Behaviour Recognition with Kinodynamic Planning Over Continuous Domains

Grady Fitzpatrick; Nir Lipovetzky; Michael Papasimeon; Miquel Ramirez; Mor Vered

doi:10.3389/frai.2021.717003

Behaviour Recognition with Kinodynamic Planning Over Continuous Domains

Front Artif Intell. 2021 Oct 25:4:717003. doi: 10.3389/frai.2021.717003. eCollection 2021.

Authors

Grady Fitzpatrick¹, Nir Lipovetzky¹, Michael Papasimeon², Miquel Ramirez¹, Mor Vered³

Affiliations

¹ The University of Melbourne, Parkville, VIC, Australia.
² Defence Science and Technology Group (DSTG), Edinburgh, SA, Australia.
³ Monash University, Melbourne, VIC, Australia.

Abstract

We investigate the application of state-of-the-art goal recognition techniques for behaviour recognition over complex continuous domains using model predictive control (MPC) for trajectory generation. We formally define the problem of kinodynamic behaviour recognition and establish a set of baseline behaviours and performance measures in the complex domain of unmanned aerial maneuvers. We evaluate how well our approach performs over a range of standard aerial maneuvers and representative initial configurations of varying complexity. The work also highlights future research directions in compound model-based behaviour recognition and team behaviour recognition where multiple agents may be acting simultaneously.

Keywords: aerial maneuvering; behaviour recognition; model predictive control (MPC); online recognition; plan recognition as planning.