Efficient Robot Learning for Perception and Mapping

TL;DR

This paper explores methods for enabling robots to understand and map their environment efficiently with minimal human effort, emphasizing continual learning and reduced annotation needs for real-world deployment.

Contribution

It introduces approaches that minimize human annotations and leverage continual learning to improve perception and mapping in unseen environments.

Findings

Reduced annotation requirements for robot perception tasks.

Effective continual learning strategies for robotic mapping.

Improved generalization to new environments.

Abstract

Holistic scene understanding poses a fundamental contribution to the autonomous operation of a robotic agent in its environment. Key ingredients include a well-defined representation of the surroundings to capture its spatial structure as well as assigning semantic meaning while delineating individual objects. Classic components from the toolbox of roboticists to address these tasks are simultaneous localization and mapping (SLAM) and panoptic segmentation. Although recent methods demonstrate impressive advances, mostly due to employing deep learning, they commonly utilize in-domain training on large datasets. Since following such a paradigm substantially limits their real-world application, my research investigates how to minimize human effort in deploying perception-based robotic systems to previously unseen environments. In particular, I focus on leveraging continual learning and reducing human annotations for efficient learning. An overview of my work can be found at https://vniclas.github.io.