6533b833fe1ef96bd129c0e9

RESEARCH PRODUCT

A Neural Solution for a Mobile Robot Navigation into Unknown Indoor Environments Using Visual Landmarks

Salvatore VitabileFilippo SorbelloFrancesco Bianco

subject

Artificial neural networkMachine visionComputer sciencebusiness.industryObstacle avoidanceRobotComputer visionMobile robotArtificial intelligenceVisual landmarksbusinessMobile robot navigationTask (project management)

description

In this paper we present a neural solution for a mobile robot navigation into unknown indoor environments by using landmarks. Robot navigation task is implemented by two groups of processes based on MLP neural networks classifiers: a Low Level Vision System performs obstacle avoidance and corridor following, while an High Level Vision System extracts landmarks contents and performs goal directed navigation. A path-planner manages the two navigation systems and interacts with the robot hardware. The proposed solution is very strong and flexible and can be used to drive a mobile robot in real indoor environments. In the paper experimental results are also reported.

yearjournalcountryeditionlanguage
1998-01-01
https://doi.org/10.1007/978-1-4471-1520-5_19