Conference Paper

Outdoor visual path following experiments.

IRISA/NRIA, Rennes
DOI: 10.1109/IROS.2007.4399247 Conference: 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 29 - November 2, 2007, Sheraton Hotel and Marina, San Diego, California, USA
Source: DBLP

ABSTRACT 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 reference images such that each neighboring pair contains a number of common landmarks. Local 3D geometries are reconstructed between the neighboring reference images in order to achieve fast feature prediction which allows the recovery from tracking failures. During navigation the robot is controlled using image-based visual servoing. The experiments show that the framework is robust against moving objects and moderate illumination changes. It is also shown that the system is capable of on-line path learning.

Download full-text

Full-text

Available from: François Chaumette, Jul 29, 2015
0 Followers
 · 
89 Views
  • Source
    • "In our proposal, the visual servoing problem is transformed in a reference tracking problem for the selected tensor element. It avoids the recurrent problem of discontinuous rotational velocity at key image switching of image-based schemes [6], [7], [8]. The use of the TT allows the gathering of many visual features into a single measurement, so that, undesired pseudoinverse of matrices is not needed. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a control scheme for visual path-following of wheeled mobile robots based on a robust geometric constraint: the trifocal tensor (TT). The proposed control law only needs one element of the TT as feedback information, which is computed from the current and the target images along the sequence of the visual path. The scheme is valid for images captured by cameras having approximately a unique center of projection, e.g., conventional, central catadioptric and some fisheye cameras. The benefits of the proposed scheme are that explicit pose parameters decomposition is not required and the rotational velocity is smooth or eventually piece-wise constant avoiding discontinuities that generally appear when a new target image must be reached. Additionally, the translational velocity is adapted as required for the path. The validity and performance of the approach is shown through realistic simulations using synthetic images.
    World Automation Congress (WAC), 2012; 01/2012
  • Source
    • "The contribution of this paper, based on [12] 1 , is the application of the vision system to a robotic vehicle using an image-based visual servoing strategy and the experimental exploration of the implementation's limits 2 . Experiments were carried out mostly on roads using an autonomous electric vehicle capable of carrying two passengers. "
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 reference 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 visual servoing. The focus of this paper is on the results from a number 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.
    IEEE Transactions on Intelligent Transportation Systems 10/2011; DOI:10.1109/TITS.2011.2122334 · 2.47 Impact Factor
  • Source
    • "The most appealing solution to this problem is probably the use of visual odometry, where images coming from neighboring nodes or image sequences taken between nodes are matched to estimate the robot displacement [11], [23], [17], [28]. Instead of estimating node positions, another solution is to use visual servoing, also known as vision-based robot control which uses feedback information extracted from a vision sensor to control the motion of a robot [6]. The robot can then be directly guided to the neighboring nodes without explicitly computing their relative positions. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We address the problem of simultaneous localization and mapping by combining visual loop-closure detection with metrical information given by the robot odometry. The proposed algorithm builds in real-time topo-metric maps of an unknown environment, with a monocular or omnidirectional camera and odometry gathered by motors encoders. A dedicated improved version of our previous work on purely appearance-based loop-closure detection [1] is used to extract potential loop-closure locations. Potential locations are then verified and classified using a new validation stage. The main contributions we bring are the generalization of the validation method for the use of monocular and omnidirectional camera with the removal of the camera calibration stage, the inclusion of an odometry-based evolution model in the Bayesian filter which improves accuracy and responsiveness, and the addition of a consistent metric position estimation. This new SLAM method does not require any calibration or learning stage (i.e. no a priori information about environment). It is therefore fully incremental and generates maps usable for global localization and planned navigation. This algorithm is moreover well suited for remote processing and can be used on toy robots with very small computational power.
    Robotics and Automation (ICRA), 2011 IEEE International Conference on; 06/2011
Show more