Efficient Training of Transfer Mapping in Physics-Infused Machine Learning Models of UAV Acoustic Field

Iqbal, R.; Behjat, Amir; Adlakha, Revant; Callanan, Jesse; Nouh, M.; Chowdhury, Souma

doi:10.2514/6.2022-0384

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To model the acoustic noise signature of the UAV, a simple yet modular wave-based computational acoustic model is utilized that can be tuned to a variety of noise sources by simply varying the input parameters to the model. It should be noted that higher fidelity models that are capable of capturing the intricate physics of sound reflection and diffusion due to obstacles and walls in the environment (e.g., (Callanan et al, 2021; Iqbal et al, 2022)) could be similarly integrated with the current framework. Following this, an add-on iterative path-correction algorithm was presented with the goal of ensuring environmental compliance of the optimal paths given based on a given sound exposure level standard.…”

Section: Discussionmentioning

confidence: 99%

“…Characterizing the acoustic signature of a mobile robot is a complex but principal step towards developing algorithms aiming to reduce the noise perceived by human operators in a collaborative work environment. High fidelity simulations (Mankbadi et al, 2020;Mankbadi et al, 2021) and experimental measurements (Callanan et al, 2021;Blanchard et al, 2020;Torija et al, 2021;Ning et al, 2017;Kloet et al, 2017;Iqbal et al, 2022) have been previously used for this purpose. Recently, Callanan et al conducted SPL measurements of a live hovering DJI Phantom in an indoor environment using a custom-built microphone array and trained a machine learning model to predict the SPL at desired locations (Callanan et al, 2021).…”

Section: Modeling Of Uav Acoustic Signaturementioning

confidence: 99%

See 1 more Smart Citation

Integration of acoustic compliance and noise mitigation in path planning for drones in human–robot collaborative environments

Adlakha

Liu

Chowdhury

et al. 2022

Journal of Vibration and Control

Self Cite

View full text Add to dashboard Cite

This work presents a framework aimed at mitigating adverse effects of high-amplitude drone noise ranging from hearing loss to reduced productivity in human–robot collaborative environments by infusing acoustic awareness in a path planning algorithm without imposing any additional design layers or hardware to an operational drone. Following a detailed outline of the proposed approach, it is shown that a significant reduction of noise levels perceived by human workers at noise-sensitive locations is realized via a path planner which generates optimal paths ranging from quietest to shortest paths. The approach is then augmented with a path-correction mechanism which accounts for noise exposure duration to ensure the aforementioned optimal paths are compliant with a given industrial/environmental standard. The correction mechanism enforces an adjustment of subsets of the planned paths inside quiet zones designated around noise-sensitive locations. The presented concepts were verified using numerical simulations conducted for a 2-dimensional rasterized obstacle field followed by a statistical design of experiments. The proposed framework is highly versatile and integrable with widely used industrial path planners, rendering it a highly valuable tool for noisy collaborative workplaces.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Modeling Of Uav Acoustic Signaturementioning

confidence: 99%

Integration of acoustic compliance and noise mitigation in path planning for drones in human–robot collaborative environments

Adlakha

Liu

Chowdhury

et al. 2022

Journal of Vibration and Control

Self Cite

View full text Add to dashboard Cite

show abstract

“…In all of these sequential hybrid-ML models however, the presence of an external partial physics model increases the complexity and cost of the training process. Previously [38], this hurdle was overcome by programming custom loss functions which include the partial physics in PyTorch [39] to enable backpropagation. However, this approach may not be feasible in all domains as PyTorch is not optimal for general purpose scientific computing (especially numerical methods).…”

Section: Introductionmentioning

confidence: 99%

Physics Infused Machine Learning Based Prediction of VTOL Aerodynamics with Sparse Datasets

Oddiraju

Amin²,

Piedmonte³

et al. 2023

AIAA AVIATION 2023 Forum

View full text Add to dashboard Cite

Complex optimal design and control processes often require repeated evaluations of expensive objective functions and consist of large design spaces. Data-driven surrogate models such as neural networks and Gaussian processes provide an attractive alternative to expensive simulations and are utilized frequently to represent these objective functions in optimization. However, pure data-driven models, due to a lack of adherence to basic physics laws and constraints, are often poor at generalizing and extrapolating. This is particularly the case, when training occurs over sparse high-fidelity datasets. A class of Physicsinfused machine learning (PIML) models integrate ML models with low-fidelity partial physics models to improve generalization performance while retaining computational efficiency. This paper presents two potential approaches for Physics infused modelling of aircraft aerodynamics which incorporate Artificial Neural Networks with a low-fidelity Vortex Lattice Method model with blown wing effects (BLOFI) to improve prediction performance while also keeping the computational cost tractable. This paper also develops an end-to-end auto differentiable open-source framework that enables efficient training of such hybrid models. These two PIML modelling approaches are then used to predict the aerodynamic coefficients of a 6 rotor eVTOL aircraft given its control parameters and flight conditions. The models are trained on a sparse high-fidelity dataset generated using a CHARM model. The trained models are then compared against the vanilla low-fidelity model and a standard pure data-driven ANN. Our results show that one of the proposed architecture outperforms all the other models and at a nominal increase in execution time. These results are promising and pave way to PIML frameworks which are able generalize over different aircraft and configurations thereby significantly reducing costs of design and control.

show abstract

Auto-Differentiable Transfer Mapping Architecture for Physics-Infused Learning of Acoustic Field

Iqbal

Behjat

Adlakha

et al. 2024

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

Efficient Training of Transfer Mapping in Physics-Infused Machine Learning Models of UAV Acoustic Field

Cited by 3 publications

References 26 publications

Integration of acoustic compliance and noise mitigation in path planning for drones in human–robot collaborative environments

Integration of acoustic compliance and noise mitigation in path planning for drones in human–robot collaborative environments

Physics Infused Machine Learning Based Prediction of VTOL Aerodynamics with Sparse Datasets

Auto-Differentiable Transfer Mapping Architecture for Physics-Infused Learning of Acoustic Field

Contact Info

Product

Resources

About