检索结果-内蒙古大学图书馆

Deep reinforcement learning for path planning of autonomous mobile robots in complicated environments

Complex and Intelligent systems 2025年第6期11卷 1-15页

作者： Zhang, Zhijie Fu, Hao Yang, Juan Lin, Yunhan School of Computer Science and Technology Wuhan University of Science and Technology No. 947 Heping Avenue Hubei Wuhan 430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System No. 947 Heping Avenue Hubei Wuhan 430081 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology No. 947 Heping Avenue Hubei Wuhan 430081 China

In complicated environments, which include dynamic and narrow areas, the path planning of Autonomous Mobile Robots (AMRs) encounters challenges, like slow model convergence and limited representational capabilities, often resulting in the robot taking longer, less efficient paths or even colliding with obstacles. To tackle these challenges, the Gated Attention Prioritized Experience Replay Soft Actor-Critic (GAP_ SAC) algorithm is proposed. Key improvements include expanding the state space for better perception, designing a dynamic heuristic reward function to more effectively guide the AMR in achieving its path planning objectives and integrating Prioritized Experience Replay (PER) to improve sample efficiency and accelerate convergence. Additionally, a gated attention mechanism is also introduced to focus on critical environmental features, enhancing the models’ perception capability. Comparative experiments validate that the proposed GAP_SAC algorithm outperforms TD3, SAC and SAC’s variant, demonstrating superior robustness and generalization in complicated environments. © The Author(s) 2025.

关键词： Autonomous mobile robot (AMR) Deep reinforcement learning (DRL) Dynamic and narrow areas Gated attention mechanism Path planning

来源：评论

学校读者我要写书评

暂无评论

Motion coordination and reactive control of autonomous multi-manipulator systems

引用

JOURNAL OF ROBOTIC systems 1996年第11期13卷 737-754页

作者： Nassal, UM Institute for Real-Time Computer Systems and Robotics (IPR) University of Karlsruhe D-76128 Karlsruhe Germany [*]Institute for Real-Time Computer Systems and Robotics (IPR) University of Karlsruhe D-76128 Karlsruhe Germany

The emerging field of service robots demands new systems with increased flexibility. The flexibility of a robot system can be increased in many different ways. Mobile manipulation-the coordinated use of manipulation capabilities and mobility-is an approach to increase robots flexibility with regard to their motion capabilities. Most mobile manipulators that are currently under development use a single arm on a mobile platform. The use of a two-arm manipulator system allows increased manipulation capabilities, especially when large, heavy, or non-rigid objects must be manipulated. This article is concerned with motion control for mobile two-arm systems. These systems require new schemes for motion coordination and control. A coordination scheme called transparent coordination is presented that allows for an arbitrary number of manipulators on a mobile platform. Furthermore, a reactive control scheme is proposed to enable the platform to support sensor-guided manipulator motion. Finally, this article introduces a collision avoidance scheme for mobile two-arm robots. This scheme surveys the vehicle motion to avoid platform collisions and arm collisions caused by self-motion of the robot. (C) 1996 John Wiley & Sons, Inc.

关键词： Reactive power control Motor Control Service robots Platform Robot System Mobile Robot Manipulators Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Dynamic task mapping in a real-time controller for distributed cooperating robot systems

引用

CONTROL ENGINEERING PRACTICE 1996年第6期4卷 831-838页

作者： Lueth, T Laengle, T Heinzman, J Institutef/or Real-Time Computer Systems and Robotics (IPR) University of Karlsruhe D-76128 Karlsruhe Germany

An intelligent control architecture for autonomous robot systems must be modular, scaleable, extendible, and adaptable to the available capacity of computer control systems. To support these properties, the concept of an adaptive control structure, ACS, is presented in this paper. Experiments with a small autonomous assembly robot show the successful use of ACS.

关键词： robot control distributed control distributed computer control systems adaptive control discrete-event systems

来源：评论

学校读者我要写书评

暂无评论

APPLICATIONS OF FUZZY-LOGIC CONTROL IN AUTONOMOUS ROBOT systems

引用

INTERNATIONAL JOURNAL OF systems SCIENCE 1993年第10期24卷 1885-1904页

作者： ZHANG, JW Institute for Real-Time Computer Systems and Robotics Department of Computer Science University of Karlsruhe Karlsruhe Germany

The development of autonomous robots involves the imitation of human decision-making abilities with the aid of diverse sensor information. Fuzzy logic, which is based on fuzzy modelling and approximate reasoning, can be applied in different levels of control tasks. We first present the research results of applying fuzzy logic control in the motion execution of mobile systems and sensor-guided fine-motion of a manipulator. To realize real-time 'reactive' control, suitable hardware which supports the acceleration of fuzzy inference should be developed. The design and development of a VME-bus compatible fuzzy co-processor is also described.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Model-based process redesign

引用

JOURNAL OF INTELLIGENT MANUFACTURING 1997年第5期8卷 345-356页

作者： Janusz, B Institute for Real-Time Computer Systems and Robotics Department of Computer Science University of Karlsruhe Karlsruhe Germany

A method is presented for the model-based redesign of enterprises. It consists of two main steps, the initialization step and the optimization step. During the initialization step, the processes are modelled and analysed. During the optimization step, the optimal configuration is found for the possible modifications of the processes. Emphasis is placed on the process analysis. The proposed approach is based on activity chains which describe the set of activities needed for the achievement of a given gear, and their execution order necessary to guarantee a low processing time. An algorithm is presented for filtering such activity chains from an enterprise model. It is based on graph theory and corresponds to the solution of an optimization problem, whereby the sum of weights of ail edges belonging to the solution graph should be maximized under some given constraints. Because of the high complexity of the problem, some complexity-reducing measures are presented, measures that arise from the earlier problem analysis.

关键词： process redesign process analysis activity chain graph theory

来源：评论

学校读者我要写书评

暂无评论

Interactive control and environment modelling for a mobile robot based on multisensor perceptions

引用

robotics AND AUTONOMOUS systems 1996年第3期18卷 301-310页

作者： Lin, IS Wallner, F Dillmann, R Institute for Real-Time Computer Systems and Robotics University of Karlsruhe D-76128 Karlsruhe Germany

This paper presents an advanced telerobotic control system for a mobile robot with multisensor feedback. A telecontrol concept for various degrees of cooperation between a human operator and a mobile robot is described. With multisensor on-board the robot at the remote site can adjust its path while continuously accepting commands from the human operator. Interactive modelling that allows the modelling of an unknown environment and makes landmarks known to the robot is introduced. A graphical user interface and a 3-D animation system are important elements in the teleoperation, they are integrated in this system to help the operator by task analysis, off-line teaching and on-line monitoring. Experiments performed with the mobile robot PRIAMOS are discussed.

关键词： mobile robot telerobotics multisensor man-machine systems

来源：评论

学校读者我要写书评

暂无评论

Hierarchical refinement of skills and skill application for autonomous robots

引用

robotics AND AUTONOMOUS systems 1997年第3-4期19卷 259-271页

作者： Kaiser, M Dillmann, R University of Karlsruhe Institute for Real-Time Computer Systems and Robotics D-76128 Karlsruhe Germany

One of the major goals in designing learning robots is to let these robots develop useful skills over time. These skills are not only related to physical actions of the robot, but also to the coordination of activities, communication with humans, and active sensing. Throughout this paper, the interdependency between these different kinds of skills is analyzed. For the case of elementary action skills and coordination skills, methods for inegration of skill application and refinement are developed. It is shown that this integration has the potential to support long-term learning and autonomous experimentation.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

AN INTEGRATED APPROACH TO SOFTWARE systems PLANNING AND SELECTION BASED ON CIMOSA MODELS

引用

CONTROL ENGINEERING PRACTICE 1995年第1期3卷 97-103页

作者： NAEGER, G REMBOLD, U Department of Computer Science Institute for Real-Time Computer Systems and Robotics University of Karlsruhe 76128 Karlsruhe Germany

Strong international competition forces enterprises to reduce organizational overhead and cost. Today's industrial practices allow, in general, only the selection of whole planning and control systems for CIM (e.g., CAD systems, PP&C systems,...). These systems can be adapted only in a limited range to the user requirements. With the introduction of executable enterprise models to the industrial environment, it is expected that it will be possible to design tailored CIM systems built of standardized software modules which will lead to higher complexity of the planning process for software systems. Thus, today's planning and selection approaches will face more and more problems. In order to master the increasing complexity of the planning of software systems for enterprises, new planning methods and tools are required. An integrated approach to software system planning and selection based on CIMOSA enterprise models was developed. The underlying idea of the approach is the conversion of the planning problem into an equivalent constraint satisfaction problem. The conversion process can be accomplished fully automatically.

关键词： ENTERPRISE MODELING CIMOSA RESOURCE SELECTION

来源：评论

学校读者我要写书评

暂无评论

PLANNING OF SENSING TASKS IN AN ASSEMBLY ENVIRONMENT

引用

JOURNAL OF INTELLIGENT & ROBOTIC systems 1991年第3期4卷 221-254页

作者： WERLING, G 1. Institute for Real-Time Computer Control Systems and Robotics University of Karlsruhe D-7500 Karlsruhe Germany

The purpose of this paper is to give an overview of past and recent work on planning sensing strategies for vision sensors. To achieve an economic use of robots in manufacturing, their programs must provide a high degree of fault-tolerance, security, and robustness to prevent unforeseen errors. Model errors (also termed uncertainties) are one of the most frequent reasons for such undesirable events. Robot systems can be made more reliable and fault-tolerant by providing them with capabilities of error detection and recovery, or error prevention. The latter may be achieved by reducing model errors using tactile and non-tactile sensors. The quality of a robot program synthesized by a task-level programming system depends on the accuracy of the model, since all information that is not explicitly given by the programmer must be derived from it. This means that the following questions have to be answered by the automatic task planner in order to plan non-tactile sensing strategies: (1) When do I have to use sensors to reduce uncertainty about the real world? (2) What do I have to use them for? (3) How do I have to use them to achieve the necessary information within an acceptable period of time? There are very few systems which deal broadly with the problem of robust robot programs, whereas there are numerous works on detail aspects of the field. The main approaches will be introduced and discussed in more detail. Finally, a new concept for generating sensor-integrated robust robot programs will be proposed.

关键词： VERIFICATION TASK-LEVEL PROGRAMMING ROBOT VISION UNCERTAINTY ASSEMBLY PLANNING FAULT TOLERANCE CLASSIFICATION PREDICTION CAMERA LOCATION

来源：评论

学校读者我要写书评

暂无评论

Intelligent control for haptic displays

引用

computer GRAPHICS FORUM 1996年第3期15卷 C217-C226页

作者： Munch, S Stangenberg, M Institute for Real-Time Computer Systems & Robotics University of Karlsruhe Kaiserstr. 12 D-76128 Karlsruhe Germany

Usually, a mouse is used for input activities only, whereas output from the computer is sent via the monitor and one or true loudspeakers. But why not use the mouse for output, tool For instance, if it would be possible to predict the next interaction object the user wants to click on, a mouse with a mechanical brake could stop the cursor movement at the desired position. This kind of aid is especially attractive for small targets like resize. handles of windows or small buttons. In this paper, we present an approach for the integration of haptic feedback in everyday graphical user interfaces. We use a specialized mouse which is able to apply simple haptic information to the user's hand and index finger. A multi-agent system has been designed which 'observes' the user is. order to predict the next interaction object and launch haptic feedback, thus supporting positioning actions with the mouse. Although primarily designed in order to provide 'intelligent' haptic feedback, the system can be combined with other output modalities as well, due to its modular and flexible architecture.

关键词： multimodal interaction haptic output user modelling human-computer interaction

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：