检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Meha Kaushik Vignesh Prasad K Madhava Krishna Balaraman Ravindran Robotics Research Center KCIS IIIT Hyderabad Embedded Systems and Robotics TCS Innovation Labs Kolkata Indian Institute of Technology Madras Chennai Tamil Nadu IN

ISBN: (纸本)9781538644539

Most methods that attempt to tackle the problem of Autonomous Driving and overtaking usually try to either directly minimize an objective function or iteratively in a Reinforcement Learning like framework to generate motor actions given a set of inputs. We follow a similar trend but train the agent in a way similar to a curriculum learning approach where the agent is first given an easier problem to solve, followed by a harder problem. We use Deep Deterministic Policy Gradients to learn overtaking maneuvers for a car, in presence of multiple other cars, in a simulated highway scenario. The novelty of our approach lies in the training strategy used where we teach the agent to drive in a manner similar to the way humans learn to drive and the fact that our reward function uses only the raw sensor data at the current time step. This method, which resembles a curriculum learning approach is able to learn smooth maneuvers, largely collision free, wherein the agent overtakes all other cars, independent of the track and number of cars in the scene.

关键词： Automobiles Autonomous vehicles Training Robot sensing systems Tracking Task analysis Neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Application Processing for FPGA-Based Resilient embedded systems in Harsh Environments

Real-Time Application Processing for FPGA-Based Resilient Em...

引用

NASA/ESA Conference on Adaptive Hardware and systems (AHS)

作者： Sangeet Saha Shoaib Ehsan Adrian Stoica Rustam Stolkin Klaus McDonald-Maier Embedded and Intelligent Systems Lab University of Essex Jet Propulsion Laboratory California Institute of Technology Extreme Robotics Lab (ERL) University of Birmingham

Real-time embedded systems nowadays get employed in harsh environments such as space, nuclear sites to carry out critical operations. Along with the traditional software based (CPU) execution, FPGAs are now also emerging as a bright prospect to accomplish such routines. However, these platforms are often get plagued by faults generated due to the high radiations in such environments. As a result, the real-time applications running on the platform could also get jeopardized. Thus, efficient execution of a set of hard real-time applications on reconfigurable systems with anomaly detection and recovery mechanism is inevitable. This work aims at tackling such problem with a “healing” approach for extreme environments. Initially, the applications are intelligently partitioned for hardware and software execution, then attempts have been made to schedule hardware applications with intermittent preemption point. Upon detecting any abnormality on such distinct points, our approach orchestrates a healing mechanism to remediate the scenario without hampering the pre-determined schedule. Experimental validation of our proposed method reveals its effectiveness.

关键词： Field programmable gate arrays Hardware Real-time systems embedded systems Schedules Scheduling

来源：评论

学校读者我要写书评

暂无评论

The use of prototypes within agile product development explorative case study of a Makeathon 23

The use of prototypes within agile product development explo...

引用

23rd International Conference on Engineering, Technology and Innovation, ICE/ITMC 2017

作者： Zink, Lukas Hostetter, Rafael Bohmer, Annette Isabel Lindemann, Udo Knoll, Alois Institute of Product Development Technical University of Munich Munich Germany Institute of Robotics and Embedded Systems Technical University of Munich Munich Germany

ISBN: (纸本)9781538607749

Due to rapid technology change and increased innovation dynamic, product development is related with high uncertainty and complexity [2]. As a consequence of the shortened product life-cycles, agile development becomes more important. It fosters cross-functional project work and enables a team to react fast and flexible to a continuously changing environment. Central aspect of the agile approach within physical product development is prototyping. This work identifies criteria to analyze the use of physical prototypes within an agile set up. Therefore, a Makeathon has been analyzed. In contrast to plan-driven development, prototypes are used to explore, design, verify, test the usability or communicate product aspects. They support the learning process by providing important insights about the solution space on which the planning of the next iteration is based. The data also support the assumption that there is not 'one' approach in agile product development. It is much more likely to be unique to each product, which is also one of the strengths of agile product development, as it allows you to react flexibly to changes. © 2017 IEEE.

关键词： Product development

来源：评论

学校读者我要写书评

暂无评论

Learning to Prevent Monocular SLAM Failure using Reinforcement Learning

arXiv

引用

arXiv 2018年

作者： Prasad, Vignesh Daga, Swapnil Yadav, Karmesh Pareekutty, Nahas Saurabh, Rohitashva Singh Madhava Krishna, K. Ravindran, Balaraman Bhowmick, Brojeshwar Embedded Systems & Robotics TCS Research & Innovation Kolkata India Robotics Research Center KCIS IIIT Hyderabad India Robotics Institute Carnegie Mellon University Pittsburgh United States Dept. of Robotics Engineering John Hopkins University Baltimore United States Dept. of Computer Science Indian Institute of Technology Madras India

Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment. While Monocular SLAM is a well studied problem, automating Monocular SLAM by integrating it with trajectory planning frameworks is particularly challenging. This paper presents a novel formulation based on Reinforcement Learning (RL) that generates fail safe trajectories wherein the SLAM generated outputs do not deviate largely from their true values. Quintessentially, the RL framework successfully learns the otherwise complex relation between perceptual inputs and motor actions and uses this knowledge to generate trajectories that do not cause failure of SLAM. We show systematically in simulations how the quality of the SLAM dramatically improves when trajectories are computed using RL. Our method scales effectively across Monocular SLAM frameworks in both simulation and in real world experiments with a mobile robot. Copyright © 2018, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Safe Stop Trajectory Planning for Highly Automated Vehicles: An Optimal Control Problem Formulation

Safe Stop Trajectory Planning for Highly Automated Vehicles:...

引用

IEEE Symposium on Intelligent Vehicle

作者： Lars Svensson Lola Masson Naveen Mohan Erik Ward Anna Pernestål Brenden Lei Feng Martin Törngren Mechatronics and Embedded Control Systems KTH Royal Institute of Technology Stockholm Sweden LAAS-CNRS University of Toulouse Toulouse France Robotics Perception and Learning KTH Royal Institute of Technology Integrated Transport Research Lab KTH Royal Institute of Technology

Highly automated road vehicles need the capability of stopping safely in a situation that disrupts continued normal operation, e.g. due to internal system faults. Motion planning for safe stop differs from nominal motion planning, since there is not a specific goal location. Rather, the desired behavior is that the vehicle should reach a stopped state, preferably outside of active lanes. Also, the functionality to stop safely needs to be of high integrity. The first contribution of this paper is to formulate the safe stop problem as a benchmark optimal control problem, which can be solved by dynamic programming. However, this solution method cannot be used in real-time. The second contribution is to develop a real-time safe stop trajectory planning algorithm, based on selection from a precomputed set of trajectories. By exploiting the particular properties of the safe stop problem, the cardinality of the set is decreased, making the algorithm computationally efficient. Furthermore, a monitoring based architecture concept is proposed, that ensures dependability of the safe stop function. Finally, a proof of concept simulation using the proposed architecture and the safe stop trajectory planner is presented.

关键词： Trajectory Planning Safety Monitoring Computer architecture Optimization Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Estimating the Region of Attraction via Forward Reachable Sets

Estimating the Region of Attraction via Forward Reachable Se...

引用

American Control Conference

作者： Ahmed El-Guindy Dongkun Han Matthias Althoff Institute of Robotics and Embedded Systems Technische Universitat Munchen

ISBN: (纸本)9781509045839

We propose and implement an algorithm based on reachability analysis to estimate the region of attraction (ROA) of an equilibrium point for nonlinear systems. The stability region is obtained via the computation of forward reachable sets. We compare our results with well-established techniques in this area. In particular, we consider the optimization of the Lyapunov function (LF) sub-level set using sum-of-squares (SOS) decomposition, and the computation of backward reachable sets of a target set using the viscosity solution of a time-dependant Hamilton-Jacobi-Isaacs (HJI) formulation. Our method can overcome many limitations imposed on the applicability of Lyapunov-based approaches, such as conservatism in estimating the stability region, and difficulties associated with choosing a suitable LF. This is due to the fact that our reachability algorithm does not require a LF in order to provide an estimate of the ROA. Various numerical examples show that our proposed approach can estimate the exact ROA quite accurately, and more importantly, scales moderately with the system dimension compared to alternative techniques.

关键词： region of attraction stability region equilibrium point target setting low frequencies reachability analysis SETTING Conservatism Attraction

来源：评论

学校读者我要写书评

暂无评论

A statistical analysis of gamakas in Carnatic music 18

A statistical analysis of gamakas in Carnatic music

引用

18th International Society for Music Information Retrieval Conference, ISMIR 2017

作者： Viraraghavan, Venkata Subramanian Aravind, R. Murthy, Hema A. TCS Research and Innovation Embedded Systems and Robotics Bangalore India Department of Electrical Engineering Indian Institute of Technology Madras India Department of Computer Science and Engineering Indian Institute of Technology Madras India

ISBN: (纸本)9789811151798

Carnatic Music, a form of classical music prevalent in South India, has a central concept called rāgas, defined as melodic scales and/or a set of characteristic melodic phrases. These definitions also account for the continuous pitch movement in gamakas and micro-tonal adjustments to pitch values. In this paper, we present several statistics of gamakas to arrive at a model of Carnatic music. We draw upon the two-component model of Carnatic Music, which splits it into a slowly varying 'stage' and a detail, called 'dance'. Based on the statistics, we propose slightly altered definitions of two similar components called constant-pitch notes and transients. An automated implementation of these definitions is used in collecting statistics from 84 concert renditions. We then suggest that the constant-pitch notes and transients can be considered as context and detail respectively of the rāga, but add that both are necessary for defining the rāga. This is verified by performing listening tests on only the constant-pitch notes and transients independently. © 2019 Venkata Subramanian Viraraghavan, R Aravind, Hema A Murthy.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

UAV Motion Planning and Control for Multi-Coverage of 3D Environments

UAV Motion Planning and Control for Multi-Coverage of 3D Env...

引用

International Conference on Unmanned Aircraft systems

作者： Matthias Weyrer Bernhard Rinner Institute for Robotics and Mechatronics Joanneum Research Klagenfurt Austria Institute of Networked and Embedded Systems Alpen-Adria-Universität Klagenfurt Austria

Multi-coverage (MC) represents an important problem for various tasks of unmanned aerial vehicles (UAVs). For the multi-coverage of a given environment, all visible surfaces must be covered by simultaneously captured images from at least k different viewpoints where additional constraints on resolution, geometry and error may be imposed. In this paper we formulate the MC problem for robot missions and propose a model-predictive control structure to navigate a stereo-pair of UAVs in a leader-follower formation throughout the mission. Our simulation study demonstrates that the UAVs reach and maintain the formation with high spatial and temporal accuracy.

关键词： Multi-camera coverage Unmanned aerial vehicles (UAV) Motion planning Model predictive control Leader-follower formation

来源：评论

学校读者我要写书评

暂无评论

Compositional transient stability analysis of power systems via the computation of reachable sets

Compositional transient stability analysis of power systems ...

引用

American Control Conference

作者： Ahmed El-Guindy Yu Christine Chen Matthias Althoff Institute of Robotics and Embedded Systems Technische Universitat Munchen Department of Electrical and Computer Engineering at the University of British Columbia

ISBN: (纸本)9781509045839

The main challenge associated with the analysis of power systems via the computation of reachable sets is improving the algorithmic efficiency to scale towards industrially relevant problem sizes. In this paper, we present a compositional algorithm that can drastically reduce the computational effort required to assess the dynamical response of power systems during transients using reachability analysis. The main reason for the algorithmic efficiency is that we reformulate the transmission network into a set of subsystems, each consisting of a synchronous generator connected to a generator bus, whose algebraic constraints are unknown-but-bounded within some confidence intervals. This makes it possible to parallelize the computation of reachable sets for transient stability analysis and, more importantly, preserve the interaction and correlation between different machines connected to the grid. The applicability of the proposed compositional algorithm is illustrated on several benchmark examples and compared to other algorithms that compute the reachable set without employing any compositional techniques.

关键词： Transient stability analysis Dynamic security assessment Power systems Reachability analysis power systems transient stability reachability analysis dynamic security assessment transmission networks Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Information estimation with node placement strategy in 3D wireless sensor networks

arXiv

引用

arXiv 2017年

作者： Karjee, Jyotirmoy Jamadagniy, H.S. Embedded Systems and Robotics Group TCS Research and Innovation Bangalore India Department of Electronic Systems Engineering Indian Institute of Science Bangalore India

The cluster formation in Three Dimensional Wireless Sensor Networks (3D-WSN) give rise to overlapping of signals due to spherical sensing range which leads to information redundancy in the network. To address this problem, we develop a sensing algorithm for 3D-WSN based on dodecahedron topology which we call Three Dimensional Distributed Clustering (3D-DC) algorithm. Using 3D-DC algorithm in 3D-WSN, accurate information extraction appears to be a major challenge due to the environmental noise where a Cluster Head (CH) node gathers and estimates information in each dodecahedron cluster. Hence, to extract precise information in each dodecahedron cluster, we propose Three Dimensional Information Estimation (3D-IE) algorithm. Moreover, Node deployment strategy also plays an important factor to maximize information accuracy in 3D-WSN. In most cases, sensor nodes are deployed deterministically or randomly. But both the deployment scenario are not aware of where to exactly place the sensor nodes to extract more information in terms of accuracy. Therefore, placing nodes in its appropriate positions in 3D-WSN is a challenging task. We propose a Three Dimensional Node Placement (3D-NP) algorithm which can find the possible nodes and their deployment strategy to maximize information accuracy in the network. We perform simulations using MATLAB to validate the 3D-DC, 3D-IE and 3D-NP, algorithms respectively. Copyright © 2017, The Authors. All rights reserved.

关键词： Sensor nodes

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：