Accurate Robot Positioning using Corrective LearningOutlineMotivationThe 2 Link ManipulatorKinematicsProblem with Inverse KinematicsCorrective LearningCorrective Learning (cont’d)Experimental SetupResults & ConclusionsFuture WorkAccurate Robot Positioning using Corrective LearningRam SubramanianECE 539 Course ProjectFall 2003Outline MotivationTwo Link ManipulatorsKinematicsCorrective LearningExperimental SetupResults & ConclusionMotivationThe human motor control mechanism works by initiating a motion in the general direction of the target. Then subsequently produces corrective movements to reach the target with a good degree of accuracy.The 2 Link ManipulatorSimple kinematicsEasy to setup control parametersEasy to Model1 2link2link1Kinematics The forward kinematics of a robot are used to determine the position of the end effecter for a given set of joint anglesThe Inverse kinematics are used to determine appropriate joint angles for a particular end effecter position.Problem with Inverse KinematicsMapping from Cartesian space of the end effecter to the joint angles of the robot is –Non linear–Potentially degenerate (leading to multiple solutions)This causes complications when controlling the manipulator. Modeling other parameters like friction etc. increases the non linearity of the system furtherCorrective LearningThe Learning Process–Initiate a movement–Determine the position error between the end effecter and the target–Adjust the joint angles based on a heuristic–Repeat until the target position is reachedCorrective Learning (cont’d)Once the joint angles corresponding to a particular target position is learned, subsequent visits to the same target point use the already learned values. This technique allows the positioning of the robot without accurate knowledge of all the link parametersExperimental SetupLearnerInitial PositionController Two Link RobotTargetPositionError(1,2 )(x,y)(x,y)(1, 2)Look upTableResults & ConclusionsThe average error between the final position of the robot end effecter and the target was found to be 3.21, with a standard deviation of 0.8 .The first reach to every target position takes one order of magnitude longer in time than the subsequent reaches to the same target position.Future WorkComparison between this learning technique, a model developed with a Back Propagation neural network and the computed torque technique.Adapt the learning technique for manipulators with larger number of
View Full Document