Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Victoria

$55,000.00

The message in the medium: bi-lateral human-robot communication

EF 2024-25

Résumé
Challenge: Addressing the current gap in robotics usability is crucial to unlocking the long-promised productivity gains in various human-involved tasks. Despite recent technical advancements, seamless interaction between robots and users in unstructured environments remains a challenge. This proposal asserts that facilitating natural and fluent communication between humans and robots is pivotal for enhancing productivity and fostering wider acceptance of robotics. For instance, improving a robot's ability to detect and respond to spatial social cues, such as right-of-way signals, can enhance navigation tasks and increase user acceptance. While language models have significantly improved verbal interfaces, there's a notable lag in the development of communication modalities like gestures, sounds, and motions. Response: This research leverages automated learning techniques to detect, select, and coordinate communication cues, focusing on three interconnected themes: social communication cue detection, learning communication cue parameterization, and enhancing robot monitoring and situational awareness through communication cues. Social cues play a vital role in communication, influencing collaboration in everyday interactions. This research explores the use of Transfer Entropy to identify meaningful social cues and leverage them to enhance the robot's interactive behaviour. Traditionally, robot cues are manually designed and tuned, but this work introduces an adaptive framework for efficiently exploring a cue's feature space to maximize user connection and retention between cue and meaning.  Additionally, the sheer volume of data generated by robot systems poses a challenge for human supervisors. This research delves into the use of multi-modal cues to help users monitor the overall status of a robot team, enabling swift identification of specific robot issues while preventing information overload. Overall, by focusing on natural communication and leveraging advanced learning techniques, this proposal aims to bridge the usability gap in robotics, paving the way for increased productivity and integration into social environments. Impact: Canada has been a leader in robotics and has advanced capabilities in kinematics, dynamics, controls, machine vision and AI. However, the emerging new wave of service robotics requires an investment in interaction technologies that captures the opportunities robotics can bring to SMEs. Recent work has attracted collaboration and funding from small and large robotics companies (Cross Compass, Amazon) and research institutes (DLR, CSIRO), with trainees obtaining academic roles at McGill, Queens, Deakin, University of Texas and joining Canadian companies like Cellula Robotics, A&K Robotics, Kardium, Motion Metrics, and YPC Technologies. This fundamental work will provide the discovery research capability capability for continued industry collaborations and produce a new cohort of robotics leaders.
Programme
Discovery Grants Program - Individual
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2024-04383
Name nom
Croft, Elizabeth
Department département
VP Academic and Provost
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
55000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
800
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information and communication services
Area of application fr
Services d'information et de télécommunications
Research subject code
2606
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Systems, man and cybernetics
Research subject fr
Systèmes, homme et cybernétique
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
The message in the medium: bi-lateral human-robot communication
Keywords
human-robot interaction; human-robot communication; cyber-physical system design; collaborative robotics; multi-modal communication; transfer entropy; multi robot systems
Application summary
Challenge: Addressing the current gap in robotics usability is crucial to unlocking the long-promised productivity gains in various human-involved tasks. Despite recent technical advancements, seamless interaction between robots and users in unstructured environments remains a challenge. This proposal asserts that facilitating natural and fluent communication between humans and robots is pivotal for enhancing productivity and fostering wider acceptance of robotics. For instance, improving a robot's ability to detect and respond to spatial social cues, such as right-of-way signals, can enhance navigation tasks and increase user acceptance. While language models have significantly improved verbal interfaces, there's a notable lag in the development of communication modalities like gestures, sounds, and motions. Response: This research leverages automated learning techniques to detect, select, and coordinate communication cues, focusing on three interconnected themes: social communication cue detection, learning communication cue parameterization, and enhancing robot monitoring and situational awareness through communication cues. Social cues play a vital role in communication, influencing collaboration in everyday interactions. This research explores the use of Transfer Entropy to identify meaningful social cues and leverage them to enhance the robot's interactive behaviour. Traditionally, robot cues are manually designed and tuned, but this work introduces an adaptive framework for efficiently exploring a cue's feature space to maximize user connection and retention between cue and meaning.  Additionally, the sheer volume of data generated by robot systems poses a challenge for human supervisors. This research delves into the use of multi-modal cues to help users monitor the overall status of a robot team, enabling swift identification of specific robot issues while preventing information overload. Overall, by focusing on natural communication and leveraging advanced learning techniques, this proposal aims to bridge the usability gap in robotics, paving the way for increased productivity and integration into social environments. Impact: Canada has been a leader in robotics and has advanced capabilities in kinematics, dynamics, controls, machine vision and AI. However, the emerging new wave of service robotics requires an investment in interaction technologies that captures the opportunities robotics can bring to SMEs. Recent work has attracted collaboration and funding from small and large robotics companies (Cross Compass, Amazon) and research institutes (DLR, CSIRO), with trainees obtaining academic roles at McGill, Queens, Deakin, University of Texas and joining Canadian companies like Cellula Robotics, A&K Robotics, Kardium, Motion Metrics, and YPC Technologies. This fundamental work will provide the discovery research capability capability for continued industry collaborations and produce a new cohort of robotics leaders.