Presents a control system for the intelligent force control of multifingered robot grips. The multilevel system architecture combines both a fuzzy-based adaptation level and a neural-based one with a conventional PID-...
详细信息
Presents a control system for the intelligent force control of multifingered robot grips. The multilevel system architecture combines both a fuzzy-based adaptation level and a neural-based one with a conventional PID-controller that allows autonomous performance of fine manipulations of an object. Two kinds of fuzzy controllers are presented. They use a decision making logic which expresses the a priori knowledge about the grasp force behaviour inside the friction cones and the necessary reactions regarding the criterion for grip stability. A neural controller, based on a Hooke-Jeeves optimisation approach, has been developed as well. The neural control algorithm is implemented by a three-layered backpropagation neural network. The neural and fuzzy controllers can be used separately or in parallel. In the last case the neural controller can be on-line trained using the input-output information from the fuzzy one. A computer based simulation system for the peg-in-hole insertion task is developed to analyse and to compare the capabilities of both control algorithms. The demands of flexibility and real-time control of the implementation of the control system are suited by a tailorable parallel computer concept. The two basic ideas of the concept are to set up each processing element individually for its application and connect these elements with different communicational methods according to the applicational demands. As this happens before runtime the concept is called static flexibility and is implemented using a new mechanical computer structure.< >
The use of two or more robots in a common workspace is essential to expand the field of potential applications. This paper presents a distributed approach for executing task-level programs for cooperating manipulators...
详细信息
The use of two or more robots in a common workspace is essential to expand the field of potential applications. This paper presents a distributed approach for executing task-level programs for cooperating manipulators or one arm systems with many degrees of freedom. At task level, only the movement of the objects to be manipulated is specified. The corresponding manipulator motions are then calculated by assigning the local intelligence to each joint. The local intelligence enables the joint agents to calculate in parallel their appropriate movements to make the end effector reach the desired position. During execution, each joint evaluates the sensor data to compensate for execution errors, to react on unexpected obstacles and to provide the manipulator coordination. Therefore, a distributed fuzzy rule base has been developed. As this local evaluation may lead to non-optimal overall behavior of the manipulator, the joint agents communications provide global suboptimality.< >
In this paper the framework of an intelligent control system of a multi-finger robot hand is described, that is especially tailored for sensor-based object handling and assembly. The research has concerned with the Ka...
详细信息
In this paper the framework of an intelligent control system of a multi-finger robot hand is described, that is especially tailored for sensor-based object handling and assembly. The research has concerned with the Karlsruhe dextrous hand, a modular three-finger hand with 9 degrees of freedom, independent finger modules and integrated sensors. The total system structure consists of three embedded subsystems, with a planning and supervisory system on the top, which has a blackboard-like architecture to exchange information with a distributed real-time control system that provides force/position control strategies for dextrous grasping and manipulating of arbitrary objects. A programming and simulation system supports the object/task-based description of all robot and gripper actions required to perform a specific operation.< >
A fuzzy logic approach for the online grasp-force-adaptation, which can be used for the control of fine manipulating with a multifingered robot hand, will be presented in this paper. The kernel of this approach consis...
详细信息
A fuzzy logic approach for the online grasp-force-adaptation, which can be used for the control of fine manipulating with a multifingered robot hand, will be presented in this paper. The kernel of this approach consists of decision making logic which expresses the a-priory knowledge about the force behaviour inside the friction cones and the necessary reactions, regarding the criterion for grip stability. For the software realisation of the fuzzy control approach a Fuzzy-C Development System supporting the entire development process was used. Two corresponding fuzzy controllers have been designed: A finger controller and a grasp controller. During fine manipulations of an object the fuzzy controller interacts with an underlying conventional controller that receives, after defuzzyfication, the adapted force values which were applied. A computer based simulation system was developed to analyse the capabilities of the designed fuzzy controllers.< >
This paper deals with the two fundamental problems that occur when objects are manipulated with multi-finger robot hands: the determination of the joint motions to perform a manipulation according to a given object tr...
详细信息
This paper deals with the two fundamental problems that occur when objects are manipulated with multi-finger robot hands: the determination of the joint motions to perform a manipulation according to a given object trajectory, and the optimization of the joint torques needed to ensure a stable and secure grip. The consideration of the effect of rolling and slipping of the fingertips at the contact points on the object surface leads to a set of linear differential equations for the joint angles and to a partly nonlinear optimization problem for the joint torques solved by the Hooke-Jeeves algorithm. The removal of redundant information reduces the computational effort to about 40% of the operations required for the standard procedure. Especially, the resulting object motions are demonstrated at an example: the rotation of an ellipsoid object with the fingers of the Karlsruhe dextrous hand.< >
In this paper, a new natural language interface is presented that can be applied to make the use of intelligent robots more flexible. This interface was developed for the autonomous mobile two-arm robot KAMRO, which u...
详细信息
In this paper, a new natural language interface is presented that can be applied to make the use of intelligent robots more flexible. This interface was developed for the autonomous mobile two-arm robot KAMRO, which uses several camera systems to generate an environment model and to perform assembly tasks. A fundamental requirement in human-machine interaction for intelligent robots is the ability to refer to objects in the robot's environment. Hence, the interface and the intelligent system need similar environment models and it is necessary to provide current sensor information. Additional flexibility can be achieved by integrating the man-machine interface into control architecture of the robot and to give it an access to all internal information and to the models that the robot uses for an autonomous behaviour. In order to fully exploit the capabilities or a natural language access, we present a dialogue-based interface KANTRA, in which the human-machine interaction is not restricted to unidirectional communication.< >
Besides the typical use of industrial robots in a manufacturing setting, new application areas for robots have been appearing during the past few years. In these areas, service robots perform general purpose activitie...
详细信息
Besides the typical use of industrial robots in a manufacturing setting, new application areas for robots have been appearing during the past few years. In these areas, service robots perform general purpose activities without requiring repeated high speed movements or other requirements of industrial robot applications. For the development of service robots, the use and integration of research results obtained in the autonomous robot field is much more necessary than for the development of robots used in manufacturing. Both, high autonomy during service performance and simple system access, which also means flexible programming or user-friendly system control is desired over an easily operated man/machine interface. In this paper, properties of service robots are defined and some similarities and differences between service robots and fully autonomous robots are explained. The enhancement of an existing autonomous assembly robot, which is made to be a flexible service robot for industrial environments, is considered. The paper concludes with a running experiment, which shows how this robot prototype is used for different tasks in a manufacturing line.< >
In this paper, a fuzzy environment includes obstacles in the vicinity of robot motion, which cannot be modelled exactly or are entirely unknown, and a vague description of the relationship between the robot and the ob...
详细信息
In this paper, a fuzzy environment includes obstacles in the vicinity of robot motion, which cannot be modelled exactly or are entirely unknown, and a vague description of the relationship between the robot and the obstacles. An integrated concept for solving the problem of motion planning and control of robots in fuzzy environments is proposed. First, critical points for the desired motion are found in a connectivity network on the boundary of static obstacles. By considering the degree of uncertainty of the obstacles, the local geometry, the available free space and the path shape, these points are further adjusted to form subgoals which reliably decide the global motion direction. During on-line motion execution, a fuzzy controller evaluates sensor data, realizes the motion towards subgoals and avoids local unexpected collisions. Simulations with mobile robots show some control results using this concept.< >
This paper introduces into the general problem of manufacturing, discusses the impact and consequences of the growing internationalisation of markets and gives an overview of the trends in key technologies of manufact...
详细信息
This paper introduces into the general problem of manufacturing, discusses the impact and consequences of the growing internationalisation of markets and gives an overview of the trends in key technologies of manufacturing systems. Furthermore, this paper discusses especially the need for virtual factory concepts and intelligent manufacturing components for future CIM systems. The intelligence of the subsystems is required in large-scale manufacturing systems to master the problems that will result from the system’s complexity.
作者：
M. KaiserUniversity of Karlsruhe
Department of Computer Science Institute for Real-Time Computer Systems & Robotics Prof. Dr.-Ing. U. Rembold and Prof. Dr.-Ing. R. Dillmann D-76128 Karlsruhe Germany
This paper presents results regarding the Application of time-Delay Neural Networks (TDNNs), up to now mainly used in speech recognition, for control tasks. A set of examples taken from a model-based robot controller ...
详细信息
This paper presents results regarding the Application of time-Delay Neural Networks (TDNNs), up to now mainly used in speech recognition, for control tasks. A set of examples taken from a model-based robot controller is used to validate the suitability of the TDNN and to show its superiority to standard multilayer perceptrons. Afterwards, a new algorithm is presented that shows how the inherent capability of the TDNN to deal with time-variant signals can be employed to directly generate a TDNN from a PID control law. This synthesized neural controller is operational from the very beginning and can be tuned on-line using existing learning techniques. The advantages of this design procedure are shown for a simple control task.
暂无评论