Industry
Kansas State's Slick Willie Robot Software
The team's robot software was nicknamed Their project was to develop software on the Nomad 200 robot for tasks such as maze following, office delivery, and office navigation. In both the second for the competition's Office Navigation and the final rounds, the software achieved event. The perfectly complete the task. It is equipped with 2 sonar route from the director's office to the conference rings of 16 sonars each and with 2 charge-coupled rooms, directed the robot to each of the device (CCD) cameras. The robot has a two conference rooms, correctly determined 486 processor on board with a hard drive and which conference room was not occupied, 16 megabytes of memory. The behaviors at the bottom level needed to worry about low-level responsibilities, such as avoiding obstacles and not hitting walls but did not need to know about the overall strategy for solving the task.
A Retrospective of the AAAI Robot Competitions
Bonasso, R. Peter, Dean, Thomas
This article is the content of an invited talk given by the authors at the Thirteenth National Conference on Artificial Intelligence (AAAI-96). The piece begins with a short history of the competition, then discusses the technical challenges and the political and cultural issues associated with bringing it off every year. We also cover the science and engineering involved with the robot tasks and the educational and commercial aspects of the competition. We finish with a discussion of the community formed by the organizers, participants, and the conference attendees. The original talk made liberal use of video clips and slide photographs; so, we have expanded the text and added photographs to make up for the lack of such media.
The 1996 AAAI Mobile Robot Competition and Exhibition
Kortenkamp, David, Nourbakhsh, Illah, Hinkle, David
The Fifth Annual AAAI Mobile Robot Competition and Exhibition was held in Portland, Oregon, in conjunction with the Thirteenth National Conference on Artificial Intelligence. The competition consisted of two events: (1) Office Navigation and (2) Clean Up the Tennis Court. The first event stressed navigation and planning. The second event stressed vision sensing and manipulation. In addition to the competition, there was a mobile robot exhibition in which teams demonstrated robot behaviors that did not fit into the competition tasks. The competition and exhibition were unqualified successes, with nearly 20 teams competing. The robot competition raised the standard for autonomous mobile robotics, demonstrating the intelligent integration of perception, deliberation, and action.
Improved Heterogeneous Distance Functions
Wilson, D. R., Martinez, T. R.
Instance-based learning techniques typically handle continuous and linear input values well, but often do not handle nominal input attributes appropriately. The Value Difference Metric (VDM) was designed to find reasonable distance values between nominal attribute values, but it largely ignores continuous attributes, requiring discretization to map continuous values into nominal values. This paper proposes three new heterogeneous distance functions, called the Heterogeneous Value Difference Metric (HVDM), the Interpolated Value Difference Metric (IVDM), and the Windowed Value Difference Metric (WVDM). These new distance functions are designed to handle applications with nominal attributes, continuous attributes, or both. In experiments on 48 applications the new distance metrics achieve higher classification accuracy on average than three previous distance functions on those datasets that have both nominal and continuous attributes.
Learning Sparse Perceptrons
Jackson, Jeffrey C., Craven, Mark
We introduce a new algorithm designed to learn sparse perceptrons overinput representations which include high-order features. Our algorithm, which is based on a hypothesis-boosting method, is able to PAClearn a relatively natural class of target concepts. Moreover, the algorithm appears to work well in practice: on a set of three problem domains, the algorithm produces classifiers that utilize small numbers of features yet exhibit good generalization performance. Perhaps most importantly, our algorithm generates concept descriptions that are easy for humans to understand. 1 Introduction Multi-layer perceptron (MLP) learning is a powerful method for tasks such as concept classification.However, in many applications, such as those that may involve scientific discovery, it is crucial to be able to explain predictions. Multi-layer perceptrons arelimited in this regard, since their representations are notoriously difficult for humans to understand.
Improving Elevator Performance Using Reinforcement Learning
Crites, Robert H., Barto, Andrew G.
This paper describes the application of reinforcement learning (RL) to the difficult real world problem of elevator dispatching. The elevator domainposes a combination of challenges not seen in most RL research to date. Elevator systems operate in continuous state spaces and in continuous time as discrete event dynamic systems. Their states are not fully observable and they are nonstationary due to changing passenger arrival rates. In addition, we use a team of RL agents, each of which is responsible for controlling one elevator car.The team receives a global reinforcement signal which appears noisy to each agent due to the effects of the actions of the other agents, the random nature of the arrivals and the incomplete observation of the state.
Experiments with Neural Networks for Real Time Implementation of Control
Campbell, Peter K., Dale, Michael, Ferrรก, Herman L., Kowalczyk, Adam
This paper describes a neural network based controller for allocating capacity in a telecommunications network. This system was proposed in order to overcome a "real time" response constraint. Two basic architectures are evaluated: 1) a feedforward network-heuristic and; 2) a feedforward network-recurrent network. These architectures are compared against a linear programming (LP) optimiser as a benchmark. This LP optimiser was also used as a teacher to label the data samples for the feedforward neural network training algorithm. It is found that the systems are able to provide a traffic throughput of 99% and 95%, respectively, of the throughput obtained by the linear programming solution. Once trained, the neural network based solutions are found in a fraction of the time required by the LP optimiser.
Tempering Backpropagation Networks: Not All Weights are Created Equal
Schraudolph, Nicol N., Sejnowski, Terrence J.
Backpropagation learning algorithms typically collapse the network's structure into a single vector of weight parameters to be optimized. We suggest that their performance may be improved by utilizing the structural information instead of discarding it, and introduce a framework for ''tempering'' each weight accordingly. In the tempering model, activation and error signals are treated as approximately independent random variables. The characteristic scale of weight changes is then matched to that ofthe residuals, allowing structural properties such as a node's fan-in and fan-out to affect the local learning rate and backpropagated error. The model also permits calculation of an upper bound on the global learning rate for batch updates, which in turn leads to different update rules for bias vs. non-bias weights. This approach yields hitherto unparalleled performance on the family relations benchmark, a deep multi-layer network: for both batch learning with momentum and the delta-bar-delta algorithm, convergence at the optimal learning rate is sped up by more than an order of magnitude.
Control of Selective Visual Attention: Modeling the "Where" Pathway
Intermediate and higher vision processes require selection of a subset of the available sensory information before further processing. Usually, this selection is implemented in the form of a spatially circumscribed region of the visual field, the so-called "focus of attention" which scans the visual scene dependent on the input and on the attentional state of the subject. We here present a model for the control of the focus of attention in primates, based on a saliency map. This mechanism is not only expected to model the functionality of biological vision but also to be essential for the understanding of complex scenes in machine vision.