Download PDFOpen PDF in browser

A Short-Term Memory for Deliberative Agents in Everyday Environments

13 pagesPublished: September 29, 2016

Abstract

Humans have the impressive capability to efficiently find near-optimal solutions to complex, multi-step problems. AI planning can model such problems well, but is inefficient for realistic problems. We propose to use AI planning in combination with a short-term memory, inspired by models of human short-term memory, to structure real-world problem domains and make the planning process more efficient, while still producing satisficing solutions. We evaluate the method in the domain of a household robot.

Keyphrases: AI Planning, domestic robots, short-term memory model

In: Christoph Benzmüller, Geoff Sutcliffe and Raul Rojas (editors). GCAI 2016. 2nd Global Conference on Artificial Intelligence, vol 41, pages 187--199

Links:
BibTeX entry
@inproceedings{GCAI2016:Short_Term_Memory_for_Deliberative,
  author    = {Ivo Chichkov and Alexandra Kirsch},
  title     = {A Short-Term Memory for Deliberative Agents in Everyday Environments},
  booktitle = {GCAI 2016. 2nd Global Conference on Artificial Intelligence},
  editor    = {Christoph Benzm\textbackslash{}"uller and Geoff Sutcliffe and Raul Rojas},
  series    = {EPiC Series in Computing},
  volume    = {41},
  pages     = {187--199},
  year      = {2016},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/xJQ},
  doi       = {10.29007/r5x5}}
Download PDFOpen PDF in browser