Spatial Imagination With Semantic Cognition for Mobile Robots
This addresses mapping challenges for mobile robots, though it appears incremental as it builds on existing semantic mapping methods with a novel imagination component.
The paper tackles the problem of limited environmental observations for mobile robots by developing a training-based algorithm that performs spatial imagination using semantic cognition, demonstrating improved efficiency and accuracy in semantic mapping tasks.
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.