Search Results for author: John-Paul Clarke

Found 7 papers, 2 papers with code

From Voice to Safety: Language AI Powered Pilot-ATC Communication Understanding for Airport Surface Movement Collision Risk Assessment

no code implementations6 Mar 2025 Yutian Pang, Andrew Paul Kendall, Alex Porcayo, Mariah Barsotti, Anahita Jain, John-Paul Clarke

We show the effectiveness of our approach by simulating two case studies, (a) the Henada airport runway collision accident happened in January 2024; (b) the KATL taxiway collision happened in September 2024.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

A Reinforcement Learning Approach to Quiet and Safe UAM Traffic Management

no code implementations15 Jan 2025 Surya Murthy, John-Paul Clarke, Ufuk Topcu, Zhenyu Gao

Urban air mobility (UAM) is a transformative system that operates various small aerial vehicles in urban environments to reshape urban transportation.

Management Multi-agent Reinforcement Learning +2

The Reliability of Remotely Piloted Aircraft System Performance under Communication Loss and Latency Uncertainties

no code implementations13 Jan 2025 Yutian Pang, Andrew Paul Kendall, John-Paul Clarke

We start with examining and deriving mathematical formulations of key reliability metrics of Required Communication Performance (RCP).

Cluster & Disperse: a general air conflict resolution heuristic using unsupervised learning

no code implementations8 Jan 2025 Mirmojtaba Gharibi, John-Paul Clarke

Using unsupervised learning, the core idea of our heuristic is to cluster the conflict points and disperse them in various flight levels.

ARC

Noise-Aware and Equitable Urban Air Traffic Management: An Optimization Approach

no code implementations1 Jan 2024 Zhenyu Gao, Yue Yu, Qinshuang Wei, Ufuk Topcu, John-Paul Clarke

Urban air mobility (UAM), a transformative concept for the transport of passengers and cargo, faces several integration challenges in complex urban environments.

Fairness Management

Risk-aware Urban Air Mobility Network Design with Overflow Redundancy

1 code implementation8 Jun 2023 Qinshuang Wei, Zhenyu Gao, John-Paul Clarke, Ufuk Topcu

In our methodology, we first model how disruptions to a given UAM network might impact on the nominal traffic flow and how this flow might be re-accommodated on an extended network with reserve capacity.

Management

Finite-Sample Analysis of Nonlinear Stochastic Approximation with Applications in Reinforcement Learning

1 code implementation27 May 2019 Zaiwei Chen, Sheng Zhang, Thinh T. Doan, John-Paul Clarke, Siva Theja Maguluri

To demonstrate the generality of our theoretical results on Markovian SA, we use it to derive the finite-sample bounds of the popular $Q$-learning with linear function approximation algorithm, under a condition on the behavior policy.

Q-Learning reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.