College of Staten Island, City University of New York
Learning to Avoid Collisions
Sklar, Elizabeth (Brooklyn College, City University of New York) | Parsons, Simon (Brooklyn College, City University of New York) | Epstein, Susan L. (Hunter College, City University of New York) | Ozgelen, Arif Tuna (The Graduate Center, City University of New York) | Munoz, Juan Pablo (The Graduate Center, City University of New York) | Abbasi, Farah (College of Staten Island, City University of New York) | Schneider, Eric (Hunter College, City University of New York) | Costantino, Michael (College of Staten Island, City University of New York)
Members of a multi-robot team, operating within close quarters, need to avoid crashing into each other. Simple collision avoidance methods can be used to prevent such collisions, typically by computing the distance to other robots and stopping, perhaps moving away, when this distance falls below a certain threshold. While this approach may avoid disaster, it may also reduce the team's efficiency if robots halt for a long time to let others pass by or if they travel further to move around one another. This paper reports on experiments where a human operator, through a graphical user interface, watches robots perform an exploration task. The operator can manually suspend robots' movements before they crash into each other, and then resume their movements when their paths are clear. Experiment logs record the robots' states when they are paused and resumed. A behavior pattern for collision avoidance is learned, by classifying the states of the robots' environment when the human operator issues "wait" and "resume" commands. Preliminary results indicate that it is possible to learn a classifier which models these behavior patterns, and that different human operators consider different factors when making decisions about stopping and starting robots.
Approaches to Multi-Robot Exploration and Localization
Ozgelen, Arif T. (The Graduate Center, City University of New York) | Costantino, Michael (College of Staten Island, City University of New York) | Ishak, Adiba (Brooklyn College, City University of New York) | Kingston, Moses (Brooklyn College, City University of New York) | Moore, Diquan (Lehman College, City University of New York) | Sanchez, Samuel (Queens College, City University of New York) | Munoz, J. Pablo (Brooklyn College, City University of New York) | Parsons, Simon (Brooklyn College, City University of New York) | Sklar, Elizabeth (Brooklyn College, City University of New York)
Students have implemented approaches to these problems, using our HRTeam framework (Sklar et al. 2010), which is built on Player/Stage (Vaughan and Gerkey 2007).
Using Decision Trees to Find Patterns in an Ophthalmology Dataset
Imberman, Susan (College of Staten Island, City University of New York) | Ludwig, Irene (City University of New York) | Zelikovitz, Sarah (College of Staten Island, City University of New York)
We present research in decision tree analysis that studies a data set and finds new patterns that were not obvious using statistical methods. Our method is applied to a database of accommodative esotropic patients. Accommodative esotropia is an eye disease that when left untreated leads to blindness. Patients whose muscles deteriorate often need corrective surgery, since less invasive methods of treatment tend to fail in these patients. Using a learn and prune methodology, decision tree analysis of 354 accommodative esotropic patients led to the discovery of two conjunctive variables that predicted deterioration in the initial year of treatment better than what was previously determined using standard statistical methods.