Keywords:  Image-based visual servoing, nonholonomic mobile robots, epipolar geometry, input-output linearization

            We present an image-based visual servoing (IBVS) strategy for driving a nonholonomic mobile robot equipped with a pinhole camera (see Fig.1) from an initial toward a target desired configuration. The proposed approach, which exploits the epipolar geometry defined by the actual and desired camera views (see Fig.2), does not need any knowledge of the observed 3-D scene geometry.

Fig.1 - The IBVS strategy controls the robot   using only visual information provided by the  pinhole camera.   Fig. 2 - The epipolar geometry is used as the main tool in our servoing strategy.

           A generical starting configuration is shown in Fig.3, while the corresponding position of  feature points and epipoles (here superimposed to the desired image) is shown in Fig.4. The control scheme is divided in two steps. In the first, using an approximate input-output linearizing feedback, the epipoles are zeroed, so as to align the robot with the goal. Feature points are then used in the second translational step to reach the desired configuration. Global asymptotic convergence has been proven, both in the calibrated and partially calibrated case.

Fig.3 - The IBVS strategy based on epipolar geometry drives the robot form initial to target position (in which the desired view is known) using the current view.	Fig.4 - From the pinhole camera we extract desired (circles) and current (crosses) features to compute epipoles (e_d and e_a) (here superimposed to the desired image) and control the robot.

Documents:

     comin' soon!

Experiments:

We present here results from the experimental session:

    Robot motion ([mp4] -  Short ~2Mb)

     Image motion ([mp4] -  Short ~2Mb)

Acknowledgments:

       We wish to thanks Nicola Pisu and Riccardo Donati for their invaluable help in the realization of experimental results.