Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Exploration

TL;DR

This paper introduces ExHistCNN, a learning-based method for autonomous 3D exploration that predicts the next best view by combining current depth data with reconstruction history, improving exploration efficiency.

Contribution

It presents a novel 3D reconstruction history representation and a lightweight CNN model for next best view estimation in indoor exploration tasks.

Findings

ExHistCNN approaches oracle-level exploration performance.

The method effectively combines depth observation and history for NBV prediction.

Extensive tests on synthetic and real data validate its robustness.

Abstract

In this work we address the problem of autonomous 3D exploration of an unknown indoor environment using a depth camera. We cast the problem as the estimation of the Next Best View (NBV) that maximises the coverage of the unknown area. We do this by re-formulating NBV estimation as a classification problem and we propose a novel learning-based metric that encodes both, the current 3D observation (a depth frame) and the history of the ongoing reconstruction. One of the major contributions of this work is about introducing a new representation for the 3D reconstruction history as an auxiliary utility map which is efficiently coupled with the current depth observation. With both pieces of information, we train a light-weight CNN, named ExHistCNN, that estimates the NBV as a set of directions towards which the depth sensor finds most unexplored areas. We perform extensive evaluation on both synthetic and real room scans demonstrating that the proposed ExHistCNN is able to approach the exploration performance of an oracle using the complete knowledge of the 3D environment.