Suchen und Finden
Preface
6
AAAI-2014 Spring Symposium Organizers
7
AAAI-2014 Spring Symposium: Keynote Speakers
7
Symposium Program Committee
8
Contents
12
1 Introduction
14
1.1 The Intersection of Robust Intelligence (RI) and Trust in Autonomous Systems
14
1.2 Background of the 2014 Symposium
15
1.3 Contributed Chapters
17
References
22
2 Towards Modeling the Behavior of Autonomous Systems and Humans for Trusted Operations
24
2.1 Introduction
24
2.2 Understanding the Value of Context
26
2.3 Context and the Complexity of Anomaly Detection
26
2.3.1 Manifolds for Anomaly Detection
27
2.4 Reinforcement Learning for Anomaly Detection
28
2.4.1 Reinforcement Learning
29
2.4.2 Supervised Autonomy
30
2.4.3 Feature Identification and Selection
31
2.4.4 Approximation Error for Alarming and Analysis
32
2.4.5 Illustration
33
2.4.5.1 Synthetic Domain
33
2.4.5.2 Real-World Domain
35
2.5 Predictive and Prescriptive Analytics
39
2.6 Capturing User Interactions and Inference
39
2.7 Challenges and Opportunities
41
2.8 Summary
42
References
43
3 Learning Trustworthy Behaviors Using an Inverse Trust Metric
45
3.1 Introduction
45
3.2 Related Work
47
3.2.1 Human-Robot Trust
47
3.2.2 Behavior Adaptation
47
3.3 Agent Behavior
49
3.4 Inverse Trust Estimate
49
3.5 Trust-Guided Behavior Adaptation
51
3.5.1 Evaluated Behaviors
52
3.5.2 Behavior Adaptation
53
3.6 Evaluation
54
3.6.1 eBotworks Simulator
55
3.6.2 Experimental Conditions
55
3.6.3 Evaluation Scenarios
56
3.6.3.1 Movement Scenario
56
3.6.3.2 Patrolling Scenario
58
3.6.4 Trustworthy Behaviors
59
3.6.5 Efficiency
62
3.6.6 Discussion
63
3.7 Conclusions
63
References
64
4 The “Trust V”: Building and Measuring Trust in Autonomous Systems
66
4.1 Introduction
66
4.2 Autonomy, Automation, and Trust
68
4.3 Dimensions of Trust
73
4.3.1 Trust Dimensions Arising from Automated Systems Attributes
73
4.3.2 Trust Dimensions Arising from Autonomous Systems Attributes
74
4.3.3 Another Trust Dimension: SoS
74
4.4 Creating Trust
75
4.4.1 Building Trust In
76
4.5 The Systems Engineering V-Model
77
4.6 The Trust V-Model
78
4.6.1 The Trust V Representation: Graphic
79
4.6.2 The Trust V Representation: Array
80
4.6.3 Trust V “Toolbox”
81
4.7 Specific Trust Example: Chatter
83
4.8 Measures of Effectiveness
84
4.9 Conclusions and Next Steps
86
A.1 Appendix
87
References10
87
5 Big Data Analytic Paradigms: From Principle Component Analysis to Deep Learning
89
5.1 Introduction
89
5.2 Wind Data Description
90
5.3 Wind Power Forecasting Via Nonparametric Models
90
5.3.1 Advanced Neural Network Architectures Application
91
5.3.2 Wind Speed Results
93
5.4 Introduction to Deep Architectures
94
5.4.1 Training Deep Architectures
100
5.4.2 Training Restricted Boltzmann Machines
100
5.4.3 Training Autoencoders
102
5.5 Conclusions
104
References
105
6 Artificial Brain Systems Based on Neural Network Discrete Chaotic Dynamics. Toward the Development of Conscious and Rational Robots
106
6.1 Introduction
106
6.2 Background
108
6.3 Numerical Simulations
114
6.4 Conclusion
121
References
122
7 Modeling and Control of Trust in Human-Robot Collaborative Manufacturing
123
7.1 Introduction
123
7.2 Trust Model
126
7.2.1 Time-Series Trust Model for Dynamic HRC Manufacturing
126
7.2.2 Robot Performance Model
127
7.2.3 Human Performance Model
127
7.3 Neural Network Based Robust Intelligent Controller
129
7.4 Control Approaches: Intersection of Trust and Robust Intelligence
130
7.4.1 Manual Mode
131
7.4.2 Autonomous Mode
131
7.4.3 Collaborative Mode
132
7.5 Simulation
132
7.5.1 Manual Mode
133
7.5.2 Autonomous Mode
135
7.5.3 Collaborative Mode
135
7.5.4 Comparison of Control Schemes
135
7.6 Experimental Validation
136
7.6.1 Experimental Test Bed
136
7.6.2 Experimental Design
136
7.6.2.1 Experiment Scenario
137
7.6.2.2 Controlled Behavioral Study
139
7.6.2.3 Imposing Fatigue
139
7.6.2.4 Experiment Procedure
141
7.6.2.5 Measurements and Scales
141
7.6.3 Experimental Results
142
7.6.3.1 Trust Model Identification Procedure
142
7.6.3.2 Manual Mode
142
7.6.3.3 Autonomous Mode
143
7.6.3.4 Collaborative Mode
144
7.6.4 Comparison and Conclusion
145
7.7 Conclusion
147
References
147
8 Investigating Human-Robot Trust in Emergency Scenarios: Methodological Lessons Learned
150
8.1 Introduction
150
8.2 Conceptualizing Trust
151
8.2.1 Conditions for Situational Trust
153
8.3 Related Work on Trust and Robots
155
8.4 Crowdsourced Narratives in Trust Research
155
8.4.1 Iterative Development of Narrative Phrasing
157
8.5 Crowdsourced Robot Evacuation
162
8.5.1 Single Round Experimental Setup
162
8.5.2 Multi-Round Experimental Setup
163
8.5.3 Asking About Trust
164
8.5.4 Measuring Trust
165
8.5.5 Incentives to Participants
165
8.5.6 Communicating Failed Robot Behavior
168
8.6 Conclusion
170
References
171
9 Designing for Robust and Effective Teamwork in Human-Agent Teams
174
9.1 Introduction
174
9.2 Related Work
175
9.2.1 Team Structure
175
9.2.2 Shared Mental Model and Team Situation Awareness
176
9.2.3 Communication
177
9.3 Experiment 1: Team Structure and Robustness
178
9.3.1 Testbed
178
9.3.2 Experiment Design
180
9.3.3 Results
181
9.3.3.1 Duplicated Work
181
9.3.3.2 Under Utilization of Vehicles
183
9.3.3.3 Infrequent Communication
184
9.4 Experiment 2: Information-Sharing
185
9.4.1 Independent Variables
185
9.4.2 Dependent Variables
187
9.4.3 Participants
187
9.4.4 Procedure
188
9.4.5 Results
188
9.4.5.1 Team Performance
188
9.4.5.2 Team Coordination
190
9.4.5.3 Workload
193
9.4.5.4 User Preference and Comments
194
9.5 Discussion
195
9.6 Conclusion
195
References
196
10 Measuring Trust in Human Robot Interactions: Development of the “Trust Perception Scale-HRI”
198
10.1 Introduction
198
10.2 Creation of an Item Pool
200
10.3 Initial Item Pool Reduction
202
10.3.1 Experimental Method
203
10.3.2 Experimental Results
204
10.3.3 Key Findings and Changes
205
10.4 Content Validation
205
10.4.1 Experimental Method
206
10.4.2 Experimental Results
207
10.5 Task-Based Validity Testing: Does the Score Change Over Time with an Intervention?
210
10.5.1 Experimental Method
211
10.5.2 Experimental Results
212
10.5.2.1 Individual Item Analysis
212
10.5.2.2 Trust Score Validation
212
10.5.2.3 40 Items Versus 14 Items
214
10.6 Task-Based Validity Testing: Does the Scale Measure Trust?
215
10.6.1 Experimental Method
215
10.6.2 Experimental Results
216
10.6.2.1 Correlation Analysis of the Three Scales
216
10.6.2.2 Pre-post Interaction Analysis
217
10.6.2.3 Differences Across Scales and Conditions
218
10.6.3 Experimental Discussion
219
10.7 Conclusion
219
10.7.1 The Trust Perception Scale-HRI
219
10.7.2 Instruction for Use
221
10.7.3 Current and Future Applications
222
References
223
11 Methods for Developing Trust Models for Intelligent Systems
226
11.1 Introduction
226
11.2 Prior Work in the Development of Trust Models
228
11.2.1 Trust Models
230
11.2.2 Trust in Human-Robot Interaction (HRI)
231
11.3 The Use of Surveys as a Method for Developing Trust Models
233
11.3.1 Methodology
234
11.3.2 Results and Discussion
235
11.3.3 Modeling Trust
242
11.4 Robot Studies as a Method for Developing Trust Models
243
11.4.1 Methodology
243
11.4.2 Results and Discussion
250
11.4.2.1 Reducing Situation Awareness (SA)
250
11.4.2.2 Providing Feedback
251
11.4.2.3 Reducing Task Difficulty
253
11.4.2.4 Long-Term Interaction
254
11.4.2.5 Impact of Timing of Periods of Low Reliability
256
11.4.2.6 Impact of Age
256
11.4.3 Modeling Trust
257
11.5 Conclusions and Future Work
258
References
259
12 The Intersection of Robust Intelligence and Trust: Hybrid Teams, Firms and Systems
262
12.1 Introduction
262
12.1.1 Background
263
12.2 Theory
265
12.3 Outline of the Mathematics
267
12.3.1 Field Model
267
12.3.2 Interdependence
269
12.3.3 Incompleteness and Uncertainty
269
12.4 Evidence of Incompleteness for Groups
270
12.4.1 The Evidence from Studies of Organizations
271
12.4.2 Modeling Competing Groups with Limit Cycles
271
12.5 Gaps
273
12.6 Conclusions
274
References
275
Alle Preise verstehen sich inklusive der gesetzlichen MwSt.