Here, an adaptive radial basis function (RBF) neural network (NN) backstepping controller is proposed for a class of input-constrained flexible joint robotic manipulators represented by strict-feedback form with unknown terms, external stochastic disturbance, and output disturbance. The approach robust against both deterministic uncertainties disturbances copes the control input amplitude satur...

Abstract It is complex and time-consuming for obtaining accurate dynamics of industrial robots. The flexibility the joint not only increases adverse effects nonlinear factors, but also makes controller design robot significantly difficult. In order to improve performance robots containing flexibility, cooperative learning (COL) theory proposed in this paper. Based on theory, a model-free intell...

The process of controlling a Flexible Joint Robot Manipulator (FJRM) requires additional sensors for measuring the state variables flexible joints. Therefore, taking elasticity into account adds lot complexity as all must be taken during control process. This paper proposes nonlinear observer that controls FJRM, without requiring equipment states. equations are derived in detail FJRM where nonl...

New generation robots, meant for physical human robot interactions, are no longer rigid; it has become soft in terms of introduction of considerable flexibility at the actuated joints, flexibility of the links and in terms of compliant coverings. Safety requirement becomes primary in situations where physical interactions occur, calling for compliance; but accuracy and control bandwidth get com...

A novel approach to the control of a single joint-single flexible link robot is proposed and experimentally evaluated. The control is completely signal based, and relies on joint trajectory pre-planning plus collocated vibration control of the flexible link through piezoelectric actuation. Trajectory pre-planning is a well known strategy for avoiding link vibrations during maneuvers, however it...

Inverse flexible dynamics control (IFDC) and fuzzy logic system adaptive control (FLSAC) strategies are used to track the end effector of a flexible space robot with sensors collocated at the joints, noncollocated at the end effector and 0.5m from the elbow joint on link 2. Collocated joint sensors satisfy hyperstability conditions but fail to capture nonminimum phase (NMP) response that genera...

Index Terms—sliding mode control, uncertainty and disturbance estimation, flexible joint. Abstract—This paper proposes sliding mode control based on uncertainty and disturbance estimator (UDE), for trajectory tracking control of flexible joint robotic system. UDE is used to estimate plant uncertainty and disturbances. The controller does not requires knowledge of plant uncertainty and external ...