# ashflamer/lidar-robot-ml-3d-suite architecture

> Architecture diagram of the GitHub repository ashflamer/lidar-robot-ml-3d-suite, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ashflamer/lidar-robot-ml-3d-suite
- Repository: https://github.com/ashflamer/lidar-robot-ml-3d-suite

## Overview

This repository combines a browser-based autonomous rover simulation and sensor comparison with a real-LiDAR data collection and model-training workflow. The main user path is starting the warehouse mission, where sensing and learned motion cues inform planning, path smoothing, and robot control; a separate workflow collects, cleans, trains, and exports real-data models for the browser. The README documents several simulation internals whose implementation is in index.html, but that source was not sampled, so those links are documented rather than source-verified.

Main entry points: [`train_real_lidar_ml.py`](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/train_real_lidar_ml.py) (Model Training), [`index.html`](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html) (LiDAR Perception), [`lidar_dataset.csv`](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/lidar_dataset.csv) (Clean LiDAR Dataset), [`export_browser_models.py`](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/export_browser_models.py) (Browser Model Export)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_simulation["Rover Simulation"]
  node_warehouse["Warehouse Mission<br/>[index.html]"]
  node_lidar_perception["LiDAR Perception<br/>[index.html]"]
  node_ml_inference["ML Inference<br/>[index.html]"]
  node_safety_bumper["Safety Bumper<br/>[index.html]"]
  node_space_time_planner["Space-Time Planner<br/>[index.html]"]
  node_path_smoothing["Path Smoothing<br/>[index.html]"]
  node_pure_pursuit["Pure Pursuit<br/>[index.html]"]
end

subgraph group_learning["Data And Models"]
  node_cleaner["Track Cleaning"]
  node_clean_dataset[("Clean LiDAR Dataset<br/>[lidar_dataset.csv]")]
  node_trainer["Model Training"]
  node_model_artifacts[("Trained Artifacts")]
  node_browser_export["Browser Model Export"]
  node_browser_models["Browser Model Pack<br/>[ml_models.js]"]
end

subgraph group_evaluation["Comparison And Evaluation"]
  node_comparison_page["Sensor Comparison<br/>[comparison.html]"]
  node_benchmark["Navigation Benchmark"]
end

subgraph group_collection["LiDAR Collection"]
  node_live_lidar["ROS LiDAR Collector"]
  node_raw_dataset[("Raw LiDAR Dataset")]
end

node_user(("User"))
node_ydlidar["YDLidar ROS Driver"]

node_user -->|"starts mission"| node_warehouse
node_warehouse -->|"senses scene"| node_lidar_perception
node_lidar_perception -->|"supplies tracks"| node_ml_inference
node_ml_inference -->|"informs costs"| node_space_time_planner
node_lidar_perception -->|"monitors corridor"| node_safety_bumper
node_space_time_planner -->|"plans route"| node_path_smoothing
node_path_smoothing -->|"provides path"| node_pure_pursuit
node_pure_pursuit -->|"drives rover"| node_warehouse
node_user -->|"opens comparison"| node_comparison_page
node_user -->|"runs benchmark"| node_benchmark
node_ydlidar -->|"publishes scans"| node_live_lidar
node_live_lidar -->|"logs measurements"| node_clean_dataset
node_raw_dataset -->|"provides records"| node_cleaner
node_cleaner -->|"writes cleaned tracks"| node_clean_dataset
node_raw_dataset -->|"provides training data"| node_trainer
node_clean_dataset -->|"provides sequences"| node_trainer
node_trainer -->|"saves models"| node_model_artifacts
node_trainer -->|"invokes export"| node_browser_export
node_model_artifacts -->|"loads weights"| node_browser_export
node_browser_export -->|"writes model pack"| node_browser_models
node_browser_models -->|"supplies models"| node_ml_inference
node_benchmark -.->|"documents results"| node_comparison_page

click node_warehouse "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html"
click node_lidar_perception "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html"
click node_ml_inference "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html"
click node_safety_bumper "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html"
click node_space_time_planner "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html"
click node_path_smoothing "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html"
click node_pure_pursuit "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html"
click node_comparison_page "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/comparison.html"
click node_benchmark "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/benchmark_navigators.py"
click node_live_lidar "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/collect_live_lidar.py"
click node_raw_dataset "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/lidar_dataset_raw.csv"
click node_cleaner "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/clean_lidar_dataset.py"
click node_clean_dataset "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/lidar_dataset.csv"
click node_trainer "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/train_real_lidar_ml.py"
click node_model_artifacts "https://github.com/ashflamer/lidar-robot-ml-3d-suite/tree/main/ml_artifacts"
click node_browser_export "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/export_browser_models.py"
click node_browser_models "https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/ml_models.js"

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_warehouse,node_lidar_perception,node_ml_inference,node_safety_bumper,node_space_time_planner,node_path_smoothing,node_pure_pursuit,node_user toneBlue
class node_cleaner,node_clean_dataset,node_trainer,node_model_artifacts,node_browser_export,node_browser_models toneAmber
class node_comparison_page,node_benchmark toneMint
class node_live_lidar,node_raw_dataset toneRose
class node_ydlidar toneIndigo
```

## Components

### Rover Simulation

- [Warehouse Mission](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html): `index.html`
- [LiDAR Perception](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html): `index.html`
- [ML Inference](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html): `index.html`
- [Safety Bumper](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html): `index.html`
- [Space-Time Planner](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html): `index.html`
- [Path Smoothing](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html): `index.html`
- [Pure Pursuit](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/index.html): `index.html`

### Data And Models

- [Track Cleaning](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/clean_lidar_dataset.py): `clean_lidar_dataset.py`
- [Clean LiDAR Dataset](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/lidar_dataset.csv): `lidar_dataset.csv`
- [Model Training](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/train_real_lidar_ml.py): `train_real_lidar_ml.py`
- [Trained Artifacts](https://github.com/ashflamer/lidar-robot-ml-3d-suite/tree/main/ml_artifacts): `ml_artifacts`
- [Browser Model Export](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/export_browser_models.py): `export_browser_models.py`
- [Browser Model Pack](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/ml_models.js): `ml_models.js`

### Comparison And Evaluation

- [Sensor Comparison](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/comparison.html): `comparison.html`
- [Navigation Benchmark](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/benchmark_navigators.py): `benchmark_navigators.py`

### LiDAR Collection

- [ROS LiDAR Collector](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/collect_live_lidar.py): `collect_live_lidar.py`
- [Raw LiDAR Dataset](https://github.com/ashflamer/lidar-robot-ml-3d-suite/blob/main/lidar_dataset_raw.csv): `lidar_dataset_raw.csv`

### Other components

- **User**
- **YDLidar ROS Driver**

## Connections

- User → Warehouse Mission: starts mission (evidence: `README.md`)
- Warehouse Mission → LiDAR Perception: senses scene (evidence: `README.md`)
- LiDAR Perception → ML Inference: supplies tracks (evidence: `README.md`)
- ML Inference → Space-Time Planner: informs costs (evidence: `README.md`)
- LiDAR Perception → Safety Bumper: monitors corridor (evidence: `README.md`)
- Space-Time Planner → Path Smoothing: plans route (evidence: `README.md`)
- Path Smoothing → Pure Pursuit: provides path (evidence: `README.md`)
- Pure Pursuit → Warehouse Mission: drives rover (evidence: `README.md`)
- User → Sensor Comparison: opens comparison (evidence: `README.md`)
- User → Navigation Benchmark: runs benchmark (evidence: `README.md`)
- YDLidar ROS Driver → ROS LiDAR Collector: publishes scans (evidence: `collect_live_lidar.py`)
- ROS LiDAR Collector → Clean LiDAR Dataset: logs measurements (evidence: `README.md`)
- Raw LiDAR Dataset → Track Cleaning: provides records (evidence: `README.md`)
- Track Cleaning → Clean LiDAR Dataset: writes cleaned tracks (evidence: `clean_lidar_dataset.py`)
- Raw LiDAR Dataset → Model Training: provides training data (evidence: `README.md`)
- Clean LiDAR Dataset → Model Training: provides sequences (evidence: `README.md`)
- Model Training → Trained Artifacts: saves models (evidence: `README.md`)
- Model Training → Browser Model Export: invokes export (evidence: `train_real_lidar_ml.py`)
- Trained Artifacts → Browser Model Export: loads weights (evidence: `export_browser_models.py`)
- Browser Model Export → Browser Model Pack: writes model pack (evidence: `export_browser_models.py`)
- Browser Model Pack → ML Inference: supplies models (evidence: `README.md`)
- Navigation Benchmark → Sensor Comparison: documents results (evidence: `README.md`)
