Inferring Human Intent from Video by Sampling Hierarchical Plans
Name
IROS_2016_camera.pdf
Description
Accepted version
Size
4.95 MB
Format
Adobe PDF
Checksum (MD5)
4787daa89beacd9dc1514f043de6a9fc
Author(s) • • • •
Holtzen, Steven
Zhao, Yibiao
Gao, Tao
Tenenbaum, Joshua B.
Zhu, Song-Chun
Date Issued
October 2016
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Holtzen, Steven, Zhao, Yibiao, Gao, Tao, Tenenbaum, Joshua B. and Zhu, Song-Chun. 2016. "Inferring Human Intent from Video by Sampling Hierarchical Plans."
Version
Author's final manuscript
Abstract
© 2016 IEEE. This paper presents a method which allows robots to infer a human's hierarchical intent from partially observed RGBD videos by imagining how the human will behave in the future. This capability is critical for creating robots which can interact socially or collaboratively with humans. We represent intent as a novel hierarchical, compositional, and probabilistic And-Or graph structure which describes a relationship between actions and plans. We infer human intent by reverseengineering a human's decision-making and action planning processes under a Bayesian probabilistic programming framework. We present experiments from a 3D environment which demonstrate that the inferred human intent (1) matches well with human judgment, and (2) provides useful contextual cues for object tracking and action recognition.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/iros.2016.7759242