Learning-Augmented Model-Based Planning for Visual Exploration

TL;DR

This paper introduces a learning-augmented model-based planning method for robotic visual exploration that leverages semantic mapping and deep learning to improve coverage efficiency in unseen indoor environments.

Contribution

It presents a novel exploration approach combining subgoal generation, Bellman equations, and deep neural networks for property estimation, enhancing exploration performance.

Findings

Outperforms classical greedy strategies by 2.1% in coverage.

Outperforms RL-based exploration methods by 8.4% in coverage.

Guarantees complete exploration if time permits.

Abstract

We consider the problem of time-limited robotic exploration in previously unseen environments where exploration is limited by a predefined amount of time. We propose a novel exploration approach using learning-augmented model-based planning. We generate a set of subgoals associated with frontiers on the current map and derive a Bellman Equation for exploration with these subgoals. Visual sensing and advances in semantic mapping of indoor scenes are exploited for training a deep convolutional neural network to estimate properties associated with each frontier: the expected unobserved area beyond the frontier and the expected timesteps (discretized actions) required to explore it. The proposed model-based planner is guaranteed to explore the whole scene if time permits. We thoroughly evaluate our approach on a large-scale pseudo-realistic indoor dataset (Matterport3D) with the Habitat simulator. We compare our approach with classical and more recent RL-based exploration methods. Our approach surpasses the greedy strategies by 2.1% and the RL-based exploration methods by 8.4% in terms of coverage.