Building occupancy grids (OGs) in order to model the surrounding environment of a vehicle implies to fusion occupancy information provided by the different embedded sensors in the same grid. The principal difficulty comes from the fact that each can have a different resolution, but also that the resolution of some sensors varies with the location in the field of view. In this article we present...

The introduction of 3-D modeling with probabilistic encoding of occupancy state of space leaded to the development of powerful tools to generate rich representations of environments. But the sophistication of the modeling scheme introduces important concerns in the way such representations can be efficiently displayed to human operators for validation purpose and decision making in the guidance...

In this paper, we propose a real-time method to detect obstacles using theoretical models of the ground plane, first in a 3D point cloud given by a stereo camera, and then in an optical flow field given by one of the stereo pair’s camera. The idea of our method is to combine two partial occupancy grids from both sensor modalities with an occupancy grid framework. The two methods do not have the...

We present a continuous Bayesian occupancy representation for dynamic environments. The method builds on Gaussian processes classifiers and addresses the main limitations of occupancy grids such as the need to discretise the space, strong assumptions of independence between cells, and difficulty to represent occupancy in dynamic environments. We develop a novel covariance function (or kernel) t...

In this work we propose an enhanced model for mapping from sonar sensors and odometry that allows a robot to represent an environment map in a more suitable way to both the sonar sensory data and odometry system of the robot. We use a stochastic modelling of the errors that brings up reliable information. As a contribution, we obtain a final map that is more coherent with the reality of the ori...

This paper addresses the problem of how occupancy values from one occupancy grid can be used to calculate occupancy values in another grid, where the latter is rotated and/or translated with respect to the former. The mapping is described in terms of a neural network, of which the parameters are learned from examples. An activation function is derived taking into account that the input and outp...

We propose a new approach to 3D environment mapping from a mobile robot, using visual information provided by alow-cost stereo vision system. Depth information recovered from disparity maps serves as input for our method that uses probabilistic modelling to determine if a region is occupied or freein an occupancy grid approach. There is no similar approach in the literature, based on statistica...

This paper introduces the concept of a temporal occupancy grid as a method for modeling and classifying spatial areas according to the time properties of their occupancy. The method extends the idea of occupancy grids[1] by considering occupancy over a number of different timescales. This paper presents the basic formalism and its implementation using planar laser rangefinders. It includes the ...