TY - GEN
T1 - Explicable planning as minimizing distance from expected behavior
AU - Kulkarni, Anagha
AU - Vadlamudi, Satya Gautam
AU - Zha, Yantian
AU - Zhang, Yu
AU - Chakraborti, Tathagata
AU - Kambhampati, Subbarao
N1 - Funding Information:
This research is supported in part by the ONR grants N00014-16-1-2892, N00014-18-1-2442, N00014-18-1-2840, the AFOSR grant FA9550-18-1-0067, the NASA grant NNX17AD06G and the NSF grant IIS-1844524.
Publisher Copyright:
© 2019 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
PY - 2019
Y1 - 2019
N2 - In order to achieve effective human-AI collaboration, it is necessary for an AI agent to align its behavior with the human's expectations. When the agent generates a task plan without such considerations, it may often result in inexplicable behavior from the human's point of view. This may have serious implications for the human, from increased cognitive load to more serious concerns of safety around the physical agent. In this work, we present an approach to generate explicable behavior by minimizing the distance between the agent's plan and the plan expected by the human. To this end, we learn a mapping between plan distances (distances between expected and agent plans) and human's plan scoring scheme. The plan generation process uses this learned model as a heuristic. We demonstrate the effectiveness of our approach in a delivery robot domain.
AB - In order to achieve effective human-AI collaboration, it is necessary for an AI agent to align its behavior with the human's expectations. When the agent generates a task plan without such considerations, it may often result in inexplicable behavior from the human's point of view. This may have serious implications for the human, from increased cognitive load to more serious concerns of safety around the physical agent. In this work, we present an approach to generate explicable behavior by minimizing the distance between the agent's plan and the plan expected by the human. To this end, we learn a mapping between plan distances (distances between expected and agent plans) and human's plan scoring scheme. The plan generation process uses this learned model as a heuristic. We demonstrate the effectiveness of our approach in a delivery robot domain.
UR - http://www.scopus.com/inward/record.url?scp=85077074208&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077074208&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85077074208
T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
SP - 2075
EP - 2077
BT - 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
T2 - 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
Y2 - 13 May 2019 through 17 May 2019
ER -