# rohanaaron/portfolio architecture

> Architecture diagram of the GitHub repository rohanaaron/portfolio, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/rohanaaron/portfolio
- Repository: https://github.com/rohanaaron/portfolio

## Overview

This is a robotics and applied-ML project portfolio, not one integrated product. Its clearest runtime workflow is the Bayesian IRL demo: a robot sorts objects, a human or simulated human corrects a placement, and the learner updates its inferred preference while the simulation displays progress. The repository also documents iterative 3D refinement and factor-graph SLAM as separate project workflows. Edges reflect the shown main-project imports and explicit README descriptions; unsampled project implementations are not inferred as connected.

Main entry points: [`graduate/projects/Bayesian IRL Human Corrections/main_project.py`](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/main_project.py) (Sorting Demo), [`graduate/CUBIST/text_to_text_entropy_ratio_FIXED (1).py`](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/text_to_text_entropy_ratio_FIXED%20(1).py) (Entropy Feedback), [`graduate/CUBIST/final_script_FIXED_v2 (1).py`](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/final_script_FIXED_v2%20(1).py) (3D Generation), [`graduate/CUBIST/Semantic_score_VLM_VQA (2).py`](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/Semantic_score_VLM_VQA%20(2).py) (VLM Scoring)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_iterative3d["3D Refinement"]
  node_prompt["Text Prompt"]
  node_generation["3D Generation"]
  node_vlm["VLM Scoring"]
  node_entropy["Entropy Feedback"]
  node_boost["Prompt Boosting"]
  node_filter["Prompt Filtering"]
end

subgraph group_irl["Human Intent Learning"]
  node_main["Sorting Demo<br/>[main_project.py]"]
  node_objects["Objects and Bins"]
  node_panda["Panda Arm<br/>[robot.py]"]
  node_human["Human Corrections"]
  node_learner["Bayesian IRL"]
  node_display["Learning Display<br/>[display_project.py]"]
end

subgraph group_slam["Factor-Graph SLAM"]
  node_camera["Marker Capture<br/>[controller.py]"]
  node_optimizer["Factor Optimizer<br/>[A4.py]"]
end

subgraph group_archives["Archive Transcription"]
  node_archive["Historical HTR<br/>[README.md]"]
end

node_operator(("Human Operator"))

node_prompt -.->|"guides generation"| node_generation
node_generation -.->|"evaluated by"| node_vlm
node_vlm -.->|"scores feedback"| node_entropy
node_entropy -.->|"refines prompt"| node_boost
node_entropy -.->|"filters tokens"| node_filter
node_operator -.->|"starts demo"| node_main
node_main -->|"uses scene"| node_objects
node_main -->|"controls arm"| node_panda
node_main -->|"requests correction"| node_human
node_main -->|"updates preferences"| node_learner
node_main -->|"updates display"| node_display
node_learner -->|"scores bins"| node_objects
node_camera -.->|"feeds landmarks"| node_optimizer

click node_prompt "https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/example_text%20(2).py"
click node_generation "https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/final_script_FIXED_v2%20(1).py"
click node_vlm "https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/Semantic_score_VLM_VQA%20(2).py"
click node_entropy "https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/text_to_text_entropy_ratio_FIXED%20(1).py"
click node_boost "https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/bigram_boost_FIXED%20(1).py"
click node_filter "https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/prompt_filter%20(2).py"
click node_main "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/main_project.py"
click node_objects "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/sort_objects_project.py"
click node_panda "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/robot.py"
click node_human "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/human_model_project.py"
click node_learner "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/bayesian_irl_project.py"
click node_display "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/display_project.py"
click node_camera "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/ArUco-SLAM-Factor-Graph/controller.py"
click node_optimizer "https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/ArUco-SLAM-Factor-Graph/A4.py"
click node_archive "https://github.com/rohanaaron/portfolio/blob/main/README.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_prompt,node_generation,node_vlm,node_entropy,node_boost,node_filter toneBlue
class node_main,node_objects,node_panda,node_human,node_learner,node_display toneAmber
class node_camera,node_optimizer toneMint
class node_archive toneRose
class node_operator toneIndigo
```

## Components

### 3D Refinement

- [Text Prompt](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/example_text%20(2).py): `graduate/CUBIST/example_text (2).py`
- [3D Generation](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/final_script_FIXED_v2%20(1).py): `graduate/CUBIST/final_script_FIXED_v2 (1).py`
- [VLM Scoring](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/Semantic_score_VLM_VQA%20(2).py): `graduate/CUBIST/Semantic_score_VLM_VQA (2).py`
- [Entropy Feedback](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/text_to_text_entropy_ratio_FIXED%20(1).py): `graduate/CUBIST/text_to_text_entropy_ratio_FIXED (1).py`
- [Prompt Boosting](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/bigram_boost_FIXED%20(1).py): `graduate/CUBIST/bigram_boost_FIXED (1).py`
- [Prompt Filtering](https://github.com/rohanaaron/portfolio/blob/main/graduate/CUBIST/prompt_filter%20(2).py): `graduate/CUBIST/prompt_filter (2).py`

### Human Intent Learning

- [Sorting Demo](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/main_project.py): `graduate/projects/Bayesian IRL Human Corrections/main_project.py`
- [Objects and Bins](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/sort_objects_project.py): `graduate/projects/Bayesian IRL Human Corrections/sort_objects_project.py`
- [Panda Arm](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/robot.py): `graduate/projects/Bayesian IRL Human Corrections/robot.py`
- [Human Corrections](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/human_model_project.py): `graduate/projects/Bayesian IRL Human Corrections/human_model_project.py`
- [Bayesian IRL](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/bayesian_irl_project.py): `graduate/projects/Bayesian IRL Human Corrections/bayesian_irl_project.py`
- [Learning Display](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/Bayesian%20IRL%20Human%20Corrections/display_project.py): `graduate/projects/Bayesian IRL Human Corrections/display_project.py`

### Factor-Graph SLAM

- [Marker Capture](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/ArUco-SLAM-Factor-Graph/controller.py): `graduate/projects/ArUco-SLAM-Factor-Graph/controller.py`
- [Factor Optimizer](https://github.com/rohanaaron/portfolio/blob/main/graduate/projects/ArUco-SLAM-Factor-Graph/A4.py): `graduate/projects/ArUco-SLAM-Factor-Graph/A4.py`

### Archive Transcription

- [Historical HTR](https://github.com/rohanaaron/portfolio/blob/main/README.md): `README.md`

### Other components

- **Human Operator**

## Connections

- Text Prompt → 3D Generation: guides generation (evidence: `README.md`)
- 3D Generation → VLM Scoring: evaluated by (evidence: `README.md`)
- VLM Scoring → Entropy Feedback: scores feedback (evidence: `README.md`)
- Entropy Feedback → Prompt Boosting: refines prompt
- Entropy Feedback → Prompt Filtering: filters tokens
- Human Operator → Sorting Demo: starts demo
- Sorting Demo → Objects and Bins: uses scene (evidence: `graduate/projects/Bayesian IRL Human Corrections/main_project.py`)
- Sorting Demo → Panda Arm: controls arm (evidence: `graduate/projects/Bayesian IRL Human Corrections/main_project.py`)
- Sorting Demo → Human Corrections: requests correction (evidence: `graduate/projects/Bayesian IRL Human Corrections/main_project.py`)
- Sorting Demo → Bayesian IRL: updates preferences (evidence: `graduate/projects/Bayesian IRL Human Corrections/main_project.py`)
- Sorting Demo → Learning Display: updates display (evidence: `graduate/projects/Bayesian IRL Human Corrections/main_project.py`)
- Bayesian IRL → Objects and Bins: scores bins (evidence: `graduate/projects/Bayesian IRL Human Corrections/bayesian_irl_project.py`)
- Marker Capture → Factor Optimizer: feeds landmarks (evidence: `README.md`)
