Person-following by autonomous robots: A categorical overview

Abstract

A wide range of human-robot collaborative applications in diverse domains such as manufacturing, health care, the entertainment industry, and social interactions, require an autonomous robot to follow its human companion. Different working environments and applications pose diverse challenges by adding constraints on the choice of sensors, the degree of autonomy, and dynamics of a person-following robot. Researchers have addressed these challenges in many ways and contributed to the development of a large body of literature. This paper provides a comprehensive overview of the literature by categorizing different aspects of person-following by autonomous robots. Also, the corresponding operational challenges are identified based on various design choices for ground, underwater, and aerial scenarios. In addition, state-of-the-art methods for perception, planning, control, and interaction are elaborately discussed and their applicability in varied operational scenarios are presented. Then, some of the prominent methods are qualitatively compared, corresponding practicalities are illustrated, and their feasibility is analyzed for various usecases. Furthermore, several prospective application areas are identified, and open problems are highlighted for future research.

Toward a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection

“…Iterative search methods are then applied to find the target model in the feature-space [3]. Machine learning techniques are also widely used to learn the diver-specific features [18,23] and predict the target location in the featurespace. Performance of the model-free algorithms depend on comprehensiveness of the model descriptors and the underlying input feature-space.…”

“…The thresholded binary image is then refined to track the centroid of the target (diver) using algorithms such as meanshift, particle filters, etc. Optical flow-based methods can also be utilized to track divers' motion in the spatiotemporal volume [18,22].…”

“…AdaBoost learns a strong tracker from a large number of simple feature-based diver trackers. Several other machine learning techniques have been investigated for diver tracking and underwater object tracking in general [18]. One major challenge involved in using these models is to design a set of robust features that are invariant to noise, lighting condition, and other variabilities such as divers' swimming motion and wearables.…”

Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning Approaches

“…The task we consider in this paper is aimed to proximity human-robot interaction [21], [22]: a drone should be able to fly at an appropriate distance in front of people, following them [23] while waiting for possible command gestures [24]. The use of visual markers [25] simplifies this task but, in general, more sophisticated techniques, like Tracking-Learning-Detection [26], are needed [27].…”

Visual Diver Recognition for Underwater Human-Robot Collaboration

“…This work is a combination of people tracking and identification tasks; a rich body of literature exists in this domain [14]. Niyogi and Adelson [21] use the positions of the head and ankles to detect human walking patterns orthogonal to camera view direction.…”