SenseExpo: Lightweight Neural Networks for Efficient Autonomous Exploration and Scene Prediction

Haohua Que, Haojia Gao, Mingkai Liu, Hoiian Au, Handong Yao, Fei Qiao

Keywords: Autonomous Exploration; Scene Prediction; Lightweight Neural Networks

Abstract: This work presents \emph{SenseExpo}, a frontier-based exploration framework powered by a lightweight local map predictor that combines GAN training, a Transformer encoder, and Fast Fourier Convolution. Our smallest model (709k parameters) surpasses much larger baselines (U-Net 24.5M, LaMa 51M) on KTH dataset, achieving PSNR 9.026 and SSIM 0.718, and shows strong cross-domain robustness on HouseExpo (FID 161.55). Leveraging predicted free space for goal selection, \emph{SenseExpo} accelerates exploration, reducing time by~67.9\% on KTH dataset and~77.1\% on MRPB 1.0 relative to MapEx, while sustaining high coverage and accuracy. Delivered as a plug-and-play ROS node, it is practical for resource-constrained robots and easy to integrate into existing navigation stacks.

Submission Type: Novel research

Student Paper: Yes

Demo Or Video: Yes

Public Extended Abstract: Yes

Submission Number: 3