Beyond the Frontier: Predicting Unseen Walls from Occupancy Grids by Learning from Floor Plans

TL;DR

This paper introduces an attention-based deep learning method to predict unseen walls in partially observed environments from occupancy grids, improving autonomous exploration and generalizing to real-world office settings.

Contribution

It presents a novel autoregressive sequence prediction approach for unseen wall detection using occupancy grids, with demonstrated improvements over existing methods.

Findings

Significant accuracy improvements over non-predictive methods

Effective in both simulated and real-world environments

Enhanced autonomous exploration capabilities

Abstract

In this paper, we tackle the challenge of predicting the unseen walls of a partially observed environment as a set of 2D line segments, conditioned on occupancy grids integrated along the trajectory of a 360{\deg} LIDAR sensor. A dataset of such occupancy grids and their corresponding target wall segments is collected by navigating a virtual robot between a set of randomly sampled waypoints in a collection of office-scale floor plans from a university campus. The line segment prediction task is formulated as an autoregressive sequence prediction task, and an attention-based deep network is trained on the dataset. The sequence-based autoregressive formulation is evaluated through predicted information gain, as in frontier-based autonomous exploration, demonstrating significant improvements over both non-predictive estimation and convolution-based image prediction found in the literature. Ablations on key components are evaluated, as well as sensor range and the occupancy grid's metric area. Finally, model generality is validated by predicting walls in a novel floor plan reconstructed on-the-fly in a real-world office environment.