Real-Time Thermal-Inertial Odometry on Embedded Hardware for High-Speed GPS-Denied Flight

2026-03-02

AI Summary

This work proposes a real-time thermal-inertial odometry system for high-speed, GPS-denied, and visually degraded environments where conventional visual-inertial odometry fails due to thermal image blur, low contrast, and aggressive motion. The system fuses a long-wave infrared camera, high-frequency IMU, laser rangefinder, barometer, and magnetometer within a fixed-lag factor graph framework. Key innovations include a lightweight thermal front-end, a depth-prior-enhanced scale stabilization mechanism, a vibration-robust IMU preintegration strategy, and an uncertainty-aware GRU-based model for dynamic barometric error correction. Deployed on a Jetson Xavier NX platform, the system enables closed-loop control at speeds up to 30 m/s with trajectory drift below 2% over kilometer-scale trajectories, significantly extending the operational envelope of thermal-inertial navigation.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We present a real-time monocular thermal-inertial odometry system designed for high-velocity, GPS-denied flight on embedded hardware. The system fuses measurements from a FLIR Boson+ 640 longwave infrared camera, a high-rate IMU, a laser range finder, a barometer, and a magnetometer within a fixed-lag factor graph. To sustain reliable feature tracks under motion blur, low contrast, and rapid viewpoint changes, we employ a lightweight thermal-optimized front-end with multi-stage feature filtering. Laser range finder measurements provide per-feature depth priors that stabilize scale during weakly observable motion. High-rate inertial data is first pre-filtered using a Chebyshev Type II infinite impulse response (IIR) filter and then preintegrated, improving robustness to airframe vibrations during aggressive maneuvers. To address barometric altitude errors induced at high airspeeds, we train an uncertainty-aware gated recurrent unit (GRU) network that models the temporal dynamics of static pressure distortion, outperforming polynomial and multi-layer perceptron (MLP) baselines. Integrated on an NVIDIA Jetson Xavier NX, the complete system supports closed-loop quadrotor flight at 30 m/s with drift under 2% over kilometer-scale trajectories. These contributions expand the operational envelope of thermal-inertial navigation, enabling reliable high-speed flight in visually degraded and GPS-denied environments.

Problem

• thermal-inertial odometry
• GPS-denied navigation
• high-speed flight
• embedded hardware
• visual degradation

Innovation

• thermal-inertial odometry
• embedded navigation
• laser depth prior
• vibration-robust IMU preintegration
• uncertainty-aware GRU