The paper describes a walking robot leg modelling process. A six-legged walking robot — the so-called hexapod is concerned. Each leg consists of three links driven by Hitec HS475HB servo motors. The proposed model is used for testing leg kinematics and dynamics of the robot gait. One can examine a number of walking algorithms. The model includes: the identified description of the servo motors, ...

The Dutch robot soccer team Clockwork Orange is a research project of the Delft University of Technology and the University of Amsterdam. In this project we study multi-robot collaboration, robot vision and robot control. Our research focus, overviewed in this paper, is on automatic calibration for robust colour segmentation, behaviour based robotics, reinforcement trained dribbling with the ba...

This paper features the kinematic modelling of a 5-axis stationary articulated robot arm which is used for doing successful robotic manipulation task in its workspace. To start with, a 5-axes articulated robot was designed entirely from scratch and from indigenous components and a brief kinematic modelling was performed and using this kinematic model, the pick and place task was performed succe...

Cognitive control is a new method for more human like interactive control of autonomous work machines especially service robots. In cognitive control environment modelling, task definition and control are made by the operator and the machine interactively by utilising communication methods, which are easy for the cognition of both parts. Human and machine cognition are fundamentally different w...

The application of Internal Model Control for process control has received much attention during the past decade. In this paper, the application of IMC for robot control is investigated. Although the IMC approach is shown to be more robust as compared to conventional robot control approaches, such as the computed-torque approach, its performance degrades in the presence of large modelling uncer...

In this paper a step toward making a toolbox for industrial robot modelling based on the computer algebra tool Maple is taken. It can be seen as a modelling platform for efficient derivation of the necessary equations for doing, e.g., sensor fusion or state estimation by an Extended Kalman Filter (EKF) algorithm. Forward kinematics is studied and the position and orientation of the robot tool a...

A Hybrid Framework for Mobile Robot Navigation Modelling with Switching State Space Networks

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected data is prediction. If a robot can learn to predict the future, it can use this predictive model to take actions to produce desired outcomes, such as moving a...