Information Roadmap Method for Robotic Sensor Map Planning

Guoxian Zhang
Special Instructions: 
Lunch and beverages will be served
Thursday, November 13, 2008 - 12:00pm
Hudson Hall Room 216
Seminar Contact(s): 
Elizabeth Irish or Justin Jaworski
Semester & Year: 
Fall 2008
A new probabilistic roadmap method is presented for planning the path of a robotic sensor deployed in order to classify multiple fixed targets located in an obstacle-populated workspace. Existing roadmap methods have been successful at planning a robot path for the purpose of moving from an initial to a final configuration in a workspace by a minimum distance. However, they are not directly applicable to robots whose primary objective is to gather target information with an on-board sensor. In this paper, a novel information roadmap method is developed in which obstacles, targets, sensor's platform and field of view are represented as closed and bounded subsets of an Euclidean workspace. The information roadmap is sampled from a normalized information theoretic metric that favors samples with a high expected value of information in configuration space. The method is applied to a landmine classification problem to plan the path of a robotic ground-penetrating radar, based on prior remote measurements and other geospatial data. Experiments show that paths obtained from the information roadmap exhibit a classification efficiency several times higher than that of existing search strategies. Also, the information roadmap can be used to deploy non-overpass capable robots that must avoid targets as well as obstacles.