The principles for the design of the switched reluctance motor drive are presented using a three-phase 12/8 structure switched reluctance motor drive for the robot joint as a example. The design can be done from the s...
详细信息
The principles for the design of the switched reluctance motor drive are presented using a three-phase 12/8 structure switched reluctance motor drive for the robot joint as a example. The design can be done from the systematic point of view, considering the motor, power converter and control strategy as a whole. The output equation relating to the relationship between the structure parameters and the electric loads is derived. The equation of the turn numbers of the phase winding is also considered. The design procedure is given. Some of the interfaces of the intelligent computational software package used for the Windows 9/spl times/ (in English) are given. The design is checked by the prototype. The accuracy is checked by the experimental measurement of the developed prototype. It is shown that the design has the advantages in practice and high precision.
Proposes a kind of population diversity (PD) measurements and their computational formulas. A quantitative relation between them is proved. The gene and individual are considered as separate units to investigate PD. A...
详细信息
Proposes a kind of population diversity (PD) measurements and their computational formulas. A quantitative relation between them is proved. The gene and individual are considered as separate units to investigate PD. A fuzzy genetic algorithm is designed using PD measurements developed, in which the fuzzy controller is used to adjust crossover rate and mutation rate dynamically to maintain the proper PD during the GA's operation. Experiments prove that premature convergence can be overcome effectively by controlling PD during the GA's operation.
Motivated by the autonomous developmental process of higher animals and humans from infancy to adulthood, the objective of our SAIL developmental robot project is to investigate how to enable a robot to develop its co...
详细信息
Motivated by the autonomous developmental process of higher animals and humans from infancy to adulthood, the objective of our SAIL developmental robot project is to investigate how to enable a robot to develop its cognitive and behavioral skills through online, real-time interactions with the environment. In other words, our goal is to enable a robot to learn autonomously from real-world experiences. The work presented here focuses on the development of its auditory behaviors. Both simulation results and experiments on real robot are reported.
In this work, we describe a framework for predicting future positions and orientation of moving obstacles in a time-varying environment using Kalman filtering techniques. No constraint are placed on the obstacles moti...
详细信息
In this work, we describe a framework for predicting future positions and orientation of moving obstacles in a time-varying environment using Kalman filtering techniques. No constraint are placed on the obstacles motion. The proposed algorithm can be used in a variety of applications, one of which is robot motion planning in time varying environments. The advantage of using this model compared to reported ones in the literature is it's ability to start the prediction process from the first time step without the need to wait for few time steps before starting the prediction process. Early experimental results are very encouraging.
This paper discusses methods of autonomous environment recognition and action by a robotic manipulator working with dynamic interaction to the environment, e.g., assembling. A method automatically recognizes the conta...
详细信息
This paper discusses methods of autonomous environment recognition and action by a robotic manipulator working with dynamic interaction to the environment, e.g., assembling. A method automatically recognizes the contacting situation with the work site from the sensor outputs and the robotic manipulator motion. The autonomous recognition then discriminates the constraint conditions at manipulator hand using the self-organizing map that is a kind of unsupervised learning of neural networks. The discrimination of the constraint conditions is successfully demonstrated by a numerical simulation of a 3-link SCARA type manipulator. Another is for the cognitive action. Some approaches based on the reinforcement learning are proposed. They give models of cognitive actions and approaches to so-called frame problem obstructing efficient learning and action.
In animated simulation of human-robot coordination, the voice command is a useful feature to free the human operator's hand during the compliance control stage. The purpose of developing the simulation program is ...
详细信息
In animated simulation of human-robot coordination, the voice command is a useful feature to free the human operator's hand during the compliance control stage. The purpose of developing the simulation program is to perform the simulation before any physical experiments with robot hardware are conducted. The outcome of the simulation may give an insight into any unexpected interactions which may endanger the human operator as well as equipment. The human operator may learn from these experiences and be aware of the problems which may appear when physical experiments are performed.
Space and underwater vehicles with robotic manipulators can severely tax the capability of conventional control architectures. In this report, the control system and operator interface for a submersible vehicle used i...
详细信息
Space and underwater vehicles with robotic manipulators can severely tax the capability of conventional control architectures. In this report, the control system and operator interface for a submersible vehicle used in microgravity simulation are examined. The architecture of the onboard controller and the control station are described as well as the vehicle/operator communications. The control approach is demonstrated on the Ranger Neutral Buoyancy Vehicle (NBV) currently in operation at the Space Systems Laboratory at the University of Maryland.
Simulation tools now occupy a place of particular importance in many fields of engineering. Some of these tools have come to be regarded as standard and/or as a point of departure for the replication of results obtain...
详细信息
Simulation tools now occupy a place of particular importance in many fields of engineering. Some of these tools have come to be regarded as standard and/or as a point of departure for the replication of results obtained in scientific papers. The present paper describes the use of one of these tools, Matlab/Simulink, used in order to simulate and validate in real time the results concerning the guidance, navigation and control techniques applied to a low cost mobile platform.
We present an approach that allows a robot to learn task representations from its own experiences of interacting with a human. The robot follows a human teacher and maps its own observations of the environment into a ...
详细信息
We present an approach that allows a robot to learn task representations from its own experiences of interacting with a human. The robot follows a human teacher and maps its own observations of the environment into a representation of what has constituted the human's demonstration. The robot then builds a representation of the experienced task in the form of a behavior network. To enable this we introduce an architecture that extends the capabilities of behavior-based systems by allowing the representation and execution of complex and flexible sequences of behaviors. We demonstrate this architecture in a set of experiments in which a mobile robot learns representations for multiple tasks and is able to execute the tasks, even in changing environments.
We study the target tracking problem using multiple, environment-embedded, stationary sensors and mobile robots. An architecture for robot motion coordination is presented which exploits a shared topological map of th...
详细信息
We study the target tracking problem using multiple, environment-embedded, stationary sensors and mobile robots. An architecture for robot motion coordination is presented which exploits a shared topological map of the environment. The stationary sensors and robots maintain region-based density estimates which are used to guide the robots to parts of the environment where unobserved targets may be present. Experiments in simulation show that the region-based approach works better than a naive target following approach when the number of targets in the environment is high.
暂无评论