P2 Explore: Efficient Exploration in Unknown Cluttered Environment with Floor Plan Prediction

TL;DR

This paper introduces FPUNet, a novel network for predicting the layout of noisy indoor environments, which improves exploration efficiency by optimizing room visiting order, reducing path length in robot exploration.

Contribution

The paper presents FPUNet, a state-of-the-art network for environment layout prediction in cluttered spaces, enhancing exploration strategies with high-level topological guidance.

Findings

FPUNet outperforms other architectures as SOTA for layout prediction.

The method reduces exploration path length by up to 34.60%.

Extensive simulations validate the effectiveness of the approach.

Abstract

Robot exploration aims at the reconstruction of unknown environments, and it is important to achieve it with shorter paths. Traditional methods focus on optimizing the visiting order of frontiers based on current observations, which may lead to local-minimal results. Recently, by predicting the structure of the unseen environment, the exploration efficiency can be further improved. However, in a cluttered environment, due to the randomness of obstacles, the ability to predict is weak. Moreover, this inaccuracy will lead to limited improvement in exploration. Therefore, we propose FPUNet which can be efficient in predicting the layout of noisy indoor environments. Then, we extract the segmentation of rooms and construct their topological connectivity based on the predicted map. The visiting order of these predicted rooms is optimized which can provide high-level guidance for exploration. The FPUNet is compared with other network architectures which demonstrates it is the SOTA method for this task. Extensive experiments in simulations show that our method can shorten the path length by 2.18% to 34.60% compared to the baselines.