Realtime Perception for Catching a Flying Ball with a Mobile Humanoid
This paper presents a realtime perception system for catching flying balls with DLR’s humanoid Rollin’ Justin. We use a two-staged bottom up approach in which we first detect balls as circles and feed these measurements into a multiple hypothesis tracker (MHT). The novel circle detection scheme works in realistic scenes without tuning parameters or background assumptions. We extend the classical multihypothesis tracking with prior information about the expected trajectories, therefore limiting the number of hypotheses in the first place. Since the robot starts moving while the ball is still tracked, the cameras shake heavily. A 6-DOF inertial measurements unit (IMU) is integrated to compensate this motion. Using ground-truth from a marker based tracking system we evaluate the metrical accuracy of the motion compensation as well as the tracker’s prediction accuracy while in motion.
Oliver Birbach Udo Frese Berthold B(a)uml
German Center for Artificial Intelligence (DFKI). 28359 Bremen,Germany DLR Institute of Robotics and Mechatronics,M(u)nchnerstr. 20,82234 Wessling,Germany
国际会议
2011 IEEE International Conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)
上海
英文
5955-5962
2011-05-09（万方平台首次上网日期，不代表论文的发表时间）