Behaviour Recognition with Kinodynamic Planning Over Continuous Domains

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.

Real-Time Online Goal Recognition in Continuous Domains via Deep Reinforcement Learning

“…Keyhole recognition describes a recognition process where the observed intelligent agent is unaware of the recognition process, and where the recognition process faces the challenge of partially observable inputs. While most goal recognition methods based on planning [7,10,25] are based on discrete domains, Vered and Kaminka [13,14,26] provided the first formal definition of goal recognition in continuous domains, which has since been further explored in subsequent studies [8].…”

“…Its aim is to infer the top-level goal of an agent based on input observation sequences and output an explanation of the observation sequence [1]. Currently, goal recognition has been applied in various fields, including intelligent assistants [2,3], autonomous driving [4,5], robot navigation [6,7], military confrontation [8], and more [9]. For example, in the application of goal recognition in a smart home assistant [2,3], the input observation sequence consists of a series of actions performed by a person as observed by a camera.…”