Experimental Evaluation of Autonomous Driving Based on Visual Memory and Image Based Visual Servoing

A. Diosi (1) , S. Segvic (1) , A. Remazeilles (1) , F. Chaumette (1)

1 Lagadic - Visual servoing in robotics, computer vision, and augmented reality

In this paper, the performance of a topological metric visual-path-following framework is investigated in different environments. The framework relies on a monocular camera as the only sensing modality. The path is represented as a series of refer- ence images such that each neighboring pair contains a number of common landmarks. Local 3-D geometries are reconstructed between the neighboring reference images to achieve fast feature prediction. This condition allows recovery from tracking failures. During navigation, the robot is controlled using image-based vi- sual servoing. The focus of this paper is on the results from a num- ber of experiments that were conducted in different environments, lighting conditions, and seasons. The experiments with a robot car show that the framework is robust to moving objects and moderate illumination changes. It is also shown that the system is capable of online path learning.

Mots clés: Visual Servoing

Domaines: Robotique [cs.RO]

A. Diosi, S. Segvic, A. Remazeilles, F. Chaumette. Experimental Evaluation of Autonomous Driving Based on Visual Memory and Image Based Visual Servoing. IEEE Transactions on Intelligent Transportation Systems, 2011, 12 (3), pp.870-883. ⟨hal-00639680⟩