NAVITE: A neural network system for sensory-based robot navigation

J. Mario Aguilar, José L. Contreras-Vidal

Research output: Chapter in Book/Report/Conference proceedingChapter


A neural network system, NAVITE, for incremental trajectory generation and obstacle avoidance is presented. Unlike other approaches, the system is effective in unstructured environments. Multimodal information from visual and range data is used to improve obstacle detection by eliminating uncertainty in the measurements. This sensory information is then used to generate alternative trajectories which avoid collision. Optimal paths are computed without explicitly optimizing cost functions, therefore reducing computational expenses. Simulations of a planar mobile robot (including the dynamic characteristics of the plant) in obstacle-free and object avoidance trajectories are presented. The system can be extended to incorporate global map information into the local decision-making process.

Original languageEnglish (US)
Title of host publicationWorld Congress on Neural Networks
PublisherTaylor and Francis
ISBN (Electronic)9781315784076
ISBN (Print)9780805817454
StatePublished - Sep 10 2021

ASJC Scopus subject areas

  • Psychology(all)


Dive into the research topics of 'NAVITE: A neural network system for sensory-based robot navigation'. Together they form a unique fingerprint.

Cite this