How to Communicate Robot Motion Intent: A Scoping Review

Abstract

a) Motion [120] (b) Attention [67] (c) State [117] (d) Instruction [128] Fig. 1. (a) Robot motion intent: The robot communicates its intended motion (e.g., a trajectory of the robot's intended movement path is visualized in Augmented Reality [120]). Furthermore, our analysis revealed three additional types of intent that complement robot motion intents. (b) Attention: A robot aims to catch the user's attention for subsequent movement activity (e.g., by moving its whole body [67]). (c) State: A robot communicates its state so that a human can predict future motions and identify potential conflicts before they occur (e.g., the robot communicates its movement activity with the help of a colored LED stripe [117]). (d) Instruction: The robot aims to provide specific instructions so that the human can assist further movement (e.g., by requesting to open a door [128]).Robots are becoming increasingly omnipresent in our daily lives, supporting us and carrying out autonomous tasks. In Human-Robot Interaction, human actors benefit from understanding the robot's motion intent to avoid task failures and foster collaboration. Finding effective ways to communicate this intent to users has recently received increased research interest. However, no common language has been established to systematize robot motion intent. This work presents a scoping review aimed at unifying existing knowledge.Based on our analysis, we present an intent communication model that depicts the relationship between robot and human through different intent dimensions (intent type, intent information, intent location). We discuss these different intent dimensions and their interrelationships with different kinds of robots and human roles. Throughout our analysis, we classify the existing research literature along our intent communication model, allowing us to identify key patterns and possible directions for future research.

HaptiX: Vibrotactile Haptic Feedback for Communication of 3D Directional Cues

“…Future Research: In our work, we aim to apply this approach to communicate the intended movements [20] of a semi-autonomous robot in collaborative scenarios, where vision alone may not be sufficient to successfully predict robot motion. In Figure 5 an assistive robot arm is illustrated, which is manually controlled by the user but is supported through an Artificial Intelligence (AI) which provides real time directional movement recommendations.…”

AdaptiX - A Transitional XR Framework for Development and Evaluation of Shared Control Applications in Assistive Robotics

“…In recent years, a growing body of research addressed these concerns and associated optimization options to increase their usability, e.g., [11,19,33]. During the AdaptiX development process, we aimed to include functionality to address the challenges of shared control optimization [18], intent communication [43], and attention guidance [45].…”

AR-supported Human-Robot Collaboration: Facilitating Workspace Awareness and Parallelized Assembly Tasks

“…One line of research has explored this in the context of designing familiar (i.e., human-like) and therefore predictable movement patterns [6,20]. More commonly, communication of a robot's intent happens through the presentation of digital information [44], e.g., by visualization of the planned movement path in AR. Providing AR guidance is typically done in three ways: through a display situated in the operator's environment [5,13,33], through projection mapping on surfaces [2,19,24], or with an HMD displaying content directly in front of the operator's eyes [11,35,42,46,49].…”

“…Recent years have seen an increase in research for supporting collaboration between humans and robots [39]. Augmented reality (AR) has shown great promise to support this collaboration [51], in particular within: communicating robot intent (e.g., [2,44,52]), dynamic task allocation (e.g., [30,45]), and step-by-step instructions (e.g., [3,19]). These works show promising results within their individual subjects, however, there is a lack of work that explores how these topics influence each other.…”