Trust-driven interactive visual navigation for autonomous robots

We describe a model of “trust” in human-robot systems that is inferred from their interactions, and inspired by similar concepts relating to trust among humans. This computable quantity allows a robot to estimate the extent to which its performance is consistent with a human's expectations, with respect to task demands. Our trust model drives an adaptive mechanism that dynamically adjusts the robot's autonomous behaviors, in order to improve the efficiency of the collaborative team. We illustrate this trust-driven methodology through an interactive visual robot navigation system. This system is evaluated through controlled user experiments and a field demonstration using an aerial robot.

Authors

• Anqi Xu 0003
• Gregory Dudek

Keywords

• Robots
• Humans
• Visualization
• Navigation
• Adaptation models
• Target tracking
• Collaboration
• Autonomic System
• Machine Vision
• Visual System
• Interactive System
• Navigation System
• Trust Model
• Autonomous Behavior
• Task Performance
• Field Trials
• Fitting Line
• Robot Control
• Human Operator
• Autonomic Control
• Human-robot Interaction
• Task Load
• Degree Of Trust
• Utility Theory
• Collaborative System
• Autonomous Underwater Vehicles
• Global Mode
• Inverse Reinforcement Learning
• Boundary Edges
• Target Boundary
• Basic Trust
• Team Efficiency
• Operations Command
• Disjoint Regions
• Digital Image Processing
• K-means Algorithm
• Edge Elements