Andrzej Burghardt

Fuzzy Sensor-Based Navigation with Neural Tracking Control of the Wheeled Mobile Robot

Navigation of the wheeled mobile robot in the unknown environment with simultaneous realisation of the generated trajectory, is one of the most challenging and up to date problems in the modern mobile robotics. In the article a new approach is presented to a collision-free trajectory generating for a wheeled mobile robot, realised in a form of the hierarchical control system with two layers. The first layer is a tracking control system, where the Neuro-Dynamic Programming algorithm in the Dual Heuristic Dynamic Programming configuration was applied. The second layer is a trajectory generator where the Fuzzy Logic systems were used. The presented control system generates and realises trajectory of the wheeled mobile robot within the complex task of goal-seeking and obstacle avoiding. The proposed hierarchical control system works on-line, its performance was verified using the wheeled mobile robot Pioneer 2-DX.

Reinforcement Learning in Discrete Neural Control of the Underactuated System

The article presents a new approach to the problem of a discrete neural control of an underactuated system, using reinforcement learning method to an on-line adaptation of a neural network. The controlled system is of the ball and beam type, which is the nonlinear dynamical object with the number of control signals smaller than the number of degrees of freedom. The main part of the neural control system is the actor-critic structure, that comes under the Neural Dynamic Programming algorithms family, realised in the form of Dual Heuristic Dynamic Programming structure. The control system includes moreover the PD controller and the supervisory therm, derived from the Lyapunov stability theorem, that ensures stability. The proposed neural control system works on-line and does not require a preliminary learning. Computer simulations have been conducted to illustrate the performance of the control system.

Conventional and fuzzy force control in robotised machining

This article presents an application of the hybrid position-force control of the robotic manipulator with use of artificial neural networks and fuzzy logic systems in complex control system. The mathematical description of the manipulator and a closed-loop system are presented. In the position control were used the PD controller and artificial neural networks, which compensate nonlinearities of the manipulator. The paper presents mainly the application of various strategies of the force control. The force control strategies using conventional controllers P, PI, PD, PID and fuzzy controllers are presented and discussed. All of the control methods were verified on the real object in order to make a comparison of a control quality.

Robotic Automation of the Turbo-Propeller Engine Blade Grinding Process

Robotic automation of industrial processes in terms of the adaptation of the robot path to changing external conditions has recently been one of the main subjects of research and implementation studies. The presented study involved trailing plane grinding the turbine blades. The suggested automated station comprises an IRB 140 robot handling the processed element, grinding tool and an IRB 1600 robot with a 3D scanning head installed. The presented robotic automation solutions may be used for finishing operations on blades constituting elements of aircraft engines, power generating turbines and wind turbines.

The application of virtual prototyping methods to determine the dynamic parameters of mobile robot

Abstract The paper presents methods used to determine the parameters necessary to build a mathematical model of an underwater robot with a crawler drive. The parameters present in the dynamics equation will be determined by means of advanced mechatronic design tools, including: CAD/CAE software andMES modules. The virtual prototyping process is described as well as the various possible uses (design adaptability) depending on the optional accessories added to the vehicle. A mathematical model is presented to show the kinematics and dynamics of the underwater crawler robot, essential for the design stage.

Optimization of Process Parameters of Edge Robotic Deburring with Force Control

Abstract The issues addressed in the paper present a part of the scientific research conducted within the framework of the automation of the aircraft engine part manufacturing processes. The results of the research presented in the article provided information in which tolerances while using a robotic control station with the option of force control we can make edge deburring.

Accomplishing Tasks in Reaching the Goal of Robot Formation

The article presents a hierarchical steering system for developing mobile robots and fulfils the established goal in unknown surroundings. The task was carried out with reference to a cooperative combination of elementary behaviour patterns such as finding destination and avoiding obstacles, and was generated using the Kohonen neural network. The paper has assumed formation shape and considered the right of steering other robots in the formation process. Finally, the proposed solution has been verified.

Artificial Intelligence Algorithms in Behavioural Control of Wheeled Mobile Robots Formation

The paper presents an innovative approach to the problem of the wheeled mobile robots formation behavioural control with use of artificial intelligence algorithms. The control task is solved by application of adaptive dynamic programming algorithms in the hierarchical control system, that generates the collision free trajectories in the unknown 2D environment for all agents in the formation, and realises generated trajectories using tracking control algorithms. The hierarchical control system consists of three layers: the trajectory generator, the wheeled mobile robots formation control system and tracking control systems for individual agents. The trajectory generator presents the new approach to the behavioural control, where one neural dynamic programming algorithm generates the behavioural control signals that make possible to compute the trajectory for realisation of the complex task, which is a composition of two individual behaviours: “goal-seeking”and “obstacle avoiding“. Computer simulations have been conducted to illustrate the path planning process.

Adaptive Critic Designs in Control of Robots Formation in Unknown Environment

In the presented article a new approach to a collision-free trajectory generating for a wheeled mobile robots formation with Adaptive Critic Designs and Fuzzy Logic algorithm, is proposed. The presented hierarchical control system consists of a trajectory generating algorithm based on a conception of reactive navigation of the wheeled mobile robots formation in the unknown 2D environment, a control system that generates individual trajectories for all agents in formation, and agents tracking control systems. A strategy of reactive navigation is developed including two main behaviours: a obstacle avoiding behaviour and a goal-seeking behaviour, realised in a form of Adaptive Critic Design algorithms. These individual behaviours are combined using two approaches: cooperative connection approach and the fuzzy combiner, that determines influence of the individual behaviours on the trajectory generation process, according to the environment conditions. Computer simulations have been conducted to illustrate the process of path planning in different environment conditions.

Neuro-Dynamic Programming in Control of the Ball and Beam System

This paper presents a new approach to the control problem of the ball and beam system, with a Neuro-Dynamic Programming algorithm implemented as the main part of the control system. The controlled system is included in the group of underactuated systems, which are nonlinear dynamical objects with the number of control signals smaller than the number of degrees of freedom. This results in problems in the formulation of a stable control algorithm, that guarantees stabilization of the ball in the desired position on the beam. The type of ball and beam material has a noticeable influence on the difficulties in stabilization of the ball, because of a smaller rolling friction and big inertia of the used metallic ball in comparison to other, for example made of non-metallic materials. The main part of the proposed discrete control system is the Neuro-Dynamic Programming algorithm in a Dual-Heuristic Dynamic Programming configuration, realized in a form of two neural networks: the actor and the critic. Neuro-Dynamic Programming algorithms use the Reinforcement Learning idea for adaptation of artificial neural network weights. Additional elements of the control system are the PD controller and the supervisory term, that ensures stability of the closed system loop. The control algorithm works on-line and does not require a preliminary learning phase of the neural network weights. Performance of the control algorithm was verified using the physical system controlled by the dSpace digital signal processing board.