Spatial Imagination With Semantic Cognition for Mobile Robots

TL;DR

This paper introduces a training-based spatial imagination algorithm for mobile robots that leverages semantic cognition to enhance mapping, collision avoidance, and path planning, demonstrating improved accuracy and efficiency in a simulated environment.

Contribution

The paper presents a novel semantic cognition-based spatial imagination algorithm for mobile robots, trained and evaluated in a photo-realistic simulation environment.

Findings

Improved semantic mapping accuracy

Enhanced efficiency in environment understanding

Universal imagination for unseen objects

Abstract

The imagination of the surrounding environment based on experience and semantic cognition has great potential to extend the limited observations and provide more information for mapping, collision avoidance, and path planning. This paper provides a training-based algorithm for mobile robots to perform spatial imagination based on semantic cognition and evaluates the proposed method for the mapping task. We utilize a photo-realistic simulation environment, Habitat, for training and evaluation. The trained model is composed of Resent-18 as encoder and Unet as the backbone. We demonstrate that the algorithm can perform imagination for unseen parts of the object universally, by recalling the images and experience and compare our approach with traditional semantic mapping methods. It is found that our approach will improve the efficiency and accuracy of semantic mapping.