Visual servoing for path reaching with nonholonomic robots

Andrea Cherubini (1, 2) , F. Chaumette (1) , G. Oriolo (2)

1 Lagadic - Visual servoing in robotics, computer vision, and augmented reality
2 UNIROMA - Università degli Studi di Roma "La Sapienza" = Sapienza University [Rome]

We present two visual servoing controllers (pose-based and image-based) en- abling mobile robots with a fixed pinhole camera to reach and follow a contin- uous path drawn on the ground. The first contribution is the theoretical and experimental comparison between pose-based and image-based techniques for a nonholonomic robot task. Moreover, our controllers are appropriate not only for path following, but also for path reaching, a problem that has been rarely tackled in the past. Thirdly, in contrast with most works, which require the path geometric model, only two path features are necessary in our image-based scheme, and three in the pose-based scheme. For both controllers, a conver- gence analysis is carried out, and the performance is validated by simulations, and outdoor experiments on a car-like robot.

Mots clés: Visual Servoing; navigation

Domaines: Robotique [cs.RO]

Andrea Cherubini, F. Chaumette, G. Oriolo. Visual servoing for path reaching with nonholonomic robots. Robotica, 2011, 29 (7), pp.1037-1048. ⟨hal-00639659⟩