Learning Reactive Admittance
نویسندگان
چکیده
In this paper, a peg-in-hole insertion task is used as an example to illustrate the utility of direct as-sociative reinforcement learning methods for learning control under real-world conditions of uncertainty and noise. An associative reinforcement learning system has to learn appropriate actions in various situations through search guided by evaluative performance feedback. We used such a learning system, implemented as a connectionist network, to learn active compliant control for peg-in-hole insertion. Our results indicate that direct reinforcement learning can be used to learn a reactive control strategy that works well even in the presence of a high degree of noise and uncertainty.
منابع مشابه
A Wide Range and Precise Active and Reactive Power Flow Controller for Fuel Cell Power Conditioning Systems A Wide Range and Precise Active and Reactive Power Flow Controller for Fuel Cell Power Conditioning Systems
(Abstract) This dissertation aims to present a detailed analysis of the grid voltage disturbance in frequency domain for the current control design in the grid-tie inverter applications and to propose current control techniques in order to minimize its impact and maximize feasibility of the power conditioning system in distributed generations. Because the grid voltage is constantly changing, th...
متن کاملLearning optimal variable admittance control for rotational motion in human-robot co-manipulation
In this paper the problem of variable admittance control in human-robot cooperation tasks is investigated, considering rotational motion of the robot’s end-effector. A Fuzzy Model Reference Learning algorithm is used to determine online the appropriate virtual damping of the admittance controller with partial state representation of the system. The learning algorithm is trained according to the...
متن کاملVariable Admittance Control Based on Fuzzy Reinforcement Learning for Minimally Invasive Surgery Manipulator
In order to get natural and intuitive physical interaction in the pose adjustment of the minimally invasive surgery manipulator, a hybrid variable admittance model based on Fuzzy Sarsa(λ)-learning is proposed in this paper. The proposed model provides continuous variable virtual damping to the admittance controller to respond to human intentions, and it effectively enhances the comfort level du...
متن کاملAn Optimal Admittance Reactive Force Control for Cooperative Robot Grasping Tasks
In this article it is proposed an optimal admittance algorithm that controls the position of the end effectors in cooperative robot systems or fingers, in case of robotic hands, reactively according to on-line force sensory data. The method is free of in-depth models or sophisticated external sensors. The sensors used are simple and provide only limited and immediate information, nonetheless th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1992