Improving hallway navigation in mobile robots with sensor habituation

Abstract

Habituation is a form of non-associative learning observed in a variety of species of animals. Arguably, it is the simplest form of learning. Nonetheless, the ability to habituate to certain stimuli implies plastic neural systems and adaptive behaviors. This article describes how computational models of habituation can be applied to real robots. In particular, we discuss the problem of the oscillatory movements observed when a Khepera robot navigates through narrow hallways. Results show that habituation to the proximity of the walls can lead to smoother navigation. Habituation to sensory stimulation to the sides of the robot does not interfere with the robot's ability to turn at dead ends and to avoid obstacles outside the hallway. This work shows that simple biological mechanisms of learning can be adapted to achieve better performance in real mobile robots.

A Simple Habituation Mechanism for Perceptual User Interfaces

“…Although we focus our work on the abilities described above, many other applications are also imaginable. In the robotics field, habituation mechanisms have been used to reduce oscillations caused by collision-avoidance behaviours when navigating through a narrow corridor [3]. Marsland [13] uses a SOM neural network as a memory for novelty detection.…”

A networked mobile sensor test-bed for collaborative multi-target tracking applications

“…Finally, multi-sensor collaborative applications will have to be developed by leveraging the underlying localization, navigation, networking and sensing services. Each of these four areas has seen recent research activities [4][5][6][7][8][9][10][11] and progress towards application-driven system integration. This paper contributes towards these integration trends by developing a system that comprises all four subsystems as well as their functional integration in the context of a collaborative multi-target tracking application in indoor settings.…”