# rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning architecture

> Architecture diagram of the GitHub repository rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning, 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/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning
- Repository: https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning

## Overview

The repository describes two product tracks: RAG-assisted automotive test generation and a two-vehicle cooperative-driving learner. The latter is represented in source by a CARLA environment, an idealized V2X channel, and recurrent MAPPO training components. RAG and test-generation stages are documented in the README but have no implementation paths in the supplied tree; their relationships are documented there. V2X wiring into the environment is not shown, so that link is marked unverified.

Main entry points: [`mappo/train.py`](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/train.py) (Training loop), [`carla_env.py`](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/carla_env.py) (Intersection environment), [`mappo/mappo.py`](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/mappo.py) (MAPPO optimizer), [`v2x.py`](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/v2x.py) (V2X channel)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_testgen["Test generation"]
  node_requirements["Automotive requirement"]
  node_retrieval["Rule retrieval"]
  node_casegen["Test-case generation"]
  node_testsim["Test-case simulation"]
end

subgraph group_simulation["Driving simulation"]
  node_env["Intersection environment<br/>[carla_env.py]"]
  node_v2x["V2X channel<br/>[v2x.py]"]
end

subgraph group_learning["MAPPO learning"]
  node_trainer["Training loop<br/>[train.py]"]
  node_buffer["Rollout buffer<br/>[buffer.py]"]
  node_mappo["MAPPO optimizer<br/>[mappo.py]"]
  node_model["Saved policy<br/>[mappo_final.pth]"]
end

subgraph group_networks["Policy networks"]
  node_actor["LSTM actor<br/>[actor.py]"]
  node_critic["LSTM critic<br/>[critic.py]"]
end

node_user(("Requirement author"))
node_carla["CARLA simulator"]

node_user -->|"specifies"| node_requirements
node_requirements -->|"retrieves rules"| node_retrieval
node_retrieval -->|"provides context"| node_casegen
node_casegen -->|"simulates cases"| node_testsim
node_testsim -->|"runs in"| node_carla
node_trainer -->|"steps"| node_env
node_env -->|"connects to"| node_carla
node_trainer -->|"selects actions and updates"| node_mappo
node_trainer -->|"stores rollouts"| node_buffer
node_mappo -->|"calls"| node_actor
node_mappo -->|"calls"| node_critic
node_trainer -->|"saves weights"| node_model
node_env -.->|"may exchange state"| node_v2x

click node_env "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/carla_env.py"
click node_v2x "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/v2x.py"
click node_trainer "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/train.py"
click node_buffer "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/buffer.py"
click node_mappo "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/mappo.py"
click node_actor "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/actor.py"
click node_critic "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/critic.py"
click node_model "https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/mappo_final.pth"

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_requirements,node_retrieval,node_casegen,node_testsim toneBlue
class node_env,node_v2x toneAmber
class node_trainer,node_buffer,node_mappo,node_model toneMint
class node_actor,node_critic toneRose
class node_user,node_carla toneIndigo
```

## Components

### Test generation

- **Automotive requirement**
- **Rule retrieval**
- **Test-case generation**
- **Test-case simulation**

### Driving simulation

- [Intersection environment](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/carla_env.py): `carla_env.py`
- [V2X channel](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/v2x.py): `v2x.py`

### MAPPO learning

- [Training loop](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/train.py): `mappo/train.py`
- [Rollout buffer](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/buffer.py): `mappo/buffer.py`
- [MAPPO optimizer](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/mappo.py): `mappo/mappo.py`
- [Saved policy](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/mappo_final.pth): `mappo/mappo_final.pth`

### Policy networks

- [LSTM actor](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/actor.py): `mappo/actor.py`
- [LSTM critic](https://github.com/rupam496/c-v2x-enabled-cooperative-autonomous-driving-using-multi-agent-reinforcement-learning/blob/main/mappo/critic.py): `mappo/critic.py`

### Other components

- **Requirement author**
- **CARLA simulator**

## Connections

- Requirement author → Automotive requirement: specifies (evidence: `README.md`)
- Automotive requirement → Rule retrieval: retrieves rules (evidence: `README.md`)
- Rule retrieval → Test-case generation: provides context (evidence: `README.md`)
- Test-case generation → Test-case simulation: simulates cases (evidence: `README.md`)
- Test-case simulation → CARLA simulator: runs in (evidence: `README.md`)
- Training loop → Intersection environment: steps (evidence: `mappo/train.py`)
- Intersection environment → CARLA simulator: connects to (evidence: `carla_env.py`)
- Training loop → MAPPO optimizer: selects actions and updates (evidence: `mappo/train.py`)
- Training loop → Rollout buffer: stores rollouts (evidence: `mappo/train.py`)
- MAPPO optimizer → LSTM actor: calls (evidence: `mappo/mappo.py`)
- MAPPO optimizer → LSTM critic: calls (evidence: `mappo/mappo.py`)
- Training loop → Saved policy: saves weights (evidence: `mappo/train.py`)
- Intersection environment → V2X channel: may exchange state
