View PDF HTML (experimental)

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.

Submission history

From: Juyeop Han [view email]
[v1] Thu, 10 Jul 2025 06:42:53 UTC (18,572 KB)
[v2] Wed, 25 Feb 2026 19:16:54 UTC (4,269 KB)
[v3] Sun, 28 Jun 2026 23:59:37 UTC (6,542 KB)