TAILIEUCHUNG - sensor based learning for practical planning of fine motion in robotics

Abstract This paper presents an implemented approach to part-mating of three-dimensional non-cylindrical parts with a 6 DOF manipulator, considering uncertainties in modeling, sensing and control. The core of the proposed solution is a reinforcement learning algorithm for selecting the actions that achieve the goal in the minimum number of steps. Position and force sensor values are encoded in the state of the system by means of a neural network. Experimental results are presented for the insertion of different parts – circular, quadrangular and triangular prisms – in three dimensions. The system exhibits good generalization. | ELSEVIER Information Sciences 145 2002 147-168 INFORMATION SCIENCES AN INTERNATIONAL JOURNAL locate ins Sensor-based learning for practical planning of fine motions in robotics Enric Cervera Angel P. del Pobil Department of Computer Science and Engineering Jaume-I University Castello Spain Received 4 July 2001 received in revised ft m 8 October 2001 accepted 28 November 2001 Abstract This paper presents an implemented approach to part-mating of three-dimensional non-cylindrical parts with a 6 DOF manipulator considering uncertainties in modeling sensing and control. The core of the proposed solution is a reinforcement learning algorithm for selecting the actions that achieve the goal in the minimum number of steps. Position and force sensor values are encoded in the state of the system by means of a neural network. Experimental results are presented for the insertion of different parts -circular quadrangular and triangular prisms - in three dimensions. The system exhibits good generalization capabilities for different shapes and location of the assembled parts. These results significantly cxecnd most of the previous aclfievements m nne motion tasks which frequentlymodel the robot as a polygon translating in the plane in a polygonal environment or do not present actual implemented prototypes. 2002 Elsevier Science Inc. All rights reserved. Keywords Robotics Neural nets Reinforcement learning 1. Introduction We present a practical framework for fine motion tasks particularly cVc insertion of non-cylindrical parts with uncertainty in modeling sensing and control. The approach is based on an algorithm which autonomously learns a Corresponding author. Present address Department of Computer Science and Engineering Jaume-I Castello Spain. E-mail addresses ecervera@ E. Cervera pobil@ . del Pobil . 0020-0255 02 - see front matter 2002 Elsevier Science Inc. All rights reserved. PII S0020-0255 02 00228- 1 148 E. Cernera . del Pobil I

• Cơ khí - Chế tạo máy
• Averaging
• Conservation of mass
• Multiphase flow models
• Multiphase flow notation
• distribution functions
• Dollar cost averaging
• Value averaging
• Retirement plan
• Target terminal wealth
• Value averaging investment strategies
• Impacts of investment horizon
• Weighted local averaging
• Galerkin method
• Euler column
• Free vibration
• Strong nonlinearity
• Modified averaging operator with some applications
• Vietnam Journal of Mechanics
• High order stochastic differential equations using averaging method
• High order stochastic differential equations
• Stochastic differential equations
• The fundamental work of Prof
• Higher order stochastic averaging method
• Mechanical systems having two degrees of freedom
• Mechanical systems having two degrees
• The Fokker Planck
• Two degree of freedom systems
• Non linearity on random vibrations
• The classical first prder stochastic averaging method
• Non linear random vibration systems
• Stochastic averaging method
• Bayesian model averaging
• Economic growth
• Public expenditure
• Explanatory variables included
• Economic theory
• Micro mechanical material models
• Strain softening material models
• The non local continuum theory
• Non local averaging
• Partial differential equations
• Threepoint linkage
• Lower link
• Averaging the lower link sensed forces
• Draft control
• Electro hydraulic systems
• Mechanics of solid
• Doctoral thesis on solid mechanics
• Weighted averaging approach
• Nonlinear vibration
• Bài toán dao động
• Lực tĩnh điện
• Summary of Doctoral Thesis in Solid Mechanics
• Doctoral Thesis in Solid Mechanics
• Nonlinear vibrations
• Nonlinear vibration problem
• Lecture Calculus
• Bài giảng Giải tích
• Averaging things out
• Riemann sum
• Mean value theorem
• Technologies