We are developing a control assistant system for a robotic wheelchair as a guide robot. This system detects the head pose and gaze direction of the user and recognizes a position and surrounding environment using sens...
详细信息
ISBN:
(纸本)0780378660
We are developing a control assistant system for a robotic wheelchair as a guide robot. This system detects the head pose and gaze direction of the user and recognizes a position and surrounding environment using sensors and a map. Since the system can detect where the user is looking from the measurements, it can estimate attentions of the user on the wheelchair. Experimental results prove that the user's intentions and attentions are related with the duration of gaze and can be distinguished by the information which our robotic wheelchair system can measure.
This paper presents an event-based hybrid system approach for the motion planning and control of mobile robot systems. The ability of dealing with unexpected events is one of the important aspects of robot intelligenc...
详细信息
ISBN:
(纸本)0780378660
This paper presents an event-based hybrid system approach for the motion planning and control of mobile robot systems. The ability of dealing with unexpected events is one of the important aspects of robot intelligence. Robotic systems can obtain environmental information from sensors and respond to environmental information by making task decisions. According to the task decisions, the system is able to modify the original planned path and control the robot to execute the task autonomously. The event based hybrid system model has three layers, one continuous layer, and two discrete layers. The hybrid system model enables the robot system to make decisions and modify original path plans. Experimental results verified the proposed approach.
In this paper we propose a force and position controller for a robot manipulator using a neurocontroller (NC) with genetic algorithm (GA) based training. It is very difficult to design the controller which applies bot...
详细信息
ISBN:
(纸本)0780378660
In this paper we propose a force and position controller for a robot manipulator using a neurocontroller (NC) with genetic algorithm (GA) based training. It is very difficult to design the controller which applies both force and position control to the robot manipulator. We use a simple three layered neural network as the controller, and the training method of the NC is GA based. Inputs to the NC are errors of the position and force. Furthermore, we input the integral information of the position error to the NC because it eliminates the steady-state position error. Simulation shows that the proposed NC has better performance for both position and force control than the conventional neural network, for the robot manipulator.
A method of fuzzy multi-layer synthetic evaluation of economic benefit of enterprise is proposed, which applies artificial neural network to analyze the influence coefficients of evaluation indexes of economic benefit...
详细信息
ISBN:
(纸本)0780378660
A method of fuzzy multi-layer synthetic evaluation of economic benefit of enterprise is proposed, which applies artificial neural network to analyze the influence coefficients of evaluation indexes of economic benefit. In this way, many subjective factors involved can be avoided and so the economic benefit of enterprise can be analyzed and evaluated more objectively and justly. The presented method is very simple and easy to implement. A practical example is also given and the results verify the validity of the method.
PC-based immersion-type display integrated with a motion capture system as well as a 3D dynamic simulator has been successfully constructed in our laboratory, as a first universal development environment of human inte...
详细信息
ISBN:
(纸本)0780378660
PC-based immersion-type display integrated with a motion capture system as well as a 3D dynamic simulator has been successfully constructed in our laboratory, as a first universal development environment of human interactive robot within Japan. This system makes it possible for us to design and examine the next generation of human interactive robot easily and safely. Experiments of a virtual robot interacts with human and performs dynamic motion show the effectiveness of our system.
It is required to adapt to the change of the dynamic characteristics in real-time so that robotics systems can achieve highspeed and high-accuracy motion. In the Model Reference Adaptive control schemes (MRAC), a mode...
详细信息
ISBN:
(纸本)0780378660
It is required to adapt to the change of the dynamic characteristics in real-time so that robotics systems can achieve highspeed and high-accuracy motion. In the Model Reference Adaptive control schemes (MRAC), a model with short time-constant must be chosen to realize fast response. However, it takes long time to adapt to the model. Thus, a new approach for MRAC was proposed. In order to improve the transient behavior, the main idea of the new algorithm is the introduction of the state feedback to the model, and the availability was verified on the first-order systems. In this paper, the proposed methodology is extended to the second-order systems. Simulations show that the efficiency of this proposed method was verified.
The object of this paper is to give a guide for designing the human-robot collaborative control system attaching importance to maneuverability of the operator. The operative "feel" is quantitatively evaluate...
详细信息
ISBN:
(纸本)0780378660
The object of this paper is to give a guide for designing the human-robot collaborative control system attaching importance to maneuverability of the operator. The operative "feel" is quantitatively evaluated using the norm of input-output signal obtained from the sensors during operation. As an example of the human-robot collaborative system, the subjective operative "feel" of the operator is qualitatively analyzed during the sine wave following task using Mink operation arm. In addition, the control performance of the operator is examined from the viewpoint of R. control using the measurement data during the collaborative operation. As a result, it was suggested that the operator executes the given task while adequately reforming the sensitivity function and complementary sensitivity function of the closed loop system of the collaborative system. Use of this method enables design of the control system taking into consideration the operative "feel" of maneuverability.
In this paper, a fuzzy logic scheme is developed to improve the performance of a magnetic bearing control system. The developed fuzzy logic strategy is utilized in the non-linear control of a dual-acting magnetic bear...
详细信息
ISBN:
(纸本)0780378660
In this paper, a fuzzy logic scheme is developed to improve the performance of a magnetic bearing control system. The developed fuzzy logic strategy is utilized in the non-linear control of a dual-acting magnetic bearing actuator system. The mathematical model of a dual acting magnetic bearing axis has been developed. The non-linearity in this system is due to the relationship between the forces generated in the electromagnetic actuator and the coil current and the air gap between the rotor and the stator. Nonlinearities in magnetic bearing systems limit control effectiveness and the region of stable performance. The model is used for dynamic simulation purposes and it is not directly used in the fuzzy controller design. Active magnetic bearing with adaptive fuzzy control showed a good improvement in step response compared to a linear PID or a steady state controller. With the presented fuzzy logic based strategy, nonlinear controllers for nonlinear applications can be designed with little effort.
In this paper we use an evolutionary algorithm to evolve paths using robot velocity profiles from an initial configuration to a configuration behind the ball. Physical conditions for wheel lift are incorporated as wel...
详细信息
In this paper, we develop a direct adaptive control framework for MIMO linear uncertain systems with exogenous bounded disturbances and l(2) Disturbances. The proposed adaptive controller addresses adaptive stabilizat...
详细信息
ISBN:
(纸本)0780378660
In this paper, we develop a direct adaptive control framework for MIMO linear uncertain systems with exogenous bounded disturbances and l(2) Disturbances. The proposed adaptive controller addresses adaptive stabilization and disturbance rejection. For bounded energy l(2) disturbances the proposed method guarantees a nonexpansivity constraint on the closed-loop input-to-states map. The framework is Lyapunov-based and the adaptive laws are characterized by Kronecker calculus. The only assumption is reachability of the pair (A, B). Finally, several numerical examples axe provided to demonstrate the efficacy of the proposed frameworks.
暂无评论