Perception-Aware Autonomous Exploration in Feature-Limited Environments

Abstract

Autonomous exploration in unknown environments relies on onboard state estimation for localisation and mapping. Existing exploration methods primarily maximise coverage efficiency, but often overlook that visual-inertial odometry (VIO) performance strongly depends on the availability of robust visual features. Consequently, exploration policies can drive a robot into feature-sparse regions where tracking degrades, leading to odometry drift, corrupted maps, and mission failure. We propose a hierarchical perception-aware exploration framework for a stereo-equipped uncrewed aerial vehicle (UAV) that explicitly incorporates perceptual quality into frontier selection and yaw planning during exploration. Our approach (i) associates each candidate frontier with an expected feature quality using a global feature map, prioritising visually informative subgoals, and (ii) optimises a continuous yaw trajectory along the planned path to maintain stable feature tracks. We evaluate our method in simulation across environments with varying texture levels and in real-world indoor experiments with largely textureless walls. Compared to baselines that ignore feature quality and/or omit continuous yaw optimisation, our method achieves more reliable feature tracking, reduced odometry drift, and up to 48% higher coverage before odometry error exceeds specified thresholds.