Action trees for scalable goal recognition in robotic applications
Helen Harman, Keshav K. Chintamani, Pieter Simoens · Ghent University Academic Bibliography (Ghent University) · 2018
Robots are being deployed in a wide range of environments to assist humans with their daily activities.To assist a person, and avoid obstructing them when executing a different task, a robot needs to know what the intentions of the people are.In this short paper we present an early version of our work, in which we focus on goal recognition using techniques from classical symbolic planning to form an Action Tree.We present results which show improved goal recognition times, without compromising on accuracy.