An evolutionary approach to visual sensing for vehicle navigation

Abstract

This paper presents an evolutionary approach able to process a digital image and detect tracks left by preceding vehicles on ice and snow in Antarctica. Biologically inspired by a colony of ants able to interact and cooperate to determine the shortest path to the food, this approach is based on autonomous agents moving along the image pixels and iteratively improving an initial coarse solution.The unfriendly Antarctic environment makes this image analysis problem extremely challenging, since light reflections, abruptly varying brightness conditions, and different terrain slopes must be considered as well.The ant-based approach is compared to a more traditional Hough-based solution and the results are discussed.

An agent based evolutionary approach to path detection for off-road vehicle guidance

“…This is due to the nice segmentation achieved in imD (Figure 4(b)) that enhances the differences between pixels inside and outside the road, and, at the same time, smooths out the differences within those two classes. So, the attractiveness of a pixel is proportional to the brightness of its correspondent pixel in the edge image (this rule defines the local heuristic function) [16]. In the same way, the cost of the movement towards a pixel is inversely proportional to the brightness of its correspondent in the edge image (this rule defines the cost function).…”

Swarm contours: A fast self-organization approach for snake initialization

“…In these researches, the multiagent solution seems just as a sophisticated metaphor without providing better results than traditional techniques [10,11]. However, some studies have applied multiagent ideas in order to achieve practically distinctive results.…”

“…Therefore, a mechanism is required to detect asymmetries and eliminate them. Our suggested mechanisms is formally shown in Equation (11), where N a denotes the set of neighbors chosen by agent a. Briefly explaining the equation, any connection is checked for asymmetry and once detected, the connection is removed and a new neighbor is selected for that agent.…”

Applications of moving windows technique to autonomous vehicle navigation

“…When the position of a right line and a left line is denoted as F L (y) and F R (y), respectively, the center of lane can be calculated as [15][16][17],…”