Deceptive path-planning

Masters, P and Sardina, S 2017, 'Deceptive path-planning', in Carles Sierra (ed.) Proceedings of the 26h International Joint Conferences on Artifical Intelligence (IJCAI 2017), Melbourne, Australia, 19-25 August 2017, pp. 4368-4375.


Document type: Conference Paper
Collection: Conference Papers

Title Deceptive path-planning
Author(s) Masters, P
Sardina, S
Year 2017
Conference name IJCAI 2017
Conference location Melbourne, Australia
Conference dates 19-25 August 2017
Proceedings title Proceedings of the 26h International Joint Conferences on Artifical Intelligence (IJCAI 2017)
Editor(s) Carles Sierra
Publisher AAAI Press
Place of publication Palo Alto, California United States
Start page 4368
End page 4375
Total pages 8
Abstract Deceptive path-planning involves finding a path such that the probability of an observer identifying the path's final destination - before it has been reached - is minimised. This paper formalises deception as it applies to path-planning and introduces the notion of a last deceptive point (LDP) which, when measured in terms of 'path completion', can be used to rank paths by their potential to deceive. Building on recent developments in probabilistic goal-recognition, we propose a formula to calculate an optimal LDP and present strategies for the generation of deceptive paths by both simulation ('showing the false') and dissimulation ('hiding the real').
Subjects Adaptive Agents and Intelligent Robotics
Keyword(s) Planning and Scheduling: Activity and Plan Recognition Planning and Scheduling: Model-Based Reasoning Robotics and Vision: Motion and Path Planning
Copyright notice © 2017 International Joint Conferences on Artificial Intelligence
ISBN 9780999241103
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Access Statistics: 67 Abstract Views  -  Detailed Statistics
Created: Mon, 18 Dec 2017, 09:53:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us