<p>Space Situational Awareness (SSA) focuses on the observation and monitoring of satellites primarily by earth-based sensors. An important component of SSA is the detection of satellite manoeuvres. Given the large amount of data produced by manoeuvre detection systems, the interpretation of this data by end users can be challenging. In recent years, the ability of conversational agents to facilitate user interaction with large datasets has increased dramatically. They are now widely deployed across domains such as healthcare, education, government service centres, and retail. To enhance the ability of users to best interact with manoeuvre detection systems, we have developed SatChat: an intelligent conversational agent for querying the results of satellite manoeuvre detections. SatChat is a text-based chat interface, built to allow users to query the results of a manoeuvre detection system using natural language. The underlying models are open source. Experimental evaluations demonstrate SatChat’s accuracy (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="44163_2025_333_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="51" /> </InlineMediaObject> <EquationSource Format="TEX">\(88.24\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>88.24</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation>) and its ability to respond to complex queries. Moreover, our system can handle sensitive and confidential data without breaching privacy. This paper presents the results of deploying SatChat in conjunction with a particle filter based manoeuvre detection system.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

An intelligent conversational agent for querying satellite manoeuvre detections: a case study

  • Wathsala Karunarathne,
  • David P Shorten,
  • Matthew Roughan

摘要

Space Situational Awareness (SSA) focuses on the observation and monitoring of satellites primarily by earth-based sensors. An important component of SSA is the detection of satellite manoeuvres. Given the large amount of data produced by manoeuvre detection systems, the interpretation of this data by end users can be challenging. In recent years, the ability of conversational agents to facilitate user interaction with large datasets has increased dramatically. They are now widely deployed across domains such as healthcare, education, government service centres, and retail. To enhance the ability of users to best interact with manoeuvre detection systems, we have developed SatChat: an intelligent conversational agent for querying the results of satellite manoeuvre detections. SatChat is a text-based chat interface, built to allow users to query the results of a manoeuvre detection system using natural language. The underlying models are open source. Experimental evaluations demonstrate SatChat’s accuracy ( \(88.24\%\) 88.24 % ) and its ability to respond to complex queries. Moreover, our system can handle sensitive and confidential data without breaching privacy. This paper presents the results of deploying SatChat in conjunction with a particle filter based manoeuvre detection system.