Embodied Communication: How Robots and People Communicate Through Physical Interaction

Abstract

Early research on physical human–robot interaction (pHRI) has necessarily focused on device design—the creation of compliant and sensorized hardware, such as exoskeletons, prostheses, and robot arms, that enables people to safely come in contact with robotic systems and to communicate about their collaborative intent. As hardware capabilities have become sufficient for many applications, and as computing has become more powerful, algorithms that support fluent and expressive use of pHRI systems have begun to play a prominent role in determining the systems’ usefulness. In this review, we describe a selection of representative algorithmic approaches that regulate and interpret pHRI, describing the progression from algorithms based on physical analogies, such as admittance control, to computational methods based on higher-level reasoning, which take advantage of multimodal communication channels. Existing algorithmic approaches largely enable task-specific pHRI, but they do not generalize to versatile human–robot collaboration. Throughout the review and in our discussion of next steps, we therefore argue that emergent embodied dialogue—bidirectional, multimodal communication that can be learned through continuous interaction—is one of the next frontiers of pHRI. Expected final online publication date for the Annual Review of Control, Robotics, and Autonomous Systems, Volume 14 is May 2023. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Collaborative robots can augment human cognition in regret-sensitive tasks

“…A robot’s hardware and software determine the format in which the robot can communicate with the human. Notable human–robot communication paradigms include tablets, natural language, gestures, programming interfaces, and human motion ( 66–68 ). Yet, improvements to the mechanical abilities of robots typically occur without the involvement of human users.…”

Sentiment analysis and opinion mining on educational data: A survey

“…• Benchmark datasets to span different models, datasets, or domains, and evaluating unlearning techniques on these benchmark datasets [179], [180]. Benchmark datasets can facilitate standardized evaluations of unlearning techniques across diverse settings and provide insights into their transferability and generalizability.…”

Data-efficient human walking speed intent identification

“…Autonomous mobile robots may navigate around moving humans (Aoude et al, 2013 ), whereas robotic lower-limb prostheses (Wentink et al, 2013 ; Yuan et al, 2022 ) and exoskeletons (Jung et al, 2012 ; Zhang et al, 2022b ) support stable, efficient gait in coordination with the user. These applications all require the ability to reason about what the human aims to accomplish (Malmi, 2013 ; Abbink et al, 2018 ; Chauhan et al, 2019 ; Khalin et al, 2021 ; Kalinowska et al, 2023 ). Robots assisting locomotion rely on a variety of sensors to glean information related to the human’s intentions.…”