EUVIMEDEUVIMED entdecken
Open Access · CC BY 3.0

Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots

Jeffrey L. Krichmar, Tiffany Hwu, Xinyun Zou, Todd Hylton

Cognitive Computation and Systems · 2019-03 · 1 (1) · 12-19

DOI: 10.1049/ccs.2018.0002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cognitive Computation and Systems, online erschienen am 04.02.2019. Verfasst von Jeffrey L. Krichmar und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mental imagery and planning are important aspects of cognitive behaviour. Being able to predict outcomes through mental simulation can increase environmental fitness and reduce uncertainty. Such predictions reduce surprise and fit with thermodynamically driven theories of brain function by attempting to reduce entropy. In the present work, the authors tested these ideas in a predator–prey scenario where agents with a limited energy budget had to maximise food intake, while avoiding a predator. Forward planning agents, with the ability to mentalise, to Actor Critic agents that do not plan beyond the current state were also compared. The authors show that the ability to mentalise has distinct advantages when in noisy, uncertain stimuli. These advantages are even more prevalent when tested in the real world on physical robots. The authors’ results highlight the importance of taking into consideration mental imagery and embodiment when constructing artificial cognitive systems.

Zitieren

APA

Krichmar, J. L., Hwu, T., Zou, X., & Hylton, T. (2019). Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots. Cognitive Computation and Systems, 1(1), 12-19. https://doi.org/10.1049/ccs.2018.0002

Vancouver

Krichmar JL, Hwu T, Zou X, Hylton T. Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots. Cognitive Computation and Systems. 2019;1(1):12-19. doi:10.1049/ccs.2018.0002

BibTeX
@article{Krichmar2019,
  author = {Krichmar, Jeffrey L. and Hwu, Tiffany and Zou, Xinyun and Hylton, Todd},
  title = {Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots},
  journal = {Cognitive Computation and Systems},
  year = {2019},
  volume = {1},
  number = {1},
  pages = {12--19},
  doi = {10.1049/ccs.2018.0002}
}
Kostenlos starten →