Robotics: Science and Systems XV最新文献_第4页

Online Incremental Learning of the Terrain Traversal Cost in Autonomous Exploration 自主勘探中地形遍历代价的在线增量学习

Robotics: Science and Systems XV Pub Date : 2019-06-22 DOI: 10.15607/RSS.2019.XV.040

Miloš Prágr, P. Čížek, J. Bayer, J. Faigl

引用次数: 22

Collective Formation and Cooperative Function of a Magnetic Microrobotic Swarm 磁性微机器人群体的集体形成与协作功能

Robotics: Science and Systems XV Pub Date : 2019-06-22 DOI: 10.15607/RSS.2019.XV.007

Xiaoguang Dong, M. Sitti

{"title":"Collective Formation and Cooperative Function of a Magnetic Microrobotic Swarm","authors":"Xiaoguang Dong, M. Sitti","doi":"10.15607/RSS.2019.XV.007","DOIUrl":"https://doi.org/10.15607/RSS.2019.XV.007","url":null,"abstract":"Untethered magnetically actuated microrobots can access distant, enclosed and small spaces, such as inside microfluidic channels and the human body, making them appealing for minimal invasive tasks. Despite the simplicity of individual magnetic microrobots, a collective of these microrobots that can work closely and cooperatively would significantly enhance their capabilities. However, a challenge of realizing such collective magnetic microrobots is to coordinate their formations and motions with underactuated control signals. Here, we report a method that allows collective magnetic microrobots working closely and cooperatively by controlling their two-dimensional (2D) formations and collective motions in a programmable manner. The actively designed formation and intrinsic adjustable compliance within the group allow bio-inspired collective behaviors, such as navigating through cluttered environments and reconfigurable cooperative manipulation ability. These collective magnetic microrobots thus could enable potential applications in programmable self-assembly, modular robotics, swarm robotics, and biomedicine. Keywordsswarm; magnetic microrobots; bio-inspired; cooperation; collective behavior.","PeriodicalId":307591,"journal":{"name":"Robotics: Science and Systems XV","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133508672","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: 1

Robust Singular Smoothers for Tracking Using Low-Fidelity Data 基于低保真度数据的鲁棒奇异平滑跟踪

Robotics: Science and Systems XV Pub Date : 2019-05-22 DOI: 10.15607/RSS.2019.XV.037

Jonathan Jonker, A. Aravkin, J. Burke, G. Pillonetto, Sarah E. Webster

{"title":"Robust Singular Smoothers for Tracking Using Low-Fidelity Data","authors":"Jonathan Jonker, A. Aravkin, J. Burke, G. Pillonetto, Sarah E. Webster","doi":"10.15607/RSS.2019.XV.037","DOIUrl":"https://doi.org/10.15607/RSS.2019.XV.037","url":null,"abstract":"Tracking underwater autonomous platforms is often difficult because of noisy, biased, and discretized input data. Classic filters and smoothers based on standard assumptions of Gaussian white noise break down when presented with any of these challenges. Robust models (such as the Huber loss) and constraints (e.g. maximum velocity) are used to attenuate these issues. Here, we consider robust smoothing with singular covariance, which covers bias and correlated noise, as well as many specific model types, such as those used in navigation. In particular, we show how to combine singular covariance models with robust losses and state-space constraints in a unified framework that can handle very low-fidelity data. A noisy, biased, and discretized navigation dataset from a submerged, low-cost inertial measurement unit (IMU) package, with ultra short baseline (USBL) data for ground truth, provides an opportunity to stress-test the proposed framework with promising results. We show how robust modeling elements improve our ability to analyze the data, and present batch processing results for 10 minutes of data with three different frequencies of available USBL position fixes (gaps of 30 seconds, 1 minute, and 2 minutes). The results suggest that the framework can be extended to real-time tracking using robust windowed estimation.","PeriodicalId":307591,"journal":{"name":"Robotics: Science and Systems XV","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116620224","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: 0

Equivalence of the Projected Forward Dynamics and the Dynamically Consistent Inverse Solution 投影正动力学的等价性和动态一致逆解

Robotics: Science and Systems XV Pub Date : 2019-04-30 DOI: 10.15607/RSS.2019.XV.036

João Moura, V. Ivan, M. S. Erden, S. Vijayakumar

{"title":"Equivalence of the Projected Forward Dynamics and the Dynamically Consistent Inverse Solution","authors":"João Moura, V. Ivan, M. S. Erden, S. Vijayakumar","doi":"10.15607/RSS.2019.XV.036","DOIUrl":"https://doi.org/10.15607/RSS.2019.XV.036","url":null,"abstract":"—The analysis, design, and motion planning of robotic systems, often relies on its forward and inverse dynamic models. When executing a task involving interaction with the environ- ment, both the task and the environment impose constraints on the robot’s motion. For modeling such systems, we need to incorporate these constraints in the robot’s dynamic model. In this paper, we deﬁne the class of Task-based Constraints (TbC) to prove that the forward dynamic models of a constrained system obtained through the Projection-based Dynamics (PbD), and the Operational Space Formulation (OSF) are equivalent. In order to establish such equivalence, we ﬁrst generalize the OSF to a rank deﬁcient Jacobian. This generalization allow us to numerically handle redundant constraints and singular conﬁgurations, without having to use different controllers in the vicinity of such conﬁgurations. We then reformulate the PbD constraint inertia matrix, generalizing all its previous distinct algebraic variations. We also analyse the condition number of different constraint inertia matrices, which affects the numerical stability of its inversion. Furthermore, we show that we can recover the operational space control with constraints from a multiple Task-based Constraint abstraction.","PeriodicalId":307591,"journal":{"name":"Robotics: Science and Systems XV","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127848248","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: 6

Learning Deep Stochastic Optimal Control Policies Using Forward-Backward SDEs 利用前向向后SDEs学习深度随机最优控制策略

Robotics: Science and Systems XV Pub Date : 2019-02-11 DOI: 10.15607/RSS.2019.XV.070

Ziyi Wang, M. Pereira, Evangelos A. Theodorou

引用次数: 41

OIL: Observational Imitation Learning OIL:观察模仿学习

Robotics: Science and Systems XV Pub Date : 2018-03-03 DOI: 10.15607/RSS.2019.XV.005

G. Li, Matthias Müller, Vincent Casser, Neil G. Smith, D. Michels, Bernard Ghanem

{"title":"OIL: Observational Imitation Learning","authors":"G. Li, Matthias Müller, Vincent Casser, Neil G. Smith, D. Michels, Bernard Ghanem","doi":"10.15607/RSS.2019.XV.005","DOIUrl":"https://doi.org/10.15607/RSS.2019.XV.005","url":null,"abstract":"Recent work has explored the problem of autonomous navigation by imitating a teacher and learning an end-to-end policy, which directly predicts controls from raw images. However, these approaches tend to be sensitive to mistakes by the teacher and do not scale well to other environments or vehicles. To this end, we propose Observational Imitation Learning (OIL), a novel imitation learning variant that supports online training and automatic selection of optimal behavior by observing multiple imperfect teachers. We apply our proposed methodology to the challenging problems of autonomous driving and UAV racing. For both tasks, we utilize the Sim4CV simulator that enables the generation of large amounts of synthetic training data and also allows for online learning and evaluation. We train a perception network to predict waypoints from raw image data and use OIL to train another network to predict controls from these waypoints. Extensive experiments demonstrate that our trained network outperforms its teachers, conventional imitation learning (IL) and reinforcement learning (RL) baselines and even humans in simulation. The project website is available at this https URL and a video at this https URL","PeriodicalId":307591,"journal":{"name":"Robotics: Science and Systems XV","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122211848","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: 33