Automatic camera placement for robot vision tasks

Publisher Website
Google Scholar
Abstract
Remote sensors such as CCD cameras can be used for a variety of robot sensing tasks, but given restrictions on camera location an d imaging geometry, task constraints, and visual occlusion it can be d ifficult to find viewing positions from which the task can be completed. The complexity of these constraints suggests that automated, quantitative methods of sensor placement are likely to be useful, particu larly when the workspace is cluttered and a mobile robot-mounted sensor is being used to increase the sensible region, circumvent occlusion s, and so forth. We describe a camera placement planner designed to produce heur- istically good static viewing positions for a robot-mounte d CCD cam- era in an experimental workcell. It can be configured to produce view- points for a variety of tasks such as workpiece location, ins pection and modelling; feedback control by visual servoing; and task progress monitoring. The planner uses a novel probability-based global search technique to optimize a viewpoint evaluation function that heuristic- ally combines task, camera, robot and environmental constraints. The main advances over previous work are the incorporation of kinematic accessibility and collision constraints in the viewpoint e valuation and the introduction of a search technique powerful enough to handle the resulting strong nonlinearities.

This publication has 8 references indexed in Scilit: