TY - GEN
T1 - Human interactive machine learning for trust in teams of autonomous robots
AU - Gutzwiller, Robert S.
AU - Reeder, John
PY - 2017/5/16
Y1 - 2017/5/16
N2 - Unmanned systems are increasing in number, while their manning requirements remain the same. To decrease manpower demands, machine learning techniques and autonomy are gaining traction and visibility. One barrier is human perception and understanding of autonomy. Machine learning techniques can result in 'black box' algorithms that may yield high fitness, but poor comprehension by operators. However, Interactive Machine Learning (IML), a method to incorporate human input over the course of algorithm development by using neuro-evolutionary machine-learning techniques, may offer a solution. IML is evaluated here for its impact on developing autonomous team behaviors in an area search task. Initial findings show that IML-generated search plans were chosen over plans generated using a non-interactive ML technique, even though the participants trusted them slightly less. Further, participants discriminated each of the two types of plans from each other with a high degree of accuracy, suggesting the IML approach imparts behavioral characteristics into algorithms, making them more recognizable. Together the results lay the foundation for exploring how to team humans successfully with ML behavior.
AB - Unmanned systems are increasing in number, while their manning requirements remain the same. To decrease manpower demands, machine learning techniques and autonomy are gaining traction and visibility. One barrier is human perception and understanding of autonomy. Machine learning techniques can result in 'black box' algorithms that may yield high fitness, but poor comprehension by operators. However, Interactive Machine Learning (IML), a method to incorporate human input over the course of algorithm development by using neuro-evolutionary machine-learning techniques, may offer a solution. IML is evaluated here for its impact on developing autonomous team behaviors in an area search task. Initial findings show that IML-generated search plans were chosen over plans generated using a non-interactive ML technique, even though the participants trusted them slightly less. Further, participants discriminated each of the two types of plans from each other with a high degree of accuracy, suggesting the IML approach imparts behavioral characteristics into algorithms, making them more recognizable. Together the results lay the foundation for exploring how to team humans successfully with ML behavior.
KW - Human automation interaction
KW - machine learning
KW - robots
KW - supervisory control
KW - unmanned vehicles
UR - http://www.scopus.com/inward/record.url?scp=85021390653&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85021390653&partnerID=8YFLogxK
U2 - 10.1109/COGSIMA.2017.7929607
DO - 10.1109/COGSIMA.2017.7929607
M3 - Conference contribution
AN - SCOPUS:85021390653
T3 - 2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management, CogSIMA 2017
BT - 2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management, CogSIMA 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management, CogSIMA 2017
Y2 - 27 March 2017 through 31 March 2017
ER -