Learning dynamics for improving control of overactuated flying systems
This addresses control challenges for overactuated flying systems used in applications like industrial inspection, but it is incremental as it builds on existing model-based and data-driven methods.
The paper tackles the problem of high-performance trajectory tracking for overactuated flying vehicles by combining a data-driven Gaussian Process regressor with a first-principle model to improve control, resulting in a 32% average reduction in attitude trajectory error compared to a nominal PID controller.
Overactuated omnidirectional flying vehicles are capable of generating force and torque in any direction, which is important for applications such as contact-based industrial inspection. This comes at the price of an increase in model complexity. These vehicles usually have non-negligible, repetitive dynamics that are hard to model, such as the aerodynamic interference between the propellers. This makes it difficult for high-performance trajectory tracking using a model-based controller. This paper presents an approach that combines a data-driven and a first-principle model for the system actuation and uses it to improve the controller. In a first step, the first-principle model errors are learned offline using a Gaussian Process (GP) regressor. At runtime, the first-principle model and the GP regressor are used jointly to obtain control commands. This is formulated as an optimization problem, which avoids ambiguous solutions present in a standard inverse model in overactuated systems, by only using forward models. The approach is validated using a tilt-arm overactuated omnidirectional flying vehicle performing attitude trajectory tracking. The results show that with our proposed method, the attitude trajectory error is reduced by 32% on average as compared to a nominal PID controller.