检索结果-内蒙古大学图书馆

Discrete-time dynamic graphical games:model-free reinforcement learning solution

Control Theory and Technology 2015年第1期13卷 55-69页

作者： Mohammed I.ABOUHEAF Frank L.LEWIS Magdi S.MAHMOUD Dariusz G.MIKULSKI Systems Engineering Department King Fahd University of Petroleum & Mineral UTA Research Institute University of Texas at ArlingtonFort Worth Texas U.S.A. State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Ground Vehicle Robotics (GVR) U.S. Army TARDEC Warren MI U.S.A.

This paper introduces a model-free reinforcement learning technique that is used to solve a class of dynamic games known as dynamic graphical games. The graphical game results from to make all the agents synchronize to the state of a command multi-agent dynamical systems, where pinning control is used generator or a leader agent. Novel coupled Bellman equations and Hamiltonian functions are developed for the dynamic graphical games. The Hamiltonian mechanics are used to derive the necessary conditions for optimality. The solution for the dynamic graphical game is given in terms of the solution to a set of coupled Hamilton-Jacobi-Bellman equations developed herein. Nash equilibrium solution for the graphical game is given in terms of the solution to the underlying coupled Hamilton-Jacobi-Bellman equations. An online model-free policy iteration algorithm is developed to learn the Nash solution for the dynamic graphical game. This algorithm does not require any knowledge of the agents＇ dynamics. A proof of convergence for this multi-agent learning algorithm is given under mild assumption about the inter-connectivity properties of the graph. A gradient descent technique with critic network structures is used to implement the policy iteration algorithm to solve the graphical game online in real-time.

关键词： Dynamic graphical games Nash equilibrium discrete mechanics optimal control model-free reinforcementlearning policy iteration

来源：评论

学校读者我要写书评

暂无评论

Towards Flexible Manufacturing: Motion Generation Concept for Coupled Multi-Robot Systems

Towards Flexible Manufacturing: Motion Generation Concept fo...

引用

IEEE International Conference on automation Science and Engineering (CASE)

作者： Yucheng Tang Wei Shen Ilshat Mamaev Björn Hein Karlsruhe University of Applied Sciences Proximity Robotics & Automation GmbH Robotics Lab (IAR - IPR) Karlsruhe Institute of Technology (KIT) Institute for Anthropomatics and Robotics - Intelligent Process Automation Karlsruhe Germany

This paper presents a motion generation concept with stiffness and path constraints for multi-robot systems in a flexible manufacturing context. An optimization approach using closed-form inverse kinematics solutions is proposed to maximize the Cartesian stiffness, simultaneously preserving the continuity of the joints' movement. We also present an efficient trajectory generation approach combining Particle Swarm Optimization (PSO) and Online Trajectory Generation (OTG) methods. For the sake of synchronization, we assume a 14 Degrees of Freedom (DOF) closed-chain kinematics for the trajectory generation of the dual-robot system. We evaluate the proposed approach on a mock-up of the sheet metal bending task using two coupled Franka Emika robots. The results show that the proposed method increases the stiffness of the robot, as it can apply three times the force compared to benchmark methods before reaching the joint torque limit in the single robot experiments. Furthermore, two physically coupled Panda robots can generate a force of up to 732 N with joint torque limits set to 10%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DESIGN AND DEVELOPMENT OF DECISION-MAKING AND CONTROL SYSTEM FOR VISION-BASED SOCCER ROBOTS

引用

IFAC Proceedings Volumes 2005年第1期38卷 221-226页

作者： Xinhe Xu Fangzhen Xue Ting Feng Key Laboratory of Process Industry Automation Ministry of Education. Institute of AI and Robotics Northeastern University Shenyang 110004 China

Centralized robot soccer becomes more and more popular project of science and technology. Because of its global vision, the decision-making and motion control becomes the keystone and the multilevel hierarchical structure is suitable. The robot controller is the ‘Brain-less' executor, the motion controller includes all kinds of action functions and the organizing level can adopt different decision schemes. Various decision and control methods make the soccer robot a micro high-tech platform. This paper is a summary to the decision-making and control system of soccer robot according our years' research and experiments.

关键词： robot soccer control and decision-making multilevel hierarchical control reasoning model reactive model system simulation

来源：评论

学校读者我要写书评

暂无评论

Control of a Smart Walker for Training Using Interaction-Energy and Personalized Parameters ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 10154-10161页

作者： Denis Stogl Daniel Zumkeller Manuel Muth Björn Hein Institute for Anthropomatics and Robotics Intelligent Process Automation and Robotics Lab (IAR-IPR) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Karlsruhe University of Applied Science Karlsruhe Germany

Smart walkers with admittance controller usually have limited dynamics and low maximal velocity to provide stable and safe behavior. To enable physically challenging training with smart walker control strategies enabling faster dynamics is needed. However, in certain situations, this can lead to instabilities, which further complicates the finding of suitable parameters for the envisioned training functionalities. To overcome these issues, we have introduced an interaction-energy limiter and developed a strategy to automatically determine individual user parameters for an adaptive admittance controller. The energy limiter bounds the controller and training elements to avoid uncomfortable and dangerous situations. These training elements are placed on a 2D map of a training environment. If the user passes these training elements with our smart walker - RoboTrainer - they are triggered. Therefore we call them spatial control actions. We can show that interaction-energy limiter successfully avoids instabilities and dangerous situations when spatial control actions are triggered. The evaluation with 22 users, which used Robo Trainer with and without individualized parameters, successfully demonstrate the benefits of the parameterization method. The presented method could be generally valuable for the implementation of smart walkers in everyday life since it provides a solution for dealing with users with different skills and a solution for safe interaction with smart walkers using high-dynamic control.

关键词： Human-machine interface Human-machine interaction Admittance control Model-based control Human-centered design Nonlinear gain Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Virtual Adversarial Humans finding Hazards in Robot Workplaces

Virtual Adversarial Humans finding Hazards in Robot Workplac...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Tom P. Huck Christoph Ledermann Torsten Kröger Intelligent Process Automation and Robotics Lab Institute of Anthropomatics and Robotics (IAR-IPR) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany

During the planning phase of industrial robot workplaces, hazard analyses are required so that potential hazards for human workers can be identified and appropriate safety measures can be implemented. Existing hazard analysis methods use human reasoning, checklists and/or abstract system models, which limit the level of detail. We propose a new approach that frames hazard analysis as a search problem in a dynamic simulation environment. Our goal is to identify workplace hazards by searching for simulation sequences that result in hazardous situations. We solve this search problem by placing virtual humans into workplace simulation models. These virtual humans act in an adversarial manner: They learn to provoke unsafe situations, and thereby uncover workplace hazards. Although this approach cannot replace a thorough hazard analysis, it can help uncover hazards that otherwise may have been overlooked, especially in early development stages. Thus, it helps to prevent costly re-designs at later development stages. For validation, we performed hazard analyses in six different example scenarios that reflect typical industrial robot workplaces.

关键词： Analytical models Phase measurement automation Service robots Conferences Employment Search problems

来源：评论

学校读者我要写书评

暂无评论

Achieving Hard Real-Time Capability for 3D Human Pose Estimation Systems

Achieving Hard Real-Time Capability for 3D Human Pose Estima...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Patrick Schlosser Christoph Ledermann Intelligent Process Automation and Robotics Lab Institute of Anthropomatics and Robotics (IAR-IPR) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany

In the industrial domain, the application of any system as a safety function has to follow strict rules and requirements, defined in safety standards such as ISO 13849 [1] and ISO 13855 [2]. Two core requirements are an extremely low rate of dangerous errors and an upper limit for the response time of the system (hard real-time requirement). Current approaches in the field of human pose estimation achieve neither of *** our work we approach the second requirement by introducing a general procedure to achieve hard real-time capability for interchangeable 3D human pose estimation systems. We use the detections of the pose estimation to model the human as 3D volume consisting of spheres and spherical cones. To bridge the time between arriving detections, the volume is adjusted in a way that ensures coherence, continuity and, most important, conformance with necessary surcharges from safety standard ISO 13855 [2]. Low and fixed computational cost for the adaption makes the procedure real-time capable. Our modelling approach using spheres and spherical cones also allows distance calculations at low and fixed computational costs, e.g. between human and robot. We show the benefit of our approach via human-robot distance calculation experiments, outperforming a safety-certified laser scanner for most of the time.

关键词： Solid modeling Adaptation models Three-dimensional displays ISO Standards Pose estimation Laser modes Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Robust Human Pose Estimation under Gaussian Noise

Robust Human Pose Estimation under Gaussian Noise

引用

IEEE International Conference on robotics and automation (ICRA)

Robustness against specific kinds of noise is of high importance for safety-critical components in industrial robot applications, as legal and normative regulations demand the identification and handling of all unacceptable risks. This includes risks from environmental conditions, like noisy data. One such component is human pose estimation, which is needed and crucial for human-robot collaboration tasks and applications. However, little research on human pose estimation under specific noise types has been performed. In our work, we focus on extensively evaluating human pose estimation under specific noise and propose potential countermeasures. We leverage Gaussian noise as specific noise type and the hourglass model as human pose estimator. We show that human pose estimation is already vulnerable to small amounts of Gaussian noise. As countermeasures we propose either denoising images upfront or training the hourglass model to be robust against Gaussian noise. All methods achieve a significantly higher robustness against Gaussian noise, typically at the cost of slightly worse performance on clean data. Three of our methods also achieved slight improvements on clean data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Upper Bounds for Localization Errors in 2D Human Pose Estimation

Upper Bounds for Localization Errors in 2D Human Pose Estima...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Patrick Schlosser Christoph Ledermann Tamim Asfour Intelligent Process Automation and Robotics Lab Institute of Anthropomatics and Robotics (IAR-IPR) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany

Obtaining reliable detections of a human is crucial for many safety-related robotic tasks. This can be done by human pose estimation methods, which predict the position of several different keypoints of the human body. In most cases, recent approaches based on neural networks produce ‘good’ results, i.e. predictions with small localization errors, however, large errors do also occur. For an individual keypoint prediction, the magnitude of the error is unknown, posing a risk to safety. In this work, we extend a neural network architecture for single-person 2D human pose estimation, so that it predicts not only the keypoints of the human body, but also corresponding upper bounds for their localization errors. These upper bounds correspond to the neural network's confidence in its output, and are obtained by one of two general strategies based on (i) a direct estimation of the localization error or (ii) the predicted standard deviations of a 2D Gaussian. We propose several approaches employing these strategies and evaluate them on the MPII Human Pose dataset. In addition, we consider two quality criteria for the results: closeness of the predicted keypoint position to the actual one, and closeness of the predicted upper bound to the localization error. The best results are achieved by a Gaussian-based approach, which predicted correct upper bounds in 94.7% of the cases, while also sufficiently fulfilling the quality criteria.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reachability-Based Confidence-Aware Probabilistic Collision Detection in Highway Driving

引用

Engineering 2024年第2期33卷 90-107页

作者： Xinwei Wang Zirui Li Javier Alonso-Mora Meng Wang School of Engineering and Materials Science Queen Mary University of LondonLondon E14NSUK Department of Cognitive Robotics Delft University of TechnologyDelft 2628 CDNetherlands School of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China Chair of Traffic Process Automation “Friedrich List”Faculty of Transport and Traffic SciencesTU DresdenDresden 01069Germany

Risk assessment is a crucial component of collision warning and avoidance systems for intelligent ***-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle ***,they suffer from over-conservatism,potentially resulting in false–positive risk events in complicated real-world *** this paper,we combine two reachability analysis techniques,a backward reachable set(BRS)and a stochastic forward reachable set(FRS),and propose an integrated probabilistic collision–detection framework for highway *** this framework,we can first use a BRS to formally check whether a two-vehicle interaction is safe;otherwise,a prediction-based stochastic FRS is employed to estimate the collision probability at each future time ***,the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical *** construct the stochastic FRS,we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction *** experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving *** efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway *** proposed risk assessment framework is promising for real-world applications.

关键词： Probabilistic collision detection Confidence awareness Probabilistic acceleration prediction Reachability analysis Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Evaluating Form-flexible Gripper in Robotic Manipulation Tasks

Evaluating Form-flexible Gripper in Robotic Manipulation Tas...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Niklas Grambow Axel Vick Bennet Schulz Process Automation and Robotics Fraunhofer IPK Berlin Germany Volkswagen Commercial Vehicles Hannover Germany

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

Common grippers used in robotic manipulation are typically designed for specific tasks, tailored to accommodate anticipated variations in object geometry, surface texture, and weight. Some grippers exist that ensure grasping a range of objects. One promising approach utilizes gripping pads that adapt the geometry and shape of the object to manipulate following by constructing a vacuum to create the effective gripping force. We propose an evaluation of a gripper that uses a circular gripping pad able to adapt to the geometry and surface of the objects to manipulate. In order to assess the gripper’s performance we utilize an optical measurement system to observe the manipulation process including various objects to be manipulated. Analyzing the data obtained from the optical tracking system enables us to evaluate the precision of grasping different objects. One experiment includes the picking of an object from a predefined initial position, performing free space motion before returning back to the initial position. The preliminary results indicate positional deviations of up to 10.36 mm.

关键词： Geometry Service robots Tracking Shape Grasping Optical variables measurement Surface texture

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：