Artificial Intelligence and Robotics Commons^™

A Practical Approach To Robotic Design For The Darpa Urban Challenge, Benjamin J. Patz, Yiannis Papelis, Remo Pillat, Gary Stein, Don Harper

VMASC Publications

This article presents a practical approach to engineering a robot to effectively navigate in an urban environment. Inherent in this approach is the use of relatively simple sensors, actuators, and processors to generate robot vision, intelligence, and planning. Sensor data are fused from multiple low-cost, two-dimensional laser scanners With an innovative rotational mount to provide three-dimensional coverage with image processing using both range and intensity data. Information is combined With Doppler radar returns to yield a world view processed by a context-based reasoning control system to yield tactical mission commands forwarded to traditional proportional-integral-derivative (PID) control loops. As an example …

Robot Controller Architecture: Layered Mode Selection Logic With Fuzzy Sensor Fusion Network, Traig E.B. Born

Theses and Dissertations

A behavior based robot controller was implemented using Layered Mode Selection Logic as a behavior coordination mechanism and a Fuzzy Sensor Fusion Network to provide perception. A series of collision experiments were conducted to create a Fuzzy Sensor Fusion Network capable of detecting collisions using acceleration readings from wheel encoders. An obstacle avoidance behavior was created, and it was demonstrated that the robot could be constrained by movable obstacles. The avoidance behavior was modified to create an obstacle manipulation behavior. This behavior allowed the robot to escape when enclosed by movable obstacles. The fuzzy sensor fusion network was enhanced to …

New Method For Approximating Vague Sets To Fuzzy Sets Based On Voting Model, Jian Liu, Zhizhan Liu, Shunxiang Wu, Yongjian Zhang

Electrical and Computer Engineering Faculty Research & Creative Works

By analyzing Vague Sets voting model, we bring forth a new method for approximating Vague Sets to Fuzzy Sets, and its general process is presented in the article. In a voting model, firstly, we suppose that the abstainers must vote for once more, and the results are close studied. Then the randomicity, uncertainty, and conformity of voting are found. As we know, an abstainer may favor somebody, oppose somebody, or just abstain. In this article, we suppose the distribution of results is consistent with a normal distribution. So, we advance the new approximation method based on Gauss Distribution. © 2008 …

Object Detection And Classification With Applications To Skin Cancer Screening, Jonathan Blackledge, Dmitryi Dubovitskiy

Articles

This paper discusses a new approach to the processes of object detection, recognition and classification in a digital image. The classification method is based on the application of a set of features which include fractal parameters such as the Lacunarity and Fractal Dimension. Thus, the approach used, incorporates the characterisation of an object in terms of its texture.

The principal issues associated with object recognition are presented which includes two novel fast segmentation algorithms for which C++ code is provided. The self-learning procedure for designing a decision making engine using fuzzy logic and membership function theory is also presented and …

The Oil Drilling Model And Iterative Deepening Genetic Annealing Algorithm For The Traveling Salesman Problem, Hoong Chuin Lau, Fei Xiao

Research Collection School Of Computing and Information Systems

In this work, we liken the solving of combinatorial optimization problems under a prescribed computational budget as hunting for oil in an unexplored ground. Using this generic model, we instantiate an iterative deepening genetic annealing (IDGA) algorithm, which is a variant of memetic algorithms. Computational results on the traveling salesman problem show that IDGA is more effective than standard genetic algorithms or simulated annealing algorithms or a straightforward hybrid of them. Our model is readily applicable to solve other combinatorial optimization problems.

Enhancing Recursive Supervised Learning Using Clustering And Combinatorial Optimization (Rsl-Cc), Kiruthika Ramanathan, Sheng Uei Guan

Research Collection School Of Computing and Information Systems

The use of a team of weak learners to learn a dataset has been shown better than the use of one single strong learner. In fact, the idea is so successful that boosting, an algorithm combining several weak learners for supervised learning, has been considered to be one of the best off-the-shelf classifiers. However, some problems still remain, including determining the optimal number of weak learners and the overfitting of data. In an earlier work, we developed the RPHP algorithm which solves both these problems by using a combination of genetic algorithm, weak learner and pattern distributor. In this paper, …