Alexandre Arnold's research while affiliated with Airbus and other places

Publications (8)

Conference Paper
Full-text available
Avant un vol, les pilotes de ligne doivent lire une longue liste de messages appelés NOTAM (pour NOtice To AirMen) donnant des informations sur des aléas potentiels le long du vol. Ces messages suivent une grammaire particulière, contiennent beaucoup d'acronymes et un vocabulaire spécifique aéronautique. Dans cet article, un modèle de langue de typ...
Preprint
Full-text available
The aerospace industry relies on massive collections of complex and technical documents covering system descriptions, manuals or procedures. This paper presents a question answering (QA) system that would help aircraft pilots access information in this documentation by naturally interacting with the system and asking questions in natural language....
Conference Paper
Full-text available
The use of conversational agents within the aerospace industry offers quick and concise answers to complex situations. The aerospace domain is characterized by products and systems that are built over decades of engineering to reach high levels of performance within complex environments. Current development in conversational agents can leverage the...
Conference Paper
Full-text available
Dans cet article, nous présentons une démonstration de vi-sualisation de l'information extraite automatiquement de la partie textuelle des NOTAMs. Dans le domaine aéro-nautique, les NOTAMs sont des messages publiés par les agences gouvernementales de contrôle de la navigation aé-rienne. Nous détaillons la construction du jeu de données, les expérie...
Conference Paper
Full-text available
This paper introduces a research problem currently faced in the use of conversational agents within the aerospace industry. The aerospace domain is characterized by products and systems that are built over decades of engineering to reach high levels of performance within complex environments. This has resulted in technical documentation piling up o...
Conference Paper
Mission planning for Earth Observation Satellite operators typically implies dynamically altering how requests from different customers are prioritised in order to meet expected deadlines. A request corresponds to a given area of interest to capture on Earth. This exercise is challenging for different reasons. First, satellites are limited by maneu...

Citations

... It is well known that enterprise search applications have different needs than a traditional web search engine, including challenges such as searching over enterprise Intranets or multiple internal sources (Hawking, 2004). Furthermore, besides the use of CIS systems in a traditional office environment, many different applications of more varied and complex environments such as airplane pilots create an extra layer of complexity (Arnold et al., 2020;Gosper et al., 2021). Many open problems in the intersection of CIS applications and enterprise need further investigation. ...
... Even within the aerospace domain, conversational agents have been proposed to offer quick and concise answers to complex situations. For example, Liu et al. [14] mixed a task-oriented dialogue system with a conversational agent and an interactive question-answering component: the objective was to assess the benefit of smart search and conversational search for cockpit documentation. ...
... In aviation, there are several potential advantages to incorporating intelligent systems into the cockpit in the form of digital flight assistants (DFAs). Recent papers have noted that the complexity of technical information in the aerospace domain makes conversational systems potentially useful in the cockpit, but also particularly complex to design and evaluate [1,2]. DFAs could optimise route planning, alleviate the pilot's cognitive burden and provide detailed warnings of errors detected by sensors throughout the aircraft. ...
... MDPs extend the classical planning view on the world by the support of action-outcome uncertainty. MDPs have been utilized extensively in applications like unmanned aerial vehicle mission planning (Jeong et al., 2014;Feng et al., 2015), searchand-rescue missions (Teichteil-Königsbuch and Fabiani, 2006;Pineda et al., 2015), military operation planning (Aberdeen et al., 2004), controlling satellites (Povéda et al., 2019), and for modeling particular tasks in autonomous driving (Abbeel et al., 2008;Brechtel et al., 2011;Wei et al., 2011). ...