%0 Conference Proceedings
%F Cherubini13a
%A Cherubini, A.
%A Grechanichenko, B.
%A Spindler, F.
%A Chaumette, F.
%T Avoiding Moving Obstacles during Visual Navigation
%B IEEE Int. Conf. on Robotics and Automation, ICRA'13
%P 3054-3059
%C Karlsruhe, Germany
%X Moving obstacle avoidance is a fundamental re- quirement for any robot operating in real environments, where pedestrians, bicycles and cars are present. In this work, we design and validate a new approach that takes explicitly into account obstacle velocities, to achieve safe visual navigation in outdoor scenarios. A wheeled vehicle, equipped with an actuated pinhole camera and with a lidar, must follow a path represented by key images, without colliding with the obstacles. To estimate the obstacle velocities, we design a Kalman-based observer. Then, we adapt the tentacles designed in [1], to take into account the predicted obstacle positions. Finally, we validate our approach in a series of simulated and real experiments, showing that when the obstacle velocities are considered, the robot behaviour is safer, smoother, and faster than when it is not
%U http://www.irisa.fr/lagadic/pdf/2013_icra_cherubini.pdf
%U http://dx.doi.org/10.1109/ICRA.2013.6631003
%8 May
%D 2013