aiqbench analysis
This research advances AI-driven robotics by replacing traditional dynamics models with differentiable neural surrogates to jointly optimize glider design and control policies. The approach significantly accelerates computation speed while improving performance on complex aerodynamic tasks like perching and landing.
Neural-Surrogate Co-Design of Aerodynamic Shape and Control
arXiv:2603.06760v2 Announce Type: replace-cross Abstract: Control co-design jointly optimizes a robot's physical design and its controller. Existing techniques are limited in the number of model parameters and the complexity of the physical models they can handle. In this paper, we propose a gradient-based bilevel formulation that replaces the dynamics models of earlier techniques with a differentiable neural surrogate and differentiates through the trajectory optimizer using a structure-exploiting approach. We validate the framework on fixed-wing gliders, using NeuralFoil as the aerodynamic surrogate. The tasks are maximum-distance gliding, minimum-distance landing, and perching. Experiments on 2D airfoils and 3D wings show that our method runs about five times faster than a state-of-the-art evolutionary baseline. It also outperforms pipelines that optimize aerodynamic proxy metrics.
Abstract:Control co-design jointly optimizes a robot's physical design and its controller. Existing techniques are limited in the number of model parameters and the complexity of the physical models they can handle. In this paper, we propose a gradient-based bilevel formulation that replaces the dynamics models of earlier techniques with a differentiable neural surrogate and differentiates through the trajectory optimizer using a structure-exploiting approach. We validate the framework on fixed-wing gliders, using NeuralFoil as the aerodynamic surrogate. The tasks are maximum-distance gliding, minimum-distance landing, and perching. Experiments on 2D airfoils and 3D wings show that our method runs about five times faster than a state-of-the-art evolutionary baseline. It also outperforms pipelines that optimize aerodynamic proxy metrics.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2603.06760 [cs.RO]
(or arXiv:2603.06760v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2603.06760 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 209 words
Related coverage
SHIFT-Truck: A High-Fidelity Aerodynamics Dataset and Benchmark for Pickup Trucks
arXiv · Oct 1, 2026
Spatio-Temporal Prediction of Unsteady Airfoil Aerodynamics Using Augmented Graph Neural Ordinary Differential Equations with Exogenous Controls
arXiv · Jul 22, 2026
CAD-Native Transformer Operators for AI-Aided Engineering
arXiv · Sep 30, 2026
Neural networks for spectral optimization
arXiv · Sep 30, 2026