A Deep Inverse-Mapping Model for a Flapping Robotic Wing

2025-02-13

AI Summary

To address the challenge of establishing real-time, invertible mappings between aerodynamic forces and wing kinematics for flapping-wing robots operating in unsteady flows, this paper proposes a lightweight sequence-to-sequence deep inverse model. Methodologically, we introduce an adaptive spectral layer to enable frequency-domain temporal representation learning and pioneer the application of a compact seq2seq architecture to the aerodynamic-force-to-kinematics inverse mapping task. Leveraging a high-fidelity 3D motion–force synchronized experimental platform (comprising high-speed cameras and a six-axis force sensor), we construct a multi-flow-regime dataset. Our model achieves an 11% reduction in median test loss and significantly outperforms Transformer-based models in inference speed—enabling embedded real-time closed-loop control. The code and dataset are publicly released, establishing a deployable inverse-control paradigm for bio-inspired aerial vehicles and medical microrobots.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• 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

In systems control, the dynamics of a system are governed by modulating its inputs to achieve a desired outcome. For example, to control the thrust of a quad-copter propeller the controller modulates its rotation rate, relying on a straightforward mapping between the input rotation rate and the resulting thrust. This mapping can be inverted to determine the rotation rate needed to generate a desired thrust. However, in complex systems, such as flapping-wing robots where intricate fluid motions are involved, mapping inputs (wing kinematics) to outcomes (aerodynamic forces) is nontrivial and inverting this mapping for real-time control is computationally impractical. Here, we report a machine-learning solution for the inverse mapping of a flapping-wing system based on data from an experimental system we have developed. Our model learns the input wing motion required to generate a desired aerodynamic force outcome. We used a sequence-to-sequence model tailored for time-series data and augmented it with a novel adaptive-spectrum layer that implements representation learning in the frequency domain. To train our model, we developed a flapping wing system that simultaneously measures the wing's aerodynamic force and its 3D motion using high-speed cameras. We demonstrate the performance of our system on an additional open-source dataset of a flapping wing in a different flow regime. Results show superior performance compared with more complex state-of-the-art transformer-based models, with 11% improvement on the test datasets median loss. Moreover, our model shows superior inference time, making it practical for onboard robotic control. Our open-source data and framework may improve modeling and real-time control of systems governed by complex dynamics, from biomimetic robots to biomedical devices.

Problem

• Inverse mapping for flapping-wing robots
• Machine-learning solution for aerodynamic forces
• Real-time control with adaptive-spectrum layer

Innovation

• Machine-learning inverse-mapping for flapping-wing robots
• Sequence-to-sequence model with adaptive-spectrum layer
• Real-time control with superior inference time