Future applications in automation of non-destructive disassembly processes - necessary and important for re-use of components - require highly sensorized and dexterous robot systems. The main elements of the presented...
详细信息
Future applications in automation of non-destructive disassembly processes - necessary and important for re-use of components - require highly sensorized and dexterous robot systems. The main elements of the presented system are a disassembly sequence planner using special elementary disassembly operations, a redundant hand-arm-system with fifteen degrees of freedom supplied by a six-axes robot and a three-fingered gripper, and a vision system used for offline grasp and motion planning as well as for online supervision. Besides a description of the overall system structure and explanation of the underlying ideas for special disassembly operations, the presentation of first results and experiences from disassembling some parts of a video camera recorder will be one of the centred points to be discussed.
This work presents an associative datafield structure that has been developed for automotive control applications by the Institute of control Engineering, department of control systems theory and robotics at the Techn...
详细信息
This work presents an associative datafield structure that has been developed for automotive control applications by the Institute of control Engineering, department of control systems theory and robotics at the Technical University of Darmstadt and the Robert Bosch GmbH. In contrast to the state-of-the-art lattice-like datafields, the new system permits the modelling of multidimensional nonlinear process and/or controller characteristics with respect to computational performance and storage capacity provided by automotive control units. Furthermore, the associative datafield allows the compensation of wear and tear and manufacturing tolerances by learning, i.e. online adaptation of its contents. The paper describes the principles of the associative datafield and different update algorithms. Results of simulations using realistic data from car engines are discussed.< >
作者:
J. MatthiesenTechnical University of Darmstadt
Control Systems Theory and Robotics Department. headed by Prof Dr. rer. nat. H. Tolle Landgraf-Georg-Str. 4 D 64283 Darmstadt. Germany
Future space robot generations will replace astronauts in deep space missions and routine operations. They will use tools, perform assembly, disassembly and handling tasks for maintenance and repair purposes, among ot...
详细信息
Future space robot generations will replace astronauts in deep space missions and routine operations. They will use tools, perform assembly, disassembly and handling tasks for maintenance and repair purposes, among others. A key feature of autonomous, task-level commandable maintenance robots is a valid and complete representation of an application's task space for planning and optimizing a rough action sequence facing a specific sensorially classified situation. This paper shows such a representation for a robot based automated material science experiment setup und proposes a method of analysis by which a valid and complete task space model can be obtained. Results of practical experiments with a terrestrial laboratory mock-up using the novel representation scheme are presented as well.
Learning controlsystems are expected to have several advantages over conventional approaches when dealing with complex, high-dimensional processes. One example is the task of controlling grasping operations of a mult...
详细信息
Learning controlsystems are expected to have several advantages over conventional approaches when dealing with complex, high-dimensional processes. One example is the task of controlling grasping operations of a multifingered, mul-tijoined robot gripper, which has been designed and implemented at our robotics lab (the Darmstadt-Hand). The Advanced Gripper control with Learning Algorithms -AGRICOLA- presented in this paper is able to maintain a stable grasp even if disturbances are applied. Also it works for objects of different sizes for which the grasping has not been learned. Compared to the conventional stiffness approach the performance of the learning system is equal but the design is much easier, since less knowledge about the gripper-hardware has to be taken into account. The main part of the learning control loop is an associative memory storing the grasping behaviour as determined by the choice of an objective function.
Learning controlsystems are expected to have several advantages over conventional approaches when dealing with complex, high-dimensional processes. One example is the task of controlling grasping operations of a mult...
详细信息
Learning controlsystems are expected to have several advantages over conventional approaches when dealing with complex, high-dimensional processes. One example is the task of controlling grasping operations of a multifingered, mul-tijoined robot gripper, which has been designed and implemented at our robotics lab (the Darmstadt-Hand). The Advanced Gripper control with Learning Algorithms-AGRICOLA- presented in this paper is able to maintain a stable grasp even if disturbances are applied. Also it works for objects of different sizes for which the grasping has not been learned. Compared to the conventional stiffness approach the performance of the learning system is equal but the design is much easier, since less knowledge about the gripper-hardware has to be taken into account. The main part of the learning control loop is an associative memory storing the grasping behaviour as determined by the choice of an objective function.
A three fingered, multijointed robot gripper for experimental use is presented. The mechanics as well as the control architecture are designed for this special purpose. The gripper system provides the basic means in t...
详细信息
A three fingered, multijointed robot gripper for experimental use is presented. The mechanics as well as the control architecture is designed for this special purpose. The gripper system provides the basic means in te...
详细信息
A three fingered, multijointed robot gripper for experimental use is presented. The mechanics as well as the control architecture is designed for this special purpose. The gripper system provides the basic means in terms of position and force control to perform experiments about grasping and object motion in a useful way. The gripper can be used to develop and evaluate different approaches of stable grasping and object manipulation. Results of the control of the gripper on joint level, the Cartesian behaviour of the fingers and some experiences with the grasping and manipulation experiments using the presented system are reported.< >
A special active compliance law is presented as the feedback element in a non-master/slave (i.e. symmetric) coordination strategy with explicit force distribution for robots with multiple cooperating arms. The method ...
详细信息
暂无评论