Chris H. Messom

Master-Slave Control of a Teleoperated Anthropomorphic Robotic Arm with Gripping Force Sensing

This paper details methods of solving problems that are encountered when human beings teleoperate robots. Special emphasis has been given to the ease of operation and some form of force sensation. Through the use of a rigid control rig, fitted to the users arm, it is possible to easily control an anthropomorphic robot arm using a master-slave control methodology. The force being exerted by the arm is measured and fed back to the user who is operating the master unit

Strategy for collaboration in robot soccer

Robot soccer is a challenging platform for multi-agent research, involving topics such as real-time image processing and control, robot path planning, obstacle avoidance and machine learning. The robot soccer game presents an uncertain and dynamic environment for cooperating agents. Dynamic role switching and formation control are crucial for a successful game. The fuzzy logic based strategy described in the paper employs an arbiter which assigns a robot to shoot or pass the ball.

Real-time identification and predictive control of fast mobile robots using global vision sensing

This paper presents a predictive controller for intercepting mobile targets. A global vision system is used to identify fast moving objects and uses a color threshold technique to calculate their position and orientation. The inherent systemic noise in the raw sensor data, as well as vision quantization noise, is smoothed using Kalman filtering before being fed to the controller, and it is shown that this leads to superior accuracy of the controller. The predictive controller is based on the state transition-based control (STBC) technique. As a case study, STBC has been applied to a goalkeepers behavior in robot soccer which includes interception and clearance of ball. Further evaluation of the controller has been done for shooting the ball toward a target position. The system is examined for both stationary and moving objects. It is shown that predictive filtering of rough sensor data is essential to increase the reliability and accuracy of detection, and thus interception, of fast moving objects.

Hough Transform Run Length Encoding for Real-Time Image Processing

This paper introduces a real-time image processing algorithm based on run length encoding (RLE) for a vision based intelligent controller of a humanoid robot system. The RLE algorithms identify objects in the image providing their size and position. A RLE Hough transform is also presented for recognition of landmarks in the image to aid robot localization. The vision system presented has been tested by simulating the dynamics of the robot system as well as the image processing subsystem. The real-time image processing and control algorithms allow the unstable dynamic model of the biped robot to be controlled

Improving predictive control of a mobile robot: Application of image processing and Kalman filtering

This paper discusses a control algorithm for the interception of a mobile target. The application domain is robot soccer in which the target is a ball while the interceptor is a wheeled robot. A case study of a wheeled robot approaching a target in a given direction is presented in detail. A shoot function has been developed, using the proposed algorithm, which calculates the robot wheel velocities to position the robot behind the ball. In order to improve the efficiency of the control, a scaling factor has been introduced which can be optimized so that the robot travels a shorter distance to intercept the target. Since the target is constantly moving, it is imperative that the future position of the target be predicted and used in the control algorithm to calculate the wheel velocities. Kalman filtering has proven to be an effective tool for predicting the target position at the point of interception, several frames ahead and thus improve the accuracy of interception.

Confidence intervals for computational effort comparisons

When researchers make alterations to the genetic programming algorithm they almost invariably wish to measure the change in performance of the evolutionary system. No one specific measure is standard, but Kozas computational effort statistic is frequently used [8]. In this paper the use of Kozas statistic is discussed and a study is made of three methods that produce confidence intervals for the statistic. It is found that an approximate 95% confidence interval can be easily produced.

Stream Processing of Integral Images for Real-Time Object Detection

This paper presents the design and evaluation of the stream processing implementation of the integral image algorithm. The integral image is a key component of many image processing algorithms in particular the Haar-like feature based systems. Modern GPUs provide a large number of processors with a peak floating point performance that is significantly higher than current general CPUs. This results in significant performance improvement when the Integral Image calculation for large input images is offloaded onto the GPU of the system.

Robotics competitions in engineering eduction

Internationally engineering education has had to become more pro-active in attracting students with the technical knowledge, skills and motivation enabling them to excel in four or more years of study with the ultimate goal of addressing the ever-growing demand for qualified engineers from the industry. General public perceptions that engineering is a difficult career field while offering inadequate financial rewards as compared to alternative fields have resulted in significant reduction in student numbers, particularly among high quality students across all the engineering, sciences and technical disciplines. This paper presents the experience of using robotic competition events to motivate school students and help them appreciate what is involved in an engineering design and development fields.

Stream processing for fast and efficient rotated Haar-like features using rotated integral images

An extended set of Haar-like features for image sensors beyond the standard vertically and horizontally aligned Haar-like features and the 45° twisted Haar-like features are introduced. The extended rotated Haar-like features are based on the standard Haar-like features that have been rotated based on whole integer pixel-based rotations. These rotated feature values can also be calculated using rotated integral images which mean that they can be fast and efficiently calculated with just eight operations irrespective of the feature size. The integral image calculations can be offloaded to the graphical processing unit (GPU) using the stream processing paradigm. The integral image calculation on the GPU is seen to be faster than the traditional central processing unit implementation of the algorithm, for large image sizes, allowing more complex classifiers to be implemented in real-time.

The reliability of confidence intervals for computational effort comparisons

This paper analyses the reliability of confidence intervals for Kozas computational effort statistic. First, we conclude that dependence between the observed minimum generation and the observed cumulative probability of success leads to the production of more reliable confidence intervals for our preferred method. Second, we show that confidence intervals from 80% to 95% have appropriate levels of performance. Third, simulated data is used to consider the effect of large minimum generations and the confidence intervals are again found to be reliable. Finally, results from four large datasets collected from real genetic programming experiments are used to provide even more empirical evidence that the method for producing confidence intervals is reliable.