SCREP: Scene Coordinate Regression and Evidential Learning-based Perception-Aware Trajectory Generation

TL;DR

This paper introduces a perception-aware trajectory planner for autonomous indoor flight that combines scene coordinate regression with evidential learning to improve pose estimation accuracy and robustness in GPS-denied environments.

Contribution

It proposes a novel trajectory planning approach that integrates SCR with evidential learning and a receding-horizon optimizer for improved localization and navigation.

Findings

Reduces translation RMSE by at least 4.9% in simulation

Reduces rotation RMSE by at least 30.8% in simulation

Validates feasibility through hardware-in-the-loop experiments

Abstract

Autonomous flight in GPS-denied indoor spaces requires trajectories that keep visual-localization error tightly bounded across varied missions. Map-based visual localization methods such as feature matching require computationally intensive map reconstruction and have feature-storage scalability issues, especially for large environments. Scene coordinate regression (SCR) provides an efficient learning-based alternative that directly predicts3D coordinates for every pixel, enabling absolute pose estimation with significant potential for onboard roboticsapplications. We present a perception-aware trajectory planner that couples an evidential learning-based SCR poseestimator with a receding-horizon trajectory optimizer. The optimizer steers the onboard camera toward reliablescene coordinates with low uncertainty, while a fixed-lag smoother fuses the low-rate SCR pose estimates with high-rate IMU data to provide a high-quality, high-rate pose estimate. In simulation, our planner reduces translationand rotation RMSE by at least 4.9% and 30.8% relative to baselines, respectively. Hardware-in-the-loop experiments validate the feasibility of our proposed trajectory planner under close-to-real deployment conditions.