Exploring Human-Robot Trust during Emergency Evacuations Alan R - PowerPoint PPT Presentation

Exploring Human-Robot Trust during Emergency Evacuations Alan R Wagner Asst. Prof. Aerospace Engineering Research Associate, Rock Ethics Institute Penn State University In collaboration with: Ayanna Howard, Georgia Tech Paul Robinette, MIT

Emergency Evacuations (nist.gov)

Emergency Evacuations

Emergency Evacuations Evacuees tend to exit through the same door they entered (NIST, 2005) High casualties at choke points (100 dead in 2003 Station Nightclub Fire)

Emergency Evacuations Exit signs are differ depending on the location No consensus on sign color, design

Robot Platforms Virtual N=196 $0.50 each • Must be able to communicate directions • Directional and approach/do not approach 6

Robot Platforms Virtual N=196 $0.50 each Remote N=128 $1.00 each 7

Robot Platforms Virtual N=196 $0.50 each Remote N=128 $1.00 each Physical N=48 $10.00 each 8

Robot Platforms Virtual N=196 $0.50 each Remote N=128 $1.00 each The Physical N=48 winner $10.00 each 9

Designing a Robotic Guide • Other failed designs

Emergency Guidance Robot Design Conclusions • Studies involved 368 participants 11

Emergency Guidance Robot Design Conclusions • Studies involved 368 participants • Robots can communicate guidance instructions: – Robot motion alone insufficient to communicate instructions – Dynamic sign very effective when near – Multiple arms allow easily understandable instructions to be communicated 12

Emergency Guidance Robot Design Conclusions • Studies involved 368 participants • Robots can communicate guidance instructions: – Robot motion alone insufficient to communicate instructions – Dynamic sign very effective when near – Multiple arms allow easily understandable instructions to be communicated • Results are consistent between virtual, remote, and physical presence experiments 13

Human-Robot Trust The robots are understandable, but are they trustworthy? 14

Human-Robot Trust W. Bainbridge, et al. 2011 M. Desai, et. al. 2013 15 Institute for Human and Machine Cognition M. Salem, et al. 2015

Human-Robot Trust Trust is “a belief, held by the trustor, that the trustee will act in a manner that mitigates the trustor’s risk in a situation in which the trustor has put its outcomes at risk.” Key point: risk (Wagner, Dissertation, 2009) Based on Lee and See 2004 ;

Factors that Impact Trust Trustee Trustor related related Situation related

To Trust or Not to Trust No trust: the outcome is 6, the trustee’s action doesn’t matter, i.e. no risk! Trustor Trust: risk 6 for a possible Lean back Don’t lean gain of 12 back Trustee Catch 6 12 4 6 Don’t catch 6 0 4 6

How much Trust? Trust  risk Loss calculated from Model based action outcome matrix uncertainty where x is predicted y is the true value Trustee related Situation specific factors factors

Office Evacuation Experiments • Virtual High Risk Experimental Setting • Efficient vs. Circuitous Robot Performance Robot Guides Experiment Participant to Emergency! Introduction Room Participant Chooses Survey Exit 20 (Robinette, Howard, Wagner, Trans. Human-Machine Systems, 2017) 20

Virtual Office Evacuation 21

Virtual Office Evacuation 22

Virtual Office Evacuation 23

Virtual Office Evacuation • 114 Participants • $2.00 payment • Demographics: – Mean age: 31.8 – 60.5% male 24

Virtual Office Evacuation • 114 Participants • $2.00 payment • Demographics: – Mean age: 31.8 – 60.5% male 25

Virtual Office Evacuation • 114 Participants • $2.00 payment • Demographics: – Mean age: 31.8 – 60.5% male • How do we repair broken trust? 26

Trust Repair Label Statement Promise “I promise to be a better guide next time.” Apology “I'm very sorry it took so long to get here.” Internal Attribution “I'm very sorry it took so long to get here. I had trouble seeing the room, but I fixed my camera.” External Attribution “I'm very sorry it took so long to get here. My programmers gave me the wrong map of the office but I have the right one now.” Distance Information “This exit is closer.” Congestion Information “The other exit is blocked.” (Robinette, Howard, Wagner, ICSR 2015) 27

Repairing Trust : Promise: or 0 External Attribution: 1 and 0 Apology: statement that resulted in negative outcomes for trustee

Trust Repair Conditions 844 Participants C1: Repair trust after mistake Robot Guides Experiment Participant to Emergency! Introduction Room Participants C2: Repair before Survey Chooses Exit emergency decision 29

Trust Repair Efficient'Control' During'Emergency'Repair' Circuitous'Control' A>er'Viola; on'Repair' After circ. navigation 30

Trust Repair Efficient'Control' During'Emergency'Repair' Circuitous'Control' A>er'Viola; on'Repair' After circ. navigation 31

Trust Repair Efficient'Control' During'Emergency'Repair' Circuitous'Control' A>er'Viola; on'Repair' After circ. navigation 39 % 32

Trust Repair Efficient'Control' During'Emergency'Repair' Circuitous'Control' A>er'Viola; on'Repair' After circ. navigation 21 % 33

Trust Repair Conditions 800 More Participants C1: Repair trust after mistake Robot Guides Experiment Participant to Emergency! Introduction Room Participants C2: Repair before Survey Chooses Exit emergency decision 34

Trust Repair Efficient'Control' During'Emergency'Repair' Circuitous'Control' A>er'Viola; on'Repair' After circ. navigation 49 % 35

Trust Repair Takeaways • Message timing matters • Message content matters – Null messages don’t repair trust – Messages displayed too briefly don’t repair trust. Messages must be consciously considered. – Apologies and promises successfully manipulate trust repair • Subject motivation matters – No emergency = coin toss decision-making 36

Trust Repair Takeaways Trust Variation with Timing Hypothesis: 80 Memory/affect of the 69.69 70 experience is short 58.33 60 50 Percentage Does impact the results 40 33.33 but not completely. 30 22.58 20 Memory of the error or 10 of the repair? 0 Early Early Small Late Small Late Survey Survey Cases

Physical Office Evacuation (Robinette, Howard, Wagner, HRI 2016) 38

Emergency Evacuation 39

Emergency Evacuation 40

Emergency Evacuation 41

Emergency Evacuation 42

Emergency Evacuation 43

Emergency Evacuation • 26 participants – 13 in Efficient – 13 in Circuitous • Solicited from Georgia Tech • Compensation $10 • Not told about emergency • IRB Approved 44

Emergency Evacuation 45

Emergency Evacuation 46

Physical Office Evacuation 47

Emergency Evacuation

Emergency Evacuation 49

Physical Office Evacuation • Everyone followed the robot! • New conditions: – Broken Robot – Immobilized Robot – Incorrect Guidance 50

Immobilized Robot (n=5) 51

Immobilized Robot (n=5) 52

Incorrect Guidance (n=6) 53

Incorrect Guidance (n=6) 54

Incorrect Guidance (n=6) 55

Incorrect Guidance (n=6) 56

Most People Follow the Robot

Physical Office Evacuation • Low scores on realism scale, but noticeable change on confusion scale • Few noticed exit sign • Focused on robot • Stated trust in the robot • Currently developing follow- up experiments 58

Follow up Study By Booth et al. • Will students open a secure door for a robot? • Students recently warned about security • Unaware that they were in an experiment • 80% opened the door when the robot had an excuse • In post interviews, 15 stated that they considered the robot might have a bomb, 13 allowed it in anyway (Booth et al, HRI 2017) 59

Overtrust of Healthcare Robots • Surveyed parents of children with mobility disorder about exoskeletons • 55% expected their child to climb, jump, or run with device • 62% stated that they would typically trust their child to handle risky situations • The average of the children was 9. (Borenstein, Wagner, Howard, 2018)

Examples of Overtrust In Simulation Tracks of position Round 1 Round 2 Green line is robot; Blue is person

Conclusions • People are trusting, probably too trusting • Virtual evaluations may not capture visceral nature of trust situations • Timing impacts human decisions to trust • Certain factors may cause one be to ignore reputation • Why do people overtrust robots? • How do we create machines that will calibrate a user’s trust?

Future/Upcoming Work • Trying to understand why and when people overtrust – the person – the situation • Exploring other high risk/visceral situations. • Goal is to create a model that the robot can use