Project Details
Description
Trust has been shown to be a crucial factor in the efficient use of automation.
Trust in Human-Robot Interaction increases the level of complexity due to the physical embodiment of the robot that shares the same space of the operator.
Research in trust has so far been restricted to post-hoc measurements of whole interaction episodes. This is useful as an analytical tool to statically optimize the system design, but does not support trust adjustment during the interaction to ensure efficient task completion.
The project was developed to achieve three objectives: (i) identification of trust indicators in industrial Human-Robot Collaboration scenario, (ii) sensorial data collection and training of machine learning models for dynamic real-time trust prediction, (iii) adapting robot behavior according to the level of trust predicted and thus ensuring efficient use of the robotic system.
Trust in Human-Robot Interaction increases the level of complexity due to the physical embodiment of the robot that shares the same space of the operator.
Research in trust has so far been restricted to post-hoc measurements of whole interaction episodes. This is useful as an analytical tool to statically optimize the system design, but does not support trust adjustment during the interaction to ensure efficient task completion.
The project was developed to achieve three objectives: (i) identification of trust indicators in industrial Human-Robot Collaboration scenario, (ii) sensorial data collection and training of machine learning models for dynamic real-time trust prediction, (iii) adapting robot behavior according to the level of trust predicted and thus ensuring efficient use of the robotic system.
Status | Active |
---|---|
Effective start/end date | 15/01/2022 → 15/01/2025 |
Keywords
- HRI
- Human robot trust
- Human Robot Interaction
- Collaborative Robotics
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.