Michael J. Procopio

Benefits of synchronous collaboration support for an application-centered analysis team working on complex problems: a case study

A month-long quasi-experiment was conducted using a distributed team responsible for modeling, simulation, and analysis. Six experiments of three different time durations (short, medium, and long) were performed. The primary goal was to discover if synchronous collaboration capability through a particular application improved the ability of the team to form a common mental model of the analysis problem(s) and solution(s). The results indicated that such collaboration capability did improve the formation of common mental models, both in terms of time and quality (i.e., depth of understanding), and that the improvement did not vary by time duration. In addition, common mental models were generally formed by interaction around a shared graphical image, the progress of collaboration was not linear but episodic, and tasks that required drawing and conversing at the same time were difficult to do.

Learning in dynamic environments with Ensemble Selection for autonomous outdoor robot navigation

Autonomous robot navigation in unstructured outdoor environments is a challenging area of active research. The navigation task requires identifying safe, traversable paths which allow the robot to progress toward a goal while avoiding obstacles. Machine learning techniques - in particular, classifier ensembles - are well adapted to this task, accomplishing near-to-far learning by augmenting near-field stereo readings in order to identify safe terrain and obstacles in the far field. Composition of the ensemble and subsequent combination of model outputs in this dynamic problem domain remain open questions. Recently, Ensemble selection has been proposed as a mechanism for selecting and combining models from an existing model library and shown to perform well in static domains. We propose the adaptation of this technique to the time-evolving data associated with the outdoor robot navigation domain. Important research questions as to the composition of the model library, as well as how to combine selected modelspsila outputs, are addressed in a two-factor experimental evaluation. We evaluate the performance of our technique on six fully labeled datasets, and show that our technique outperforms memoryless baseline techniques that do not leverage past experience.

Coping with imbalanced training data for improved terrain prediction in autonomous outdoor robot navigation

Autonomous robot navigation in unstructured outdoor environments is a challenging and largely unsolved area of active research. The navigation task requires identifying safe, traversable paths that allow the robot to progress towards a goal while avoiding obstacles. Machine learning techniques are well adapted to this task, accomplishing near-to-far learning by training appearance-based models using near-field stereo readings in order to predict safe terrain and obstacles in the far field. However, these methods are subject to degraded performance when training data sets exhibit class imbalance, or skew, where data instances of one class outnumber those in another. In such scenarios, classifiers can be overwhelmed by the majority class, and will tend to ignore the minority class. In this paper, we show that typical outdoor terrain scenarios are associated with training data imbalance, and examine the impact of using undersampling, oversampling, SMOTE, and biased penalties techniques to correct for imbalance in stereo-derived training data. We conduct a statistically significant, repeated measures empirical evaluation and demonstrate improved far-field terrain prediction performance when using such methods for handling class imbalance versus taking no corrective action at all.