TY - GEN
T1 - Autonomous Causally-Driven Explanation of Actions
AU - Katz, Garrett E.
AU - Dullnig, Dale
AU - Davis, Gregory P.
AU - Gentili, Rodolphe J.
AU - Reggia, James A.
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2018/12/4
Y1 - 2018/12/4
N2 - We propose a cause-effect reasoning mechanism with which an autonomous system can justify planned actions to a human end user. The mechanism is based on a structure we call a 'causal plan graph,' which encodes the causal relationships between the actions, intentions, and goals of the autonomous system. Causal chains within this graph can potentially serve as intuitive, human-friendly justifications for the autonomous system's planned actions. A prototype of this mechanism is tested in simulation on a set of planning problems from an autonomous maintenance scenario. We demonstrate empirically that shortest path algorithms can effectively reduce a very large number of possible causal chains to a small, intelligible subset that might reasonably be inspected and ranked by a human. Consequently this work can serve as the basis for an experimental platform for future end user studies with human participants.
AB - We propose a cause-effect reasoning mechanism with which an autonomous system can justify planned actions to a human end user. The mechanism is based on a structure we call a 'causal plan graph,' which encodes the causal relationships between the actions, intentions, and goals of the autonomous system. Causal chains within this graph can potentially serve as intuitive, human-friendly justifications for the autonomous system's planned actions. A prototype of this mechanism is tested in simulation on a set of planning problems from an autonomous maintenance scenario. We demonstrate empirically that shortest path algorithms can effectively reduce a very large number of possible causal chains to a small, intelligible subset that might reasonably be inspected and ranked by a human. Consequently this work can serve as the basis for an experimental platform for future end user studies with human participants.
KW - cause-effect reasoning
KW - explainable artificial intelligence (XAI)
KW - imitation learning
KW - robotics
UR - http://www.scopus.com/inward/record.url?scp=85060603398&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060603398&partnerID=8YFLogxK
U2 - 10.1109/CSCI.2017.133
DO - 10.1109/CSCI.2017.133
M3 - Conference contribution
AN - SCOPUS:85060603398
T3 - Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
SP - 772
EP - 778
BT - Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
A2 - Tinetti, Fernando G.
A2 - Tran, Quoc-Nam
A2 - Deligiannidis, Leonidas
A2 - Yang, Mary Qu
A2 - Yang, Mary Qu
A2 - Arabnia, Hamid R.
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
Y2 - 14 December 2017 through 16 December 2017
ER -