A Narwhal-Inspired Sensing-to-Control Framework for Small Fixed-Wing Aircraft

2025-10-08

AI Summary

To address poor maneuverability and challenging airflow perception for small fixed-wing UAVs at low speeds, this paper proposes a bio-inspired, end-to-end perception–control framework motivated by the narwhal’s tusk. A multi-hole probe is deployed upstream in the far field to enhance freestream measurement accuracy; sparse wing-pressure sensing is fused with data-driven calibration for high-fidelity flow-field estimation. Soft left–right symmetry regularization improves dynamical identifiability under partial observability, decoupling control surface inputs from aerodynamic disturbances. A control-affine dynamical model is constructed via physics-informed modeling and convex control allocation. Wind-tunnel experiments demonstrate that adding pressure sensors reduces aerodynamic force estimation error by 25–30%; out-of-distribution generalization error increases only marginally (to 12% vs. baseline 44%); and normal-force tracking RMSE decreases by 27% relative to an affine baseline and by 34% relative to a non-structured baseline.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Bio-inspired Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Fixed-wing unmanned aerial vehicles (UAVs) offer endurance and efficiency but lack low-speed agility due to highly coupled dynamics. We present an end-to-end sensing-to-control pipeline that combines bio-inspired hardware, physics-informed dynamics learning, and convex control allocation. Measuring airflow on a small airframe is difficult because near-body aerodynamics, propeller slipstream, control-surface actuation, and ambient gusts distort pressure signals. Inspired by the narwhal's protruding tusk, we mount in-house multi-hole probes far upstream and complement them with sparse, carefully placed wing pressure sensors for local flow measurement. A data-driven calibration maps probe pressures to airspeed and flow angles. We then learn a control-affine dynamics model using the estimated airspeed/angles and sparse sensors. A soft left/right symmetry regularizer improves identifiability under partial observability and limits confounding between wing pressures and flaperon inputs. Desired wrenches (forces and moments) are realized by a regularized least-squares allocator that yields smooth, trimmed actuation. Wind-tunnel studies across a wide operating range show that adding wing pressures reduces force-estimation error by 25-30%, the proposed model degrades less under distribution shift (about 12% versus 44% for an unstructured baseline), and force tracking improves with smoother inputs, including a 27% reduction in normal-force RMSE versus a plain affine model and 34% versus an unstructured baseline.

Problem

• Addresses fixed-wing UAVs' lack of low-speed agility
• Measures distorted airflow using bio-inspired sensors and probes
• Learns control-affine dynamics to improve force tracking accuracy

Innovation

• Narwhal-inspired upstream probes with wing sensors
• Data-driven calibration for airspeed and flow angles
• Regularized dynamics learning with convex control allocation