Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to optimize. Traditionally, imitation learning in RL has been used to overcome this problem. Unfortunately, hitherto imitation learning methods tend to require that d...

This paper deals with the design of a nonlinear observer for the inverted pendulum. The observer uses the standard structure of the linear observer with the linear model replaced by a nonlinear model. Nominal observer gains are determined from a linearized model. This model is also used to find a compromise between robustness and performance. The stability of the observer is then discussed and ...

A physical control problem is studied with the p methodology. The issues of modelling, uncertainty modelling, performance specification, controller design and laboratory implementation are discussed. The laboratory experiment is a double inverted pendulum placed on a cart. The limitations in the system with respect to performance are the limitation in the control signal and the limitation of th...

During human and animal locomotion, the dynamics of the body can be represented with the help of simplified biomechanical models, such as the spring-mass model (often described as spring-loaded inverted pendulum, SLIP model). In this model, it is assumed that the force generated by each limb resembles that of a linear spring. Furthermore, it is assumed that force generated by the leg mainly act...

Seventy-five young, healthy adults completed a lateral weight-shifting activity in which each shifted his/her center of pressure (CoP) to visually displayed target locations with the aid of visual CoP feedback. Each subject's CoP data were modeled using a single-link inverted pendulum system with a spring-damper at the joint. This extends the simple inverted pendulum model of static balance in ...

The balancing of an inverted pendulum by moving a cart along a horizontal track is a classic problem in the area of automatic control. In this paper two Neural Network controllers to swing a pendulum attached to a cart from an initial downwards position to an upright position and maintain that state are described. Both controllers are able to learn the demonstrated behavior which was swinging u...

 The paper presents a hybrid system controller, incorporating a neural and an LQG controller. The neural controller has been optimized by genetic algorithms directly on the inverted pendulum system. The failure-free optimization process stipulated a relatively small region of the asymptotic stability of the neural controller, which is concentrated around the regulation point. The presented hyb...

This paper presents the application of discrete-time variable structure control with sliding mode based on the ‘reaching law’ method for robust control of a ‘simple inverted pendulum on moving cart’ a standard nonlinear benchmark system. The controllers designed using the above techniques are completely insensitive to parametric uncertainty and external disturbance. The controller design is car...

Two-wheeled balancing robots based on inverted pendulum configuration which relies upon dynamic balancing systems for balancing and maneuvering. The idea of a mobile inverted pendulum robot has focused in recent years and has attracted interest from control system researchers worldwide, research on a two-wheel inverted pendulum, which commonly known as the self-balancing robot. In this, the DC ...

In this paper, a nonlinear model predictive swing-up and stabilizing sliding controller is proposed for an inverted pendulum-cart system. In the swing up phase, the nonlinear model predictive control is formulated as a nonlinear programming problem with energy based objective function. By solving this problem at each sampling instant, a sequence of control inputs that optimize the nonlinear obj...