Explicable planning as minimizing distance from expected behavior

Anagha Kulkarni, Satya Gautam Vadlamudi, Yantian Zha, Yu Zhang, Tathagata Chakraborti, Subbarao Kambhampati

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

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.

Original languageEnglish (US)
Title of host publication18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages2075-2077
Number of pages3
ISBN (Electronic)9781510892002
StatePublished - Jan 1 2019
Event18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 - Montreal, Canada
Duration: May 13 2019May 17 2019

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume4
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
CountryCanada
CityMontreal
Period5/13/195/17/19

    Fingerprint

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering

Cite this

Kulkarni, A., Vadlamudi, S. G., Zha, Y., Zhang, Y., Chakraborti, T., & Kambhampati, S. (2019). Explicable planning as minimizing distance from expected behavior. In 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 (pp. 2075-2077). (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS; Vol. 4). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).