> For the complete documentation index, see [llms.txt](https://howllian27s-organization.gitbook.io/graphyti/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://howllian27s-organization.gitbook.io/graphyti/methodology-personalised-physics.md).
# Methodology: Personalised Physics
### **Text-driven physics customisation**
Our physics engine enables physics properties customisation via text (Fig. 10). We train on a corpus of five million words, decided based on the rule of 10, for semantic understanding and dynamic parameter adjustment \[16]. We will pursue zero-shot 3D content creation solely with CLIP guidance.
!\[A diagram of a diagram
Description automatically generated]\(/files/L7gLlWTelzGRoLREseIF)\
\&#xNAN;*Figure. 10: Text-Driven Physics Customisation Framework*
Firstly, for dynamic parameter adjustment, the LLM employs semantic mapping that uses trained embeddings to map the tokenised text components to predefined physics parameters in the engine. Secondly, this is translated to actionable commands. Lastly, such commands will make dynamic parameter adjustment.
*Figure 11: Example of Actionable Command Translated from Parsed Instructions*
### **Developing a custom physics engine**
!\[A diagram of a custom physics engine
Description automatically generated]\(/files/rnIvL6T2pFsKAJfQ0tlE)
*Figure 12: Physics Engine Features*
At its core, the engine (Fig. 11) simulates both solid and deformable structures, using a NeRF-inspired finite elements dissection for detailed physical property analysis. It employs Finite Element Analysis (FEA) to anticipate structural responses to external forces, enabling rapid computation of stress and deformation under applied loads. Through text prompts, users can specify the load\[1], so the engine will simulate and visualise the resulting stress distribution.
Optimised with octrees \[13] and bounding volume hierarchies \[11], the engine will integrate the Gilbert-Johnson-Keerthi (GJK) algorithm to pinpoint collisions \[14] and use an impulse-based resolution system that determines appropriate collision responses. The engine also manages structural joints and constraints, ensuring authentic movement patterns of interconnected structures. Users can customise both collision properties\[2] and joint management\[3] via textual prompts.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://howllian27s-organization.gitbook.io/graphyti/methodology-personalised-physics.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.