Towards robots reasoning about group behavior of museum visitors: Leader detection and group tracking

Abstract

Abstract. The field of human-robot interaction (HRI) is a broad community encompassing robotics, artificial intelligence (AI), human-computer interaction (HCI), psychology and social science. HRI in social robotics explores important issues in designing a robot system that works with people in daily life environments, capable of interacting with, modeling, and learning from humans. Robotic systems should improve their capabilities to not only understand humans but also to convey their intention within their actions. The present work demonstrates this behaviour is achievable through a field study conducted at a science museum. This article introduces a computer vision algorithm which is able to detect and track a leader within a group of peoplethe science communicator, for this particular case -and distinguish between group members and non-group members as well, all by means of a cognitive and logical behaviour analysis of their interactions on scene. The leader's direction is also computed as an attention reference for this approach. The computer vision system is supervising people within a group following a guide to prevent accidents and missing persons. This work represents one of a wide range of possible applications and future scenarios where group interactions are a key aspect for robots to understand and effectively participate in social environments.

Using Deep Learning for Collecting Data about Museum Visitor Behavior

“…In particular, the possibility of providing museum curators and staff members with a system to track visitor behavior for improving the service offered is a widely investigated topic. In [11], the authors propose a computer vision algorithm based on Kinect and RGB-D camera. They track groups of visitors at the National Museum of Emerging Science and Innovation (Miraikan) in Tokyo, Japan, to identify the leader and study their dynamics.…”

“…In [11], the authors propose a computer vision algorithm based on Kinect and RGB-D camera. They track visitor groups in a museum to identify the leader and study its dynamics.…”

Human-Like Guide Robot that Proactively Explains Exhibits

“…Regarding the treatment of multiple visitors, from the view of a function of the system, the current robot can also handle groups by extending the condition part of the episode rules. However, since the situation where groups of visitors look around becomes complex [37], we need to model the situation and define episode rules for appropriate behaviors in the situation. For example, even with regard to the order of explanation, it is unclear that the robot should approach to which of the following visitors: a visitor who is looking at an exhibit for a long time, a repeater, or a family including children.…”