Closed-Loop Output Error Approaches for Drone's Physics Informed Trajectory Inference

Perrusquía, Adolfo; Guo, Weisi

doi:10.1109/tac.2023.3247461

Cited by 9 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem requires additional analysis to first attenuate the noise and second to increase the prediction capabilities using the control information. This can be solved by incorporating novel state estimation and parameter identification techniques such as closed-loop output error techniques [32,33] and new methodologies for inverse reinforcement learning based on model predictive control and experience inference [34].…”

Section: Scope Discussion and Conclusionmentioning

confidence: 99%

Uncovering Drone Intentions using Control Physics Informed Machine Learning

Perrusquía

Guo

Fraser

et al. 2023

Preprint

View full text Add to dashboard Cite

Fully autonomous aerial platforms or drones are increasingly used across diverse application areas. Uncooperative drones do not announce their identity nor file flight plans and can pose a potential risk to a variety of critical infrastructures. Understanding an uncooperative drone's intention is important to assigning risk and executing countermeasures. Drones have rapidly changing design, flexible capabilities, and diverse underpinning algorithms. This makes distinguishing malicious from naive intentions across platforms difficult. Intentions are often intangible and unobservable, and a variety of tangible intention classes are often inferred as a proxy. However, inference of drone intention classes (e.g., via inverse learning) using observational data alone is inherently unreliable due to observational and learning bias. Here we develop a novel control-physics informed machine learning (CPhy-ML) that can robustly infer across intention classes, out performing over expert-defined anomaly detection and inverse learning approaches. Our CPhy-ML complementary learning couples the representation power of deep learning with the conservation laws of aerospace control models, reducing bias and instability. The results in simulation and experimentation demonstrate that we can find common intention patterns across the inferred intention classes, ranging from trajectory to reward goals. We believe that this framework can provide deeper insight into the complex nature of intention and a firm step towards to its smooth integration in current counter drone technologies. The techniques developed here can aid the enforcement of drone incursions in a time where geo-fencing is no-longer efficiently enforceable. As transport and operational autonomy is increasingly used, enforcement algorithms can also inform the design of better criminal justice system and safer autonomous systems themselves.

show abstract

Section: Scope Discussion and Conclusionmentioning

confidence: 99%

Uncovering Drone Intentions using Control Physics Informed Machine Learning

Perrusquía

Guo

Fraser

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In this paper, drone high-level intent is referred to the purpose of use of the drone [23], e.g., surveillance, inspection, delivery, etc. We focus on four high-level intent classes due to the low number of open-access datasets of drones mission profiles, however the approach can easily be extended for n distinct classes.…”

Section: Data Preparation and Radar Simulationmentioning

confidence: 99%

“…Moreover, additional flights are carry out using a DJI Mavic Air 2 to complement the perimeter and mapping intent classes. The telemetry data of each flight include longitude, latitude and altitude, which are converted into Cartesian coordinates [23] to avoid location bias. Furthermore, each flight class has different sampling time and hence, each dataset were down/up-sampled as required to standardised the sample time to 1 Hz.…”

Section: Data Preparation and Radar Simulationmentioning

confidence: 99%

Hybrid Deep Neural Networks for Drone High Level Intent Classification using Non-Cooperative Radar Data

Fraser,

Perrusquía,

Panagiotakopoulos

et al. 2023

2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)

Self Cite

View full text Add to dashboard Cite

The proliferation of drones has brought many benefits in different industrial and government sectors due to their low cost and potential applications. Nevertheless, the security and air space can be compromised due to anomalous performances derived to negligence or intentional malicious activities. Thus, identify the hidden intentions of drones' mission profiles is paramount to execute adequate countermeasures. In this paper, an hybrid deep neural network architecture is proposed to classify the high level intent of drones' mission profiles using non-cooperative radar. Radar measurements are created synthetically using open access telemetry data of flight trajectories. The proposed architecture exploits the classification and reconstruction capabilities of deep neural models to classify the drones hidden high-level intent. Several experiments and comparisons are carried out to verify the effectiveness of the proposed approach.

show abstract

“…In contrast with intention classification approaches 10 , 11 , intention inference methods have been adopted to predict the future trajectory of autonomous systems 12 and pedestrians 13 . The majority of these methods are data-driven learning models that use snap-shot data to cluster together drone attributes 7 to predict the trajectory in several time steps in the future 14 , 15 . However, the continuous flight physics has been left aside despite providing crucial information about the mission profile and intention.…”

Section: Introductionmentioning

confidence: 99%

Uncovering drone intentions using control physics informed machine learning

Perrusquía,

Guo,

Fraser

et al. 2024

Commun Eng

Self Cite

View full text Add to dashboard Cite

Unmanned Autonomous Vehicle (UAV) or drones are increasingly used across diverse application areas. Uncooperative drones do not announce their identity/flight plans and can pose a potential risk to critical infrastructures. Understanding drone’s intention is important to assigning risk and executing countermeasures. Intentions are often intangible and unobservable, and a variety of tangible intention classes are often inferred as a proxy. However, inference of drone intention classes using observational data alone is inherently unreliable due to observational and learning bias. Here, we developed a control-physics informed machine learning (CPhy-ML) that can robustly infer across intention classes. The CPhy-ML couples the representation power of deep learning with the conservation laws of aerospace models to reduce bias and instability. The CPhy-ML achieves a 48.28% performance improvement over traditional trajectory prediction methods. The reward inference results outperforms conventional inverse reinforcement learning approaches, decreasing the root mean squared spectral norm error from 3.3747 to 0.3229.

show abstract

Closed-Loop Output Error Approaches for Drone's Physics Informed Trajectory Inference

Cited by 9 publications

References 43 publications

Uncovering Drone Intentions using Control Physics Informed Machine Learning

Uncovering Drone Intentions using Control Physics Informed Machine Learning

Hybrid Deep Neural Networks for Drone High Level Intent Classification using Non-Cooperative Radar Data

Uncovering drone intentions using control physics informed machine learning

Contact Info

Product

Resources

About