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

• URL: http://arxiv.org/abs/2603.02114v1
• Date: Mon, 02 Mar 2026 17:38:37 GMT
• Title: Real-Time Thermal-Inertial Odometry on Embedded Hardware for High-Speed GPS-Denied Flight
• Abstract summary: Real-time monocular thermal-inertialometry system designed for high-velocity, GPS-denied flight on embedded hardware.<n>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.
• Score: 3.3292574415204537
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Dense Soft Weighting for Radar Ego-Velocity Estimation [6.356174487225252]
  We present Dense Soft Weighting, an analytic radar front-end for ego-velocity estimation.<n>It maps every range-Doppler cell to a continuous confidence metric rather than enforcing a binary detection threshold.<n>It reduces mean absolute pose error by 31-45% relative to the strongest CFAR point-cloud baseline.
  arXiv  Detail & Related papers  (2026-07-29T14:37:52Z)
• physfusion: A Transformer-based Dual-Stream Radar and Vision Fusion Framework for Open Water Surface Object Detection [3.3795150675738808]
  PhysFusion is a physics-informed radar-image detection framework for water-surface perception.<n>It integrates a Physics-In Radar (PIR) with an RCS Mapper and Quality Gate, transforming per-point radar attributes into compact scattering priors.<n>Experiments on WaterScenes and FLOW demonstrate that PhysFusion achieves 59.7% mAP50:95 and 90.3% mAP50 on WaterScenes.
  arXiv  Detail & Related papers  (2026-03-02T15:00:22Z)
• How IMU Drift Influences Multi-Radar Inertial Odometry for Ground Robots in Subterranean Terrains [16.196972581962342]
  We propose a two-stage MRIO framework that combines an IMU bias estimator for resilient localization and mapping.<n>It maintains accuracy across cost-efficient FMCW radar setups and different IMUs, showing resilience with Pixhawk and higher-grade units such as VectorNav.<n>The proposed framework further supports radar-only mapping by exploiting the robot's estimated translational and rotational displacements.
  arXiv  Detail & Related papers  (2026-02-27T17:15:50Z)
• RadarEye: Robust Liquid Level Tracking Using mmWave Radar in Robotic Pouring [4.023217125139733]
  RadarEye is a real-time mmWave radar signal processing pipeline for liquid level estimation and tracking.<n>RadarEye achieves a 0.35 cm median absolute height error at 0.62 ms per update, substantially outperforming vision and ultrasound baselines.
  arXiv  Detail & Related papers  (2026-02-11T01:57:13Z)
• Radar-Inertial Odometry For Computationally Constrained Aerial Navigation [0.7310043452300737]
  We present Radar-Inertial Odometry (RIO) algorithms to fuse the information from IMU and radar.<n>We show a novel way to exploit advances in deep learning to retrieve 3D point correspondences in sparse and noisy radar point clouds.
  arXiv  Detail & Related papers  (2026-02-04T15:03:26Z)
• Vision-Language-Model-Guided Differentiable Ray Tracing for Fast and Accurate Multi-Material RF Parameter Estimation [45.40179208702883]
  This paper proposes a vision-language-model (VLM) guided framework that accelerates and stabilizes multi-material parameter estimation.<n> Experiments in NVIDIA Sionna on indoor scenes show 2-4$times$ faster convergence and 10-100$times$ lower final parameter error.
  arXiv  Detail & Related papers  (2026-01-26T07:54:53Z)
• SDG-Track: A Heterogeneous Observer-Follower Framework for High-Resolution UAV Tracking on Embedded Platforms [11.029096488950414]
  Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict.<n>We propose a Sparse Detection-Guided Tracker that adopts an Observer-Follower architecture to reconcile this conflict.<n>Experiments on a ground-to-air tracking station demonstrate that SDG-Track achieves 35.1 FPS system throughput while retaining 97.2% of the frame-by-frame detection precision.
  arXiv  Detail & Related papers  (2025-12-04T15:11:43Z)
• mmPred: Radar-based Human Motion Prediction in the Dark [43.00006337997152]
  Existing Human Motion Prediction methods based on RGB-D cameras are sensitive to lighting conditions and raise privacy concerns.<n>This work introduces radar as a novel sensing modality for HMP, for the first time.<n>We propose mmPred, the first diffusion-based framework tailored for radar-based HMP.
  arXiv  Detail & Related papers  (2025-11-29T06:26:55Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• Learning-based Airflow Inertial Odometry for MAVs using Thermal Anemometers in a GPS and vision denied environment [13.910943185843706]
  This work demonstrates an airflow based odometry system with multi-sensor data fusion, including thermal anemometer, IMU, ESC, and barometer.<n>We employ a GRU-based deep neural network to estimate relative air speed from noisy and disturbed anemometer measurements.<n>A complete flight data, including takeoff and landing on the ground, shows that the approach is able to decouple the downwash induced wind speed caused by propellers and the ground effect.
  arXiv  Detail & Related papers  (2025-05-21T02:53:49Z)
• Multi-photon enhanced resolution for Superconducting Nanowire Single-Photon Detector-based Time-of-Flight lidar systems [0.0]
  We report a lidar system based on waveguide-integrated SNSPDs that excels in temporal accuracy, which translates into high range resolution.<n>For single-shot measurements, we find resolution in the millimeter regime, resulting from the jitter of the time-of-flight signal of 21$,$ps for low photon numbers.<n>For multi-shot measurements we find sub-millimeter range-accuracy of 0.75$,$mm and reveal additional surface information of scanned objects.
  arXiv  Detail & Related papers  (2025-03-19T15:47:16Z)
• Optimal baseline exploitation in vertical dark-matter detectors based on atom interferometry [50.06952271801328]
  Several terrestrial detectors for gravitational waves and dark matter based on long-baseline atom interferometry are currently in the final planning stages or already under construction. We show that resonant-mode detectors based on multi-diamond fountain gradiometers achieve the optimal, shot-noise limited, sensitivity if their height constitutes 20% of the available baseline.
  arXiv  Detail & Related papers  (2023-09-08T08:38:24Z)
• Demo Abstract: Indoor Positioning System in Visually-Degraded Environments with Millimetre-Wave Radar and Inertial Sensors [44.58134907168034]
  We present a real-time indoor positioning system which fuses millimetre-wave (mmWave) radar and Inertial Measurement Units (IMU) data via deep sensor fusion. Good accuracy and resilience were exhibited even in poorly illuminated scenes.
  arXiv  Detail & Related papers  (2020-10-26T17:41:25Z)
• LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion [52.59664614744447]
  We present LiRaNet, a novel end-to-end trajectory prediction method which utilizes radar sensor information along with widely used lidar and high definition (HD) maps. automotive radar provides rich, complementary information, allowing for longer range vehicle detection as well as instantaneous velocity measurements.
  arXiv  Detail & Related papers  (2020-10-02T00:13:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.