen

引用次数: 20

Comparison of Dynamic Models for Non-Contact Micromanipulation Based on Dielectrophoretic Actuation 基于介电泳驱动的非接触微操作动力学模型比较

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8594377

Vladimir Gauthier, A. Bolopion, M. Gauthier

引用次数: 1

Single Leg Dynamic Motion Planning with Mixed-Integer Convex Optimization 基于混合整数凸优化的单腿动态运动规划

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8594161

Yanran Ding, Chuanzheng Li, Hae-won Park

{"title":"Single Leg Dynamic Motion Planning with Mixed-Integer Convex Optimization","authors":"Yanran Ding, Chuanzheng Li, Hae-won Park","doi":"10.1109/IROS.2018.8594161","DOIUrl":"https://doi.org/10.1109/IROS.2018.8594161","url":null,"abstract":"This paper proposes a mixed-integer convex programming formulation for dynamic motion planning. Many dynamic constraints such as the actuator torque constraint are nonlinear and non-convex due to the trigonometrical terms from the Jacobian matrix. This often causes the optimization problem to converge to local optima or even infeasible set. In this paper, we convexify the torque constraint by formulating a mixed-integer quadratically-constrained program (MIQCP). More specifically, the workspace is discretized into a union of disjoint polytopes and torque constraint is enforced upon a convex outer approximation of the torque ellipsoid, obtained by solving a semidefinite program (SDP). Bilinear terms are approximated by McCormick envelope convex relaxation. The proposed MIQCP framework could be solved efficiently to global optimum and the generated trajectories could exploit the rich features of the rough terrain without any initial guess from the designer. The demonstrated experiment results prove that this approach is currently capable of planning consecutive jumps that navigates a single-legged robot through challenging terrains.","PeriodicalId":6640,"journal":{"name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"96 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80903764","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: 17

Energy-Efficient Trajectory Generation for a Hexarotor with Dual- Tilting Propellers 双倾斜螺旋桨六旋翼机的节能轨迹生成

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8594419

F. Morbidi, Davide Bicego, Markus Ryll, A. Franchi

引用次数: 23

Leg Design to Enable Dynamic Running and Climbing on BOBCAT 腿的设计，使动态运行和攀登的山猫

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8594355

Max P. Austin, Jason M. Brown, Charles Young, Jonathan E. Clark

引用次数: 10

Efficient Distributed Torque Computation for Large Scale Robot Skin 大型机器人皮肤的高效分布式扭矩计算

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8594144

Florian Bergner, E. Dean-León, G. Cheng

引用次数: 8

Apple Counting using Convolutional Neural Networks 苹果计数使用卷积神经网络

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8594304

Nicolai Häni, Pravakar Roy, Volkan Isler

{"title":"Apple Counting using Convolutional Neural Networks","authors":"Nicolai Häni, Pravakar Roy, Volkan Isler","doi":"10.1109/IROS.2018.8594304","DOIUrl":"https://doi.org/10.1109/IROS.2018.8594304","url":null,"abstract":"Estimating accurate and reliable fruit and vegetable counts from images in real-world settings, such as orchards, is a challenging problem that has received significant recent attention. Estimating fruit counts before harvest provides useful information for logistics planning. While considerable progress has been made toward fruit detection, estimating the actual counts remains challenging. In practice, fruits are often clustered together. Therefore, methods that only detect fruits fail to offer general solutions to estimate accurate fruit counts. Furthermore, in horticultural studies, rather than a single yield estimate, finer information such as the distribution of the number of apples per cluster is desirable. In this work, we formulate fruit counting from images as a multi-class classification problem and solve it by training a Convolutional Neural Network. We first evaluate the per-image accuracy of our method and compare it with a state of the art method based on Gaussian Mixture Models over four test datasets. Even though the parameters of the Gaussian Mixture Model based method are specifically tuned for each dataset, our network outperforms it in three out of four datasets with a maximum of 94% accuracy. Next, we use the method to estimate the yield for two datasets for which we have ground truth. Our method achieved 96-97% accuracies. For additional details please see our video here: https://www.youtube.com/watch?v=Le0mb5P-SYc.","PeriodicalId":6640,"journal":{"name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"16 1","pages":"2559-2565"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78252855","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: 23

Distributed Reconfigurable Formation Generator for Mini Aerial Vehicles 小型飞行器分布式可重构编队发生器

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8593511

Lara Brifion-Arranz, Matthieu Muschinowski, J. Dumon, N. Marchand

引用次数: 0

Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition 稳定基于激光雷达位置识别的无监督特征学习

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8593562

Peng Yin, Lingyun Xu, Zhe Liu, Lu Li, Hadi Salman, Yuqing He, Weiliang Xu, Hesheng Wang, H. Choset

{"title":"Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition","authors":"Peng Yin, Lingyun Xu, Zhe Liu, Lu Li, Hadi Salman, Yuqing He, Weiliang Xu, Hesheng Wang, H. Choset","doi":"10.1109/IROS.2018.8593562","DOIUrl":"https://doi.org/10.1109/IROS.2018.8593562","url":null,"abstract":"Place recognition is one of the major challenges for the LiDAR-based effective localization and mapping task. Traditional methods are usually relying on geometry matching to achieve place recognition, where a global geometry map need to be restored. In this paper, we accomplish the place recognition task based on an end-to-end feature learning framework with the LiDAR inputs. This method consists of two core modules, a dynamic octree mapping module that generates local 2D maps with the consideration of the robot's motion; and an unsupervised place feature learning module which is an improved adversarial feature learning network with additional assistance for the long-term place recognition requirement. More specially, in place feature learning, we present an additional Generative Adversarial Network with a designed Conditional Entropy Reduction module to stabilize the feature learning process in an unsupervised manner. We evaluate the proposed method on the Kitti dataset and North Campus Long-Term LiDAR dataset. Experimental results show that the proposed method outperforms state-of-the-art in place recognition tasks under long-term applications. What's more, the feature size and inference efficiency in the proposed method are applicable in real-time performance on practical robotic platforms.","PeriodicalId":6640,"journal":{"name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"5 1","pages":"1162-1167"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73183441","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: 15

Learning-based Path Tracking Control of a Flapping-wing Micro Air Vehicle 基于学习的扑翼微型飞行器路径跟踪控制

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Pub Date : 2018-10-01 DOI: 10.1109/IROS.2018.8594387

Jonggu Lee, Seungwan Ryu, Taewan Kim, Wonchul Kim, H. Kim

引用次数: 6