Next Article in Journal
CNN-FWS: A Model for the Diagnosis of Normal and Abnormal ECG with Feature Adaptive
Previous Article in Journal
Composing Music Inspired by Sculpture: A Cross-Domain Mapping and Genetic Algorithm Approach
Previous Article in Special Issue
The Free Energy Principle for Perception and Action: A Deep Learning Perspective
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Entropy
Volume 24
Issue 4
10.3390/e24040469
entropy-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Goal-Directed Planning and Goal Understanding by Extended Active Inference: Evaluation through Simulated and Physical Robot Experiments

by
Takazumi Matsumoto
,
Wataru Ohata
,
Fabien C. Y. Benureau
and
Jun Tani
*
Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology, Okinawa 904-0495, Japan
*
Author to whom correspondence should be addressed.
Entropy 2022, 24(4), 469; https://doi.org/10.3390/e24040469
Submission received: 31 January 2022 / Revised: 24 March 2022 / Accepted: 24 March 2022 / Published: 28 March 2022
(This article belongs to the Special Issue Emerging Methods in Active Inference)
Browse Figures
Review Reports Versions Notes

Abstract

We show that goal-directed action planning and generation in a teleological framework can be formulated by extending the active inference framework. The proposed model, which is built on a variational recurrent neural network model, is characterized by three essential features. These are that (1) goals can be specified for both static sensory states, e.g., for goal images to be reached and dynamic processes, e.g., for moving around an object, (2) the model cannot only generate goal-directed action plans, but can also understand goals through sensory observation, and (3) the model generates future action plans for given goals based on the best estimate of the current state, inferred from past sensory observations. The proposed model is evaluated by conducting experiments on a simulated mobile agent as well as on a real humanoid robot performing object manipulation.
Keywords: active inference; teleology; goal-directed action planning active inference; teleology; goal-directed action planning

Share and Cite

MDPI and ACS Style

Matsumoto, T.; Ohata, W.; Benureau, F.C.Y.; Tani, J. Goal-Directed Planning and Goal Understanding by Extended Active Inference: Evaluation through Simulated and Physical Robot Experiments. Entropy 2022, 24, 469. https://doi.org/10.3390/e24040469

AMA Style

Matsumoto T, Ohata W, Benureau FCY, Tani J. Goal-Directed Planning and Goal Understanding by Extended Active Inference: Evaluation through Simulated and Physical Robot Experiments. Entropy. 2022; 24(4):469. https://doi.org/10.3390/e24040469

Chicago/Turabian Style

Matsumoto, Takazumi, Wataru Ohata, Fabien C. Y. Benureau, and Jun Tani. 2022. "Goal-Directed Planning and Goal Understanding by Extended Active Inference: Evaluation through Simulated and Physical Robot Experiments" Entropy 24, no. 4: 469. https://doi.org/10.3390/e24040469

APA Style

Matsumoto, T., Ohata, W., Benureau, F. C. Y., & Tani, J. (2022). Goal-Directed Planning and Goal Understanding by Extended Active Inference: Evaluation through Simulated and Physical Robot Experiments. Entropy, 24(4), 469. https://doi.org/10.3390/e24040469

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop