SEER: Safe Efficient Exploration for Aerial Robots using Learning to Predict Information Gain

TL;DR

This paper presents SEER, a learning-based framework enabling micro aerial vehicles to efficiently explore indoor environments by predicting unseen areas, selecting informative viewpoints, and planning safe trajectories, outperforming existing methods.

Contribution

The paper introduces a novel exploration framework that combines learning-based occupancy prediction, semantic feature extraction, and trajectory planning for safe and efficient indoor exploration.

Findings

Outperforms state-of-the-art by 24% in path length

Achieves higher success rate in exploration tasks

Validated in both simulated and real-world environments

Abstract

We address the problem of efficient 3-D exploration in indoor environments for micro aerial vehicles with limited sensing capabilities and payload/power constraints. We develop an indoor exploration framework that uses learning to predict the occupancy of unseen areas, extracts semantic features, samples viewpoints to predict information gains for different exploration goals, and plans informative trajectories to enable safe and smart exploration. Extensive experimentation in simulated and real-world environments shows the proposed approach outperforms the state-of-the-art exploration framework by 24% in terms of the total path length in a structured indoor environment and with a higher success rate during exploration.