The UBC Semantic Robot Vision System

Scott Helmer, David Meger, Per-Erik Forssén, Tristram Southey, Sancho McCann, Pooyan Fazli, James J. Little, David G. Lowe

Abstract: This abstract outlines the algorithms and robot hardware used in the UBC robot competing in the Semantic Robot Vision Challenge (SRVC), held at the AAAI’07 conference in Vancouver, Canada. Successfully completing the SRVC involves smooth integration of tasks such as data acquisition, training, obstacle avoidance, visual search, and object recognition. Given that these tasks span several research disciplines, successful integration is a formidable task. The value of working on these problems jointly is that assumptions built into an isolated method will be exposed when it is integrated, thus highlighting where further research is required. In addition, this will focus research on robots that can navigate safely and identify objects in their environment. Our approach is decomposed into five primary modules, each of which relies on the success of other modules, avoiding some of the unrealistic assumptions that are sometimes made when the tasks are tackled independently. The five primary modules are: