Predictive Inference Models for Real-World Physical Environments
Open Access
- 20 May 2025
- journal article
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 29 (3) , 456-468
Abstract
In recent years, artificial intelligence has become increasingly important for understanding the real world and the innate human ability to process intuitive physics with computers. Most research on real-world detection and prediction has used methods that generate predictive images of the environment from changes in the pixels of an image, or that predict changes in objects in the environment from changes in the numerical values of a physical simulator. However, the actual method of predicting the environment in humans is believed to consist of both visual and physical information. Therefore, in this study, in order to recognize the motion of objects, the relationship of motion characteristics between objects is represented by a graph structure, which enables the extraction of anomalous points in response to changes in the environment. Then, based on both visual and physical information, we constructed a change point prediction model that can predict the motion of objects in the environment and capture the timing of collisions between objects. Moreover, to improve the accuracy, the basic prediction model was modified and the accuracy of the model was compared. The results showed that visual information and physical information were inferred independently, and the more physical information included the physical properties of the objects, the higher the accuracy. In the change point prediction model, as the prediction accuracy of the base prediction model increased, the change point extraction accuracy also increased.Keywords
Funding Information
- Japan Society for the Promotion of Science (JP22KJ1355)
- Tateisi Science and Technology Foundation
This publication has 17 references indexed in Scilit:
- Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models2023
- PreCNet: Next-Frame Video Prediction Based on Predictive CodingIEEE Transactions on Neural Networks and Learning Systems, 2023
- Intuitive physics learning in a deep-learning model inspired by developmental psychologyNature Human Behaviour, 2022
- SimVP: Simpler yet Better Video Prediction2022
- Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning2021
- YOLACT: Real-Time Instance Segmentation2019
- Interpretable Intuitive Physics Model2018
- CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning2017
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014