Jason Gauci

ORCID: 0000-0002-8575-3911
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Air Traffic Management and Optimization
  • Aerospace and Aviation Technology
  • Mobile and Web Applications
  • Human-Automation Interaction and Safety
  • Autonomous Vehicle Technology and Safety
  • Evolutionary Algorithms and Applications
  • Computational Physics and Python Applications
  • Distributed and Parallel Computing Systems
  • Advanced Vision and Imaging
  • Educational Games and Gamification
  • Transportation and Mobility Innovations
  • Robotic Path Planning Algorithms
  • Artificial Intelligence in Games
  • Traffic control and management
  • Scientific Computing and Data Management
  • Computer Graphics and Visualization Techniques
  • Augmented Reality Applications
  • Vehicle Dynamics and Control Systems
  • Robotics and Sensor-Based Localization
  • Reinforcement Learning in Robotics
  • Metaheuristic Optimization Algorithms Research
  • Risk and Safety Analysis
  • Advanced Memory and Neural Computing
  • Target Tracking and Data Fusion in Sensor Networks
  • Multimedia Communication and Technology

University of Malta
2015-2025

Telenor (Norway)
2015

University of Central Florida
2007-2014

CollegeAmerica
2014

Consumer Healthcare Products Association
2014

Springer Nature (United States)
2014

Cranfield University
2008-2009

Research in neuroevolution—that is, evolving artificial neural networks (ANNs) through evolutionary algorithms—is inspired by the evolution of biological brains, which can contain trillions connections. Yet while neuroevolution has produced successful results, scale natural brains remains far beyond reach. This article presents a method called hypercube-based NeuroEvolution Augmenting Topologies (HyperNEAT) that aims to narrow this gap. HyperNEAT employs an indirect encoding connective...

10.1162/artl.2009.15.2.15202 article EN Artificial Life 2009-01-14

Looking to nature as inspiration, for at least the past 25 years, researchers in field of neuroevolution (NE) have developed evolutionary algorithms designed specifically evolve artificial neural networks (ANNs). Yet ANNs evolved through NE lack distinctive characteristics biological brains, perhaps explaining why is not yet a mainstream subject computation. Motivated by this gap, letter shows that when geometry introduced hypercube-based augmenting topologies algorithm, they begin acquire...

10.1162/neco.2010.06-09-1042 article EN Neural Computation 2010-03-17

In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry RL problems where datasets are large (millions billions of observations), the feedback loop slow (vs. a simulator), and experiments must be done with care because they don't run in simulator. Unlike other platforms, which often for fast prototyping experimentation, production use cases as top mind. The contains workflows train...

10.48550/arxiv.1811.00260 preprint EN other-oa arXiv (Cornell University) 2018-01-01

Connectivity patterns in biological brains exhibit many repeating motifs. This repetition mirrors inherent geometric regularities the physical world. For example, stimuli that excite adjacent locations on retina map to neurons are similarly visual cortex. That way, neural connectivity can exploit locality outside world by employing local connections brain. If such could be discovered methods evolve artificial networks (ANNs), then they exploited solve problems would otherwise require...

10.1145/1276958.1277158 article EN 2007-07-07

The aviation industry has proposed multiple solutions to reduce fuel consumption, air pollution and noise at airports, one of which involves deploying electric trucks for aircraft towing between the stand runway. However, introduction tow results in increased surface traffic, posing challenges from perspective Air Traffic Controller's (ATCO). Various involving automated planning execution have been proposed, but many are constrained by their inability manage active runways...

10.20944/preprints202403.0076.v1 preprint EN 2024-03-04

Ground collisions between aircraft and other obstacles in aerodrome areas are quite common, causing a lot of inconvenience to passengers, airport operators airlines. This paper presents an onboard non-collaborative system detect track generic around the wingtips large transport when maneuvering on ramps taxiways. The requirements such outlined it is shown that stereo vision most appropriate technology for this application. Then, setup its processing blocks discussed detail. has been tested...

10.2514/6.2009-5866 article EN AIAA Guidance, Navigation and Control Conference 2009-06-14

Touch screen technology is already present on the flight deck of various categories aircraft, with majority current solutions based use multiple touch displays situated main instrument panel and/or central pedestal. This often requires crew to lean forward or sideways interact different and makes it harder make accurate selections, particularly in turbulent conditions.

10.1109/dasc.2015.7311398 article EN 2015 IEEE/AIAA 34th Digital Avionics Systems Conference (DASC) 2015-09-01

RAID is one of nine European projects co-financed by SESAR Joint Undertaking with the purpose to investigate integration Remotely Piloted Aircraft Systems (RPAS) in non-segregated airspaces. The main objective this project successfully and safely fly an RPAS un-segregated airspace a multi-aircraft manned flight environment. Both Real-Time simulations Humans – –loop (RTS-HIL) Flight Trails several different scenarios are foreseen project. En-Route Operations RPAS, entering leaving Temporary...

10.2514/6.2015-3407 article EN 14th AIAA Aviation Technology, Integration, and Operations Conference 2015-06-18

Abstract Game-tree search is the engine behind many computer game opponents. Traditional game-tree algorithms decide which move to make based on simulating actions, evaluating future board states, and then applying evaluations estimate optimal play by all players. Yet limiting factor of such that space increases exponentially with number actions taken (i.e. depth search). More recent research in has revealed even more important than states effective pruning space. Accordingly, this paper...

10.1145/2001576.2001629 article EN 2011-07-12

The aviation industry has proposed multiple solutions to reduce fuel consumption, air pollution, and noise at airports, one of which involves deploying electric trucks for aircraft towing between the stand runway. However, introduction tow results in increased surface traffic, posing challenges from perspective traffic controllers (ATCOs). Various involving automated planning execution have been proposed, but many are constrained by their inability manage active runways simultaneously,...

10.3390/aerospace11040307 article EN cc-by Aerospace 2024-04-14

There is an ever-increasing urge to integrate unmanned air systems (UAS) into the same airspace as manned aircraft. A step towards achieving this goal develop Sense and Avoid (SAA) capabilities provide UAS with required technology detect maneuver around traffic. This paper details algorithm which enables vehicle reach a target waypoint by following shortest path avoiding fixed obstacles moving In context, multi-layer planner developed enable planning of trajectories in cluttered environment...

10.1109/icuas.2018.8453481 article EN 2022 International Conference on Unmanned Aircraft Systems (ICUAS) 2018-06-01

To date, most of the interactions between pilots and avionic systems commercial passenger aircraft are carried out using physical controls. This paper discusses evaluation a multimodal interface which allows to control various combination touchscreen gestures (via single interface) voice commands. was evaluated by eight airline in fixed-based flight simulator. Although improvements can be made interface, evaluations successfully demonstrated feasibility potential benefits flight.

10.1109/dasc.2018.8569607 article EN 2015 IEEE/AIAA 34th Digital Avionics Systems Conference (DASC) 2018-09-01

This paper addresses pilot error due to distractions, lack of situational awareness and misjudgment separation during taxi manoeuvers.A display is being developed minimize these errors assist pilots determine safe passage while navigating taxi.Part the development consisted implementation a tracking algorithmbased on particle filterwhich presented in this paper.The algorithm tracks obstacles that have been detected reconstructed using stereo vision techniques.Afterwards, tracked are...

10.2514/6.2019-1265 article EN AIAA SCITECH 2022 Forum 2019-01-06
Coming Soon ...