Reservoir Computing for Drone Trajectory Intent Prediction: A Physics Informed Approach

Perrusquía, Adolfo; Guo, Weisi

doi:10.1109/tcyb.2024.3379381

Cited by 4 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[84], the differences in the wave pattern of the moving ROV can be employed to perform reservoir computations. Such computations can help predict an optimal trajectory of the ROV based on the previous inputs of the human operator and taking into account the environmental factors, including the speed of wind, temperature and salinity of water as well as the presence of obstacles such as rocks and debris [92,93]. Since the ROV creates the waves that are used to predict the trajectory, the on-board reservoir computer does not consume significant energy apart from the need to power the sensors, thereby satisfying the requirements for autonomous AI systems [34].…”

Section: Towards Reservoir Computing With Water Waves Created By An Rovmentioning

confidence: 99%

“…Before discussing those results, we also highlight the proposals of physical RC systems designed to predict the trajectory of a flying drone [93,95]. Although the idea of using physical processes taking place in the surrounding environment of the drone were not expressed in Ref.…”

Section: Physical Reservoir Computing Using Fluid Flow Disturbancesmentioning

confidence: 99%

“…Although the idea of using physical processes taking place in the surrounding environment of the drone were not expressed in Ref. [93,95], the approach presented there can be extended to implement the concepts illustrated in Figure 1a, b. In this context, we remind that the discipline of fluid dynamics is concerned with the flow of both liquids and gases [96].…”

Section: Physical Reservoir Computing Using Fluid Flow Disturbancesmentioning

confidence: 99%

See 2 more Smart Citations

Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective

Abbas,

Abdel-Ghani,

Maksymov

2024

Preprint

View full text Add to dashboard Cite

Artificial intelligence (AI) systems of autonomous systems such as drones, robots and self-driving cars may consume up to 50% of total power available onboard, thereby limiting the vehicle’s range of functions and considerably reducing the distance the vehicle can travel on a single charge. Next-generation onboard AI systems need an even higher power since they collect and process even larger amounts of data in real time. This problem cannot be solved using the traditional computing devices since they become more and more power-consuming. In this review article, we discuss the perspectives of development of onboard neuromorphic computers that mimic the operation of a biological brain using nonlinear-dynamical properties of natural physical environments surrounding autonomous vehicles. Previous research also demonstrated that quantum neuromorphic processors (QNPs) can conduct computations with the efficiency of a standard computer while consuming less than 1% of the onboard battery power. Since QNPs is a semi-classical technology, their technical simplicity and low, compared with quantum computers, cost make them ideally suitable for application in autonomous AI system. Providing a perspective view on the future progress in unconventional physical reservoir computing and surveying the outcomes of more than 200 interdisciplinary research works, this article will be of interest to a broad readership, including both students and experts in the fields of physics, engineering, quantum technologies and computing.

show abstract

Section: Towards Reservoir Computing With Water Waves Created By An Rovmentioning

confidence: 99%

Section: Physical Reservoir Computing Using Fluid Flow Disturbancesmentioning

confidence: 99%

Section: Physical Reservoir Computing Using Fluid Flow Disturbancesmentioning

confidence: 99%

See 1 more Smart Citation

Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective

Abbas,

Abdel-Ghani,

Maksymov

2024

Preprint

View full text Add to dashboard Cite

show abstract

Uncovering Reward Goals in Distributed Drone Swarms Using Physics-Informed Multiagent Inverse Reinforcement Learning

Perrusquía,

Guo

2025

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective

Abbas,

Abdel-Ghani,

Maksymov

2024

Dynamics

View full text Add to dashboard Cite

Artificial intelligence (AI) systems of autonomous systems such as drones, robots and self-driving cars may consume up to 50% of the total power available onboard, thereby limiting the vehicle’s range of functions and considerably reducing the distance the vehicle can travel on a single charge. Next-generation onboard AI systems need an even higher power since they collect and process even larger amounts of data in real time. This problem cannot be solved using traditional computing devices since they become more and more power-consuming. In this review article, we discuss the perspectives on the development of onboard neuromorphic computers that mimic the operation of a biological brain using the nonlinear–dynamical properties of natural physical environments surrounding autonomous vehicles. Previous research also demonstrated that quantum neuromorphic processors (QNPs) can conduct computations with the efficiency of a standard computer while consuming less than 1% of the onboard battery power. Since QNPs are a semi-classical technology, their technical simplicity and low cost compared to quantum computers make them ideally suited for applications in autonomous AI systems. Providing a perspective on the future progress in unconventional physical reservoir computing and surveying the outcomes of more than 200 interdisciplinary research works, this article will be of interest to a broad readership, including both students and experts in the fields of physics, engineering, quantum technologies and computing.

show abstract

Reservoir Computing for Drone Trajectory Intent Prediction: A Physics Informed Approach

Cited by 4 publications

References 47 publications

Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective

Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective

Uncovering Reward Goals in Distributed Drone Swarms Using Physics-Informed Multiagent Inverse Reinforcement Learning

Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective

Contact Info

Product

Resources

About