Combining Planning with Gaze for Online Human Intention Recognition
By Ronal Singh, Tim Miller, Joshua Newn, Liz Sonenberg, Eduardo Velloso, Frank Vetere. 2018
38 citations recorded by the source corpus.
Intention recognition is the process of using behavioural cues to infer an agent's goals or future behaviour. People use many behavioural cues to infer others' intentions, such as deliberative actions, facial expressions, eye gaze, and gestures. In artificial intelligence, two approaches for intention recognition, among others, are gaze-based and model-based intention recognition. Approaches in the former class use gaze to determine which parts of a space a person looks at more often to infer a person's intention. Approaches in the latter use models of possible future behaviour to rate intentions as more likely if they are a better 'fit' to observed actions. In this paper, we propose a novel model of human intention recognition that combines gaze and model-based approaches for online human intention recognition. Gaze data is used to build probability distributions over a set of possible intentions, which are then used as priors in a model-based intention recognition algorithm. In human-behavioural experiments ( n =20) involving a multi-player board game, we found that adding gaze-based priors to model-based intention recognition more accurately determined intentions ( p < 0.01), determined those intentions earlier ( p < 0.01), and at no additional cost; all compared to a model-based-only approach.
Subfields: Computer Vision and Pattern Recognition, Social Psychology, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
In Social Psychology
In Human-Computer Interaction
Citations in the corpus
- Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, positive): “3, concepts such as abnormality could be used to infer likely foils, but techniques for HCI, such as eye gaze [163] and gestures could be used to infer foils in some applications.”
- A Grounded Interaction Protocol for Explainable Artificial Intelligence (2019, methodology): “rom Pittsburgh to Houston) and a city area opponent might be interested in (e.g Interested around Houston). Predictions are generated from the implemented intent recognition algorithm of Singh et al. [29]. The wizard follows a simple natural language template: prediction followed by the explanation.”