MBDS: A Multi-Body Dynamics Simulation Dataset for Graph Networks Simulators

TL;DR

This paper introduces MBDS, a comprehensive high-quality multi-body dynamics simulation dataset for graph network simulators, enabling improved training and evaluation of physical modeling methods.

Contribution

The authors created a large, detailed dataset with diverse scenes and trajectories, addressing limitations of existing datasets for physical simulation research.

Findings

Enhanced dataset with 1D, 2D, 3D scenes and more trajectories.

Systematic evaluation of existing GNS methods using the new dataset.

Improved realism in multi-body dynamics simulation.

Abstract

Modeling the structure and events of the physical world constitutes a fundamental objective of neural networks. Among the diverse approaches, Graph Network Simulators (GNS) have emerged as the leading method for modeling physical phenomena, owing to their low computational cost and high accuracy. The datasets employed for training and evaluating physical simulation techniques are typically generated by researchers themselves, often resulting in limited data volume and quality. Consequently, this poses challenges in accurately assessing the performance of these methods. In response to this, we have constructed a high-quality physical simulation dataset encompassing 1D, 2D, and 3D scenes, along with more trajectories and time-steps compared to existing datasets. Furthermore, our work distinguishes itself by developing eight complete scenes, significantly enhancing the dataset's comprehensiveness. A key feature of our dataset is the inclusion of precise multi-body dynamics, facilitating a more realistic simulation of the physical world. Utilizing our high-quality dataset, we conducted a systematic evaluation of various existing GNS methods. Our dataset is accessible for download at https://github.com/Sherlocktein/MBDS, offering a valuable resource for researchers to enhance the training and evaluation of their methodologies.