MRS2003

Experiments in Human-Robot Teams: 

Experiments in Human-Robot Teams Curtis W. Nielsen, Michael A. Goodrich, Jacob W. Crandall Brigham Young University

Motivation: 

Motivation Search and Rescue Robotics Still in its infancy Current methods have very high workload

The Questions: 

The Questions How do human-robot interactions affect team performance and human workload? Where is the “Sweet Spot?”

Procedure: 

Procedure Domain Topological map-building Interaction Schemes Teleoperate Point to Point Region of Interest Experiment

Behavior-based Landmarks: 

Behavior-based Landmarks Set of behaviors afforded to the robot Affordance: “the perceived actionable properties between the world and an actor” (Gibson) Actor = robot Afforded behaviors: turn right, turn left, go forward Afforded behaviors are found using filtered sonar measurements

Building a Topological Map: 

Building a Topological Map Classify a landmark Disambiguate landmarks Choose an action

Characterizing the interaction schemes: 

Characterizing the interaction schemes Landmark classification Landmark disambiguation Choose an action Advantages Disadvantages

Teleoperate (TOL): 

Teleoperate (TOL) Choose an action: Human Landmark classification: Human Landmark disambiguation: Human Advantage: Human has very high control of the movement of the robot Disadvantage: The human must devote a lot of attention to the robot

Point To Point (PTP): 

Point To Point (PTP) Choose an action: Human Landmark classification: Robot Landmark disambiguation: Human Advantage: Relatively low workload Disadvantage: Requires human control for each new action

Region of Interest (ROI): 

Region of Interest (ROI) Choose an action: Human / Robot Landmark classification: Robot Landmark disambiguation: Robot Advantage: Very little human workload Disadvantage: Takes a long time to disambiguate landmarks

The interface: 

The interface

Joystick Control: 

Joystick Control Action Selection Landmark Classification Landmark Disambiguation

Point to Point Control: 

Point to Point Control Action Selection Landmark Classification Landmark Disambiguation

Region of Interest Control: 

Region of Interest Control Action Selection Landmark Recognition Landmark Disambiguation

Measuring Performance: 

Measuring Performance Time… The time it takes for the system to complete an accurate map of the environment.

Measuring Workload: Behavioral Entropy: 

Measuring Workload: Behavioral Entropy Entropy of the joystick (Boer) Velocity of the mouse. Button clicks on the mouse and joystick Change robots Scaling issues

Experiment: 10 subjects: 

Experiment: 10 subjects

Region of Interest: 

Region of Interest

Point to Point: 

Point to Point

Mixed with Joystick: 

Mixed with Joystick

Workload(without joystick): 

Workload (without joystick)

Elapsed Time (without joystick): 

Elapsed Time (without joystick)

Workload (with Joystick): 

Workload (with Joystick)

Elapsed Time (with Joystick): 

Elapsed Time (with Joystick)

Results: 

Results With Teleop Without Teleop Tradeoff Curve

Conclusions: 

Conclusions Measured performance and workload for a system where a human controls 3 robots in a map-building task. Analyzed the tradeoffs in terms of workload and performance of changing interaction schemes between robots. Found a sweet spot where performance is relatively high and workload is relatively low. Sweet spot can change as representation and autonomy level change.

Questions for Future Work: 

Questions for Future Work Vary the number of robots? Vary the number of users? Vary environment complexity? Dynamic autonomy? Workload measurements (scaling issues)?