Maintaining efficient collaboration with trust-seeking robots

In this work, we grant robot agents the capacity to sense and react to their human supervisor's changing trust state, as a means to maintain the efficiency of their collaboration. We propose the novel formulation of Trust-Aware Conservative Control (TACtiC), in which the agent alters its behaviors momentarily whenever the human loses trust. This trust-seeking robot framework builds upon an online trust inference engine and also incorporates an interactive behavior adaptation technique. We present end-to-end instantiations of trust-seeking robots for distinct task domains of aerial terrain coverage and interactive autonomous driving. Empirical assessments comprise a large-scale controlled interaction study and its extension into field evaluations with an autonomous car. These assessments substantiate the efficiency gains that trust-seeking agents bring to asymmetric human-robot teams.

Authors

• Anqi Xu 0003
• Gregory Dudek

Keywords

• Robots
• Teamwork
• Visualization
• Context
• Navigation
• Probabilistic logic
• Efficient Collaboration
• Interactive
• Control Study
• Adaptive Behavior
• Self-driving
• Inference System
• Large-scale Interaction
• Robotic Agents
• Human Intervention
• User Study
• Subjective Assessment
• Behavioral Alterations
• Friedman Test
• Interactive Experience
• Robot Control
• Interactive Sessions
• Autonomous Agents
• Degree Of Trust
• Objective Metrics
• Loss Of Trust
• Conservation Behavior
• Trust Model
• Subjective Metrics
• Team Efficiency
• Optimal Set Of Hyperparameters
• User Trust
• Task Scenarios
• Robotics Research
• Conservation Status
• Robotic Technology