Artificial Intelligence and Robotics Commons^™

Pyro: A Python-Based Versatile Programming Environment For Teaching Robotics, D. Blank, D. Kumar, Lisa A. Meeden, H. Yanco

Computer Science Faculty Works

In this article we describe a programming framework called Pyro, which provides a set of abstractions that allows students to write platform-independent robot programs. This project is unique because of its focus on the pedagogical implications of teaching mobile robotics via a top-down approach. We describe the background of the project, its novel abstractions, its library of objects, and the many learning modules that have been created from which curricula for different types of courses can be drawn. Finally, we explore Pyro from the students' perspective in a case study.

Predicting Nonlinear Network Traffic Using Fuzzy Neural Network, Zhaoxia Wang, Tingzhu Hao, Zengqiang Chen, Zhuzhi Yuan

Research Collection School Of Computing and Information Systems

Network traffic is a complex and nonlinear process, which is significantly affected by immeasurable parameters and variables. This paper addresses the use of the five-layer fuzzy neural network (FNN) for predicting the nonlinear network traffic. The structure of this system is introduced in detail. Through training the FNN using back-propagation algorithm with inertia] terms the traffic series can be well predicted by this FNN system. We analyze the performance of the FNN in terms of prediction ability as compared with solely neural network. The simulation demonstrates that the proposed FNN is superior to the solely neural network systems. In addition, …

Task Allocation Via Multi-Agent Coalition Formation: Taxonomy, Algorithms And Complexity, Hoong Chuin Lau, L. Zhang

Research Collection School Of Computing and Information Systems

Coalition formation has become a key topic in multiagent research. In this paper, we propose a preliminary classification for the coalition formation problem based on three driving factors (demands, resources and profit objectives). We divide our analysis into 5 cases. For each case, we present algorithms and complexity results. We anticipate that with future research, this classification can be extended in similar fashion to the comprehensive classification for the job scheduling problem.

A Computer-Based Articulation Training Aid For Short Words (Cata), Mukund Devarajan

Electrical & Computer Engineering Theses & Dissertations

Several improvements in the vowel articulation training aid (VATA) are described, as well as the efforts to extend the visual feedback system to operate with short words in the form of consonant, vowel and consonant (CVC). The extended version of the visual feedback system is referred to as CATA (Computer-based Articulation Training Aid); the vowel version of the aid (VATA) only operates with ten American English monopthong vowels. Improvements in VATA include the use of a neural network (NN) recognizer method to prune a large database of vowel recordings to eliminate noisy and/or mispronounced tokens. The spectral jitter problem, previously …

Safe Robot Driving In Cluttered Environments, Chuck Thorpe, Justin Carlson, Dave Duggins, Jay Gowdy, Rob Maclachlan, Christoph Mertz, Arne Suppe, Bob Wang

Research Collection School Of Computing and Information Systems

The Navlab group at Carnegie Mellon University has a long history of development of automated vehicles and intelligent systems for driver assistance. The earlier work of the group concentrated on road following, cross-country driving, and obstacle detection. The new focus is on short-range sensing, to look all around the vehicle for safe driving. The current system uses video sensing, laser rangefinders, a novel light-stripe rangefinder, software to process each sensor individually, and a map-based fusion system. The complete system has been demonstrated on the Navlab 11 vehicle for monitoring the environment of a vehicle driving through a cluttered urban environment, …

Multi-Agent Coalition Via Autonomous Price Negotiation In A Real-Time Web Environment, Hoong Chuin Lau, Wei Sian Lim

Research Collection School Of Computing and Information Systems

In e-marketplaces, customers specify job requests in real-time and agents form coalitions to service them. This paper proposes a protocol for self-interested agents to negotiate prices in forming successful coalitions. We propose and experiment with two negotiation schemes: one allows information sharing while the other does not.

Solving Multi-Objective Multi-Constrained Optimization Problems Using Hybrid Ants System And Tabu Search, Hoong Chuin Lau, Min Kwang Lim, Wee Chong Wan, Hui Wang, Xiaotao Wu

Research Collection School Of Computing and Information Systems

Many real-world optimization problems today are multi-objective multi-constraint generalizations of NP-hard problems. A classic case we study in this paper is the Inventory Routing Problem with Time Windows (IRPTW). IRPTW considers inventory costs across multiple instances of Vehicle Routing Problem with Time Windows (VRPTW). The latter is in turn extended with time-windows constraints from the Vehicle Routing Problem (VRP), which is extended with optimal fleet size objective from the single-objective Traveling Salesman Problem (TSP). While single-objective problems like TSP are solved effectively using meta-heuristics, it is not obvious how to cope with the increasing complexity systematically as the problem is …

A Generic Object-Oriented Tabu Search Framework, Hoong Chuin Lau, Wee Chong Wan, Xiaomin Jia

Research Collection School Of Computing and Information Systems

Presently, most tabu search designers devise their applications without considering the potential of design and code reuse, which consequently prolong the development of subsequent applications. In this paper, we propose a software solution known as Tabu Search Framework (TSF), which is a generic C++ software framework for tabu search implementation. The framework excels in code recycling through the use of a welldesigned set of generic abstract classes that clearly define their collaborative roles in the algorithm. Additionally, the framework incorporates a centralized process and control mechanism that enhances the search with intelligence. This results in a generic framework that is …

A Generic Object-Oriented Tabu Search Framework, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Presently, most tabu search designers devise their applications without considering the potential of design and code reuse, which consequently prolong the development of subsequent applications. In this paper, we propose a software solution known as Tabu Search Framework (TSF), which is a generic C++ software framework for tabu search implementation. The framework excels in code recycling through the use of a welldesigned set of generic abstract classes that clearly define their collaborative roles in the algorithm. Additionally, the framework incorporates a centralized process and control mechanism that enhances the search with intelligence. This results in a generic framework that is …

On Machine Learning Methods For Chinese Document Classification, Ji He, Ah-Hwee Tan, Chew-Lim Tan

Research Collection School Of Computing and Information Systems

This paper reports our comparative evaluation of three machine learning methods, namely k Nearest Neighbor (kNN), Support Vector Machines (SVM), and Adaptive Resonance Associative Map (ARAM) for Chinese document categorization. Based on two Chinese corpora, a series of controlled experiments evaluated their learning capabilities and efficiency in mining text classification knowledge. Benchmark experiments showed that their predictive performance were roughly comparable, especially on clean and well organized data sets. While kNN and ARAM yield better performances than SVM on small and clean data sets, SVM and ARAM significantly outperformed kNN on noisy data. Comparing efficiency, kNN was notably more costly …

Machine Learning Approaches For Determining Effective Seeds For K -Means Algorithm, Kaveephong Lertwachara

Doctoral Dissertations

In this study, I investigate and conduct an experiment on two-stage clustering procedures, hybrid models in simulated environments where conditions such as collinearity problems and cluster structures are controlled, and in real-life problems where conditions are not controlled. The first hybrid model (NK) is an integration between a neural network (NN) and the k-means algorithm (KM) where NN screens seeds and passes them to KM. The second hybrid (GK) uses a genetic algorithm (GA) instead of the neural network. Both NN and GA used in this study are in their simplest-possible forms.

In the simulated data sets, I investigate two …

Automatic Speaker Identification Using Reusable And Retrainable Binary-Pair Partitioned Neural Networks, Ashutosh Mishra

Electrical & Computer Engineering Theses & Dissertations

This thesis presents an extension of the work previously done on speaker identification using Binary Pair Partitioned (BPP) neural networks. In the previous work, a separate network was used for each pair of speakers in the speaker population. Although the basic BPP approach did perform well and had a simple underlying algorithm, it had the obvious disadvantage of requiring an extremely large number of networks for speaker identification with large speaker populations. It also requires training of networks proportional to the square of the number of speakers under consideration, leading to a very large number of networks to be trained …

Pid Stabilization Of A Position-Controlled Robot Manipulator Acting Independently Of In Collaboration With Human Arm, Anindo Roy, Kamran Iqbal

Journal of the Arkansas Academy of Science

In this paper we develop framework for PID stabilization of a robot manipulator when using an object independently or in collaboration with a human arm. In both applications, the manipulator is equipped with a wrist sensor represented by an impedance. A second order manipulator transfer function along each coordinate direction is assumed. The aim of the paper is to design a PID controller when measurement of contact force, available via wrist sensor, is used to command the position controlled manipulator to a desired position and/or force profile. Necessary and sufficient conditions for stability of the closed loop system are developed …