A fuzzy-energy regions based switching method has been studied to control Underactuated manipulators. The switching rule of this method was designed on sub-energy regions with several boundary curves represented by fu...
A fuzzy-energy regions based switching method has been studied to control Underactuated manipulators. The switching rule of this method was designed on sub-energy regions with several boundary curves represented by fuzzy reasoning. However, it was pointed out, through some simulations, that the number of switching times for partially stable controllers increased according to the initial conditions and design parameters. The present paper introduces a novel energy definition in the sense of monotonic decreasing and develops the corresponding switching rules with such energy, to reduce the number of switching times. The effectiveness of the proposed approach is verified through some simulations for a 2-link Underactuated manipulator.
An emotion-based task sharing approach has been developed for a cooperative multiagent robotic system. A stochastic emotion model based on Markov theory is adopted to conform the emotional state of agents while perfor...
详细信息
An emotion-based task sharing approach has been developed for a cooperative multiagent robotic system. A stochastic emotion model based on Markov theory is adopted to conform the emotional state of agents while performing task. The task assignment and then task sharing among the agents depend on the emotional state of each agent. Different emotional traits are considered as important factors for task sharing which are obtained by updating the state transition matrix of stochastic model. Perception of stimuli has an impact on emotion inducing factors and thus, affects on emotion dynamics. A Matlab based simulation is performed with the developed emotional approach to analyze the behavior of the agents with the emotional capability.
This paper presents a method of intelligent perception assist (IPA) with optimum force vector modification for an upper-limb exoskeleton robot to assist the perception of the user to interact with environment in addit...
详细信息
This paper presents a method of intelligent perception assist (IPA) with optimum force vector modification for an upper-limb exoskeleton robot to assist the perception of the user to interact with environment in addition to power-assist. The exoskeleton assists not only the motion but also the perception of the user. In the case of perception assist, the exoskeleton assists user to interact with the environment by monitoring the userpsilas interaction with the environment. The exoskeleton is equipped with a sonar sensor and a stereo camera to gain information on the userpsilas interaction with the environment. When the user interacts with the environment, if the exoskeleton found any problem in the userpsilas motion, the optimum force vector modification (i.e., the modification of power-assist force vector with the optimum amount of force) is carried out by the exoskeleton to modify the userpsilas motion to solve the problem without giving any uncomfortable feeling to the user due to motion modification. IPA ensures that the userpsilas interaction with the environment can be monitored by the camera all the time by rotating the camera to track the location of the userpsilas hand. The effectiveness of the proposed concept was experimentally evaluated.
A control problem is studied for generating the locomotion pattern of a semi-looper type robot by applying central pattern generators (CPGs), in which such a robot can realize two-rhythm motion and green caterpillar l...
A control problem is studied for generating the locomotion pattern of a semi-looper type robot by applying central pattern generators (CPGs), in which such a robot can realize two-rhythm motion and green caterpillar locomotion depending on the condition of environment. After deriving the dynamical model with two links and one actuator, the simulation of the robot is conducted using a CPG consisting of one van der Pol (VDP) oscillator. A CPG network composed of two VDP oscillators is further constructed to realize four-rhythm motion with three links and two actuators.
An obstacle avoidance method is proposed for quadruped robots by using the combination or switching of fundamental actions, which are composed of four, such as go-straight-on action, detour action, striding action, an...
An obstacle avoidance method is proposed for quadruped robots by using the combination or switching of fundamental actions, which are composed of four, such as go-straight-on action, detour action, striding action, and climbing-over action. The transition of these actions is described in a finite automaton that is understandable visually in two-dimensional plane for our designer compared to any logical description. The external sensor information, provided by a monocular camera, some ultrasonic sensors and some force sensors, are utilized to change the fundamental actions. The effectiveness of the proposed method is demonstrated with some experiments.
The estimation of human behaviors by robots is one of key technologies in an environment in which humans and robots coexist. In this paper, a method is proposed for promptly estimating the behavioral targets by applyi...
The estimation of human behaviors by robots is one of key technologies in an environment in which humans and robots coexist. In this paper, a method is proposed for promptly estimating the behavioral targets by applying a fuzzy neural network (FNN). Here, inputs to the FNN are the human velocity, the angle of the human relative to an object, and the distance between the human and an object, whereas outputs are confidences that each object among all candidates is selected to be an intended object. The resultant human behavior can be estimated as a combination of the human action estimation and the behavioral target estimation.
This paper presents an alternative solution to simultaneous localization and mapping (SLAM) problem by applying a fuzzy Kalman filter using a pseudolinear measurement model of nonholonomic mobile robots. Takagi-Sugeno...
This paper presents an alternative solution to simultaneous localization and mapping (SLAM) problem by applying a fuzzy Kalman filter using a pseudolinear measurement model of nonholonomic mobile robots. Takagi-Sugeno fuzzy model based on an observation for a nonlinear system is adopted to represent the process and measurement models of the vehicle-landmark system. The complete system of the vehicle-landmark model is decomposed into several linear models. Using the Kalman filter theory, each local model is filtered to find the local estimates. The linear combination of these local estimates gives the global estimate for the complete system. The simulation results shows that the new approach performs better, though nonlinearity is directly involved in the Kalman filter equations, compared to the conventional approach.
In this paper, we propose an omnidirectional electric wheelchair (OEW). The proposed OEW has four omniwheels for the omnidirectional movement. Two of the omniwheels are arranged to X-axis direction and the other two a...
详细信息
In this paper, we propose an omnidirectional electric wheelchair (OEW). The proposed OEW has four omniwheels for the omnidirectional movement. Two of the omniwheels are arranged to X-axis direction and the other two are arranged to Y-axis direction. By controlling the movement of the omniwheels, the OEW can instantaneously rotate and move in all directions. Hence that, especially in the narrow spaced indoor environment, the omnidirectional nature of the OEW has an advantage over the standard wheelchair. Furthermore, the operatorpsilas posture is used as signal to the OEW. The operatorpsilas posture is measured by a ldquoZabuton sensorrdquo which uses a pressure sensor to measure the pressure distribution. The effectiveness of proposed the system is reflected by the experimental results of the prototype OEW and Zabuton sensor system.
Realization of cooperative behavior in multi-agent system is important for improving problem solving ability. Reinforcement learning is one of the learning methods for such cooperative behavior of agents. In this pape...
详细信息
ISBN:
(纸本)9781424437825
Realization of cooperative behavior in multi-agent system is important for improving problem solving ability. Reinforcement learning is one of the learning methods for such cooperative behavior of agents. In this paper, we consider pursuit problem for multi-agent reinforcement learning with communication between the agents. In our study, the agents obtain communication codes through learning. Here, the codes are rules for communicating appropriate information under various situations. We call the learning of communication codes signal learning. The signal is expressed by bit sequence, and its length is set to be variable. We carried out experiment for performance comparison with varying the signal length from 0 to 4 bits. As a result, it has been shown that, in learning precision, the case of 1 bit or more bits communication outperformed the case of no communication. It also has been shown that 4 bits communication produced the best result among the five cases, while learning with longer signals required much more iterations.
暂无评论