Compare commits

...

2 Commits

Author SHA1 Message Date
JackM323 42974fd994 Readme Updated 2026-07-31 14:50:59 +02:00
JackM323 01f993d727 new default values for training 2026-07-31 14:17:22 +02:00
4 changed files with 117 additions and 125 deletions
+115 -64
View File
@@ -1,21 +1,65 @@
# JackBot — Hexapod Control, Simulation & RL Framework
# JackBot — Hexapod Control & Simulation
JackBot is a modular 3D hexapod robot control and machine learning framework built in Python. It supports real-time kinematics, multi-input options (GUI, gamepads), hardware streaming (ESP32 / Arduino), and vectorized Reinforcement Learning (PPO) using PyBullet and Gymnasium.
JackBot is a Python project for controlling and simulating a six-legged hexapod robot.
It uses IKPy for inverse kinematics, PyBullet for optional simulation, and can send joint commands to ESP32 or Arduino hardware.
---
## Requirements
## Key Features
- Python 3.12 is safest for `pygame` compatibility
- Required Python packages:
- `numpy`
- `pygame`
- `ikpy`
- `pybullet`
- `pyserial`
- `matplotlib`
* **Unified Robot Abstraction (`Robot.py`):** Virtual backends (`RobotBackend` protocol) allow seamless switching between 3D PyBullet simulation and physical hardware (ESP32 / Arduino) without changing high-level logic.
* **Flexible Input Pipeline:** Pluggable input handlers supporting Pygame gamepad controllers, manual GUI sliders, or randomized direction vectors.
* **Parallel Multi-Robot Training:** Vectorized Gymnasium environment (`JackBotEnv`) capable of simulating and training $N$ parallel hexapods simultaneously in PyBullet for PPO reinforcement learning.
* **Live Telemetry & Visual Tracking:** Built-in PyBullet overlay features including real-time performance HUDs, floating leader crown tracking ($\text{👑}$) for top-reward robots, and visual failure feedback (failed robots turn semi-transparent dark gray).
## Setup
---
## Project Architecture
```text
JackBot/
├── main.py # Primary application entry point for manual & hardware control
├── Robot.py # Core Robot class, kinematics wrapper, and Backend protocols
├── config.py # Global settings (backend selection, URDF path, communication specs)
├── kinematics.py # Forward and Inverse Kinematics (IKPy)
├── simulation.py # Base PyBullet GUI wrapper for single-robot interactive simulation
├── robot_init.py # Default stance angles and neutral leg positions
├── DataTypes.py # Strongly typed arrays (PosArray, RadArray, DegArray) & structs
│
├── states/ # Finite State Machine (FSM) gait states
│ ├── State.py # Base State class
│ ├── idle.py # Neutral stance state
│ └── walking.py # Inverse-kinematics tripod gait state
│
├── inputs/ # Input providers
│ ├── InputProvider.py # Base input abstraction
│ └── PygameController.py # Asynchronous gamepad loop (process-isolated)
│
├── gui/ # Control interface
│ └── MainWindow.py # Pygame / parameter GUI layout and command resolver
│
├── EspCommunication.py # WiFi socket sender for ESP32 hardware
├── ArduinoCommunication.py # Serial communication wrapper for Arduino hardware
├── JackBotUrdf.urdf # Kinematic 3D model definition (18 active joints)
│
└── ml/ # Machine Learning Subsystem
├── env.py # JackBotEnv (Gymnasium multi-robot vector environment)
├── SimManager.py # Physics server initialization and scene loading
├── MetricsOverlay.py # PyBullet HUD (MetricsHUD) & leader crown tracking (LeaderCrown)
├── run_train.py # PPO training execution script
└── run_eval.py # Model evaluation script
```
---
## System Requirements
* **Python 3.12** (Recommended)
* **OS:** Linux (Ubuntu/Debian) or Windows 10/11
* **Dependencies:** `pybullet`, `gymnasium`, `stable-baselines3`, `torch`, `numpy`, `pygame`, `ikpy`, `pyserial`, `matplotlib`
---
## Installation & Setup
### Linux (Bash)
@@ -26,6 +70,12 @@ python -m pip install --upgrade pip setuptools wheel
pip install -r requirements.txt
```
> **Linux X11 Headless Note:** If running PyBullet GUI on Linux gives an X11 server connection error (`cannot connect to X server`), ensure your display environment variable is set:
> ```bash
> export DISPLAY=:0
> python main.py
> ```
### Windows (PowerShell)
```powershell
@@ -35,75 +85,76 @@ python -m pip install --upgrade pip setuptools wheel
pip install -r requirements.txt
```
If PowerShell blocks activation:
If PowerShell blocks script execution:
```powershell
Set-ExecutionPolicy -Scope Process -ExecutionPolicy RemoteSigned
.\.venv\Scripts\Activate.ps1
```
## Run
---
From the repository root:
## Usage Guide
```
### 1. Manual Control & Hardware Streaming (`main.py`)
`main.py` is the operational entry point for driving the robot manually via GUI sliders or a gamepad, running either in 3D PyBullet simulation or connected to physical hardware.
To launch:
```bash
python main.py
```
If Linux breaks with
```
ExampleBrowserThreadFunc started
X11 functions dynamically loaded using dlopen/dlsym OK!
#### Configuration (`config.py`)
Edit `config.py` prior to launching `main.py` to configure execution mode and connections:
cannot connect to X server
```
run:
```
export DISPLAY=:0
python main.py
* **Backend Selection (`cfg.backend`):**
* `BackendType.SIMULATION`: Executes motion inside a 3D PyBullet window.
* `BackendType.ESP32`: Streams target joint angles over WiFi sockets to an ESP32 micro-controller (`cfg.esp32_ip`, `cfg.esp32_port`).
* `BackendType.ARDUINO`: Streams target joint angles over Serial to an Arduino (`cfg.port`, `cfg.baudrate`).
---
### 2. Machine Learning: PPO Training & Evaluation (`ml/`)
The `ml/` directory contains tools to train RL policies using **Proximal Policy Optimization (PPO)**. The agent receives observations ($18\text{ joint angles} + 4\text{ velocity/turning commands}$) and outputs continuous joint delta actions in $[-1, 1]$.
#### A. Training a Model (`run_train.py`)
Train a single robot policy:
```bash
python ml/run_train.py --timesteps 100000 --model ml/checkpoints/ppo_joint_command
```
## Configuration
Train using multi-robot parallel vectorization with visual GUI enabled:
```bash
python ml/run_train.py --timesteps 500000 --model ml/checkpoints/ppo_joint_command --num-robots 16 --robot-spacing 0.75 --gui
```
Edit `config.py` before running:
**Training CLI Arguments:**
* `--timesteps`: Total training timesteps.
* `--num-robots`: Number of parallel robot instances spawned in a grid layout (e.g., 16 to 64).
* `--robot-spacing`: Distance in meters between robot spawn origins.
* `--start-pose`: Stance pose at environment reset (`init_deg` or `init90_deg`).
* `--gui`: Renders the live PyBullet GUI with metrics HUD, leader crown, and failure graying.
- `sim = True` to enable PyBullet simulation
- `sim = False` to use hardware control
- `arduinoConnection = True` to use Arduino
- `arduinoConnection = False` to use ESP32
- `port` and `baudrate` for Arduino
- `esp32_ip` and `esp32_port` for ESP32
- `urdf_path = "JackBotUrdf.urdf"`
#### B. Evaluating a Model (`run_eval.py`)
## Project structure
Run an evaluation loop using a saved model checkpoint:
```bash
python ml/run_eval.py --model ml/checkpoints/ppo_joint_command.zip --episodes 5 --gui
```
- `main.py` — main application entry point
- `Controller.py` — Pygame-based controller and input display
- `kinematics.py` — IKPy forward/inverse kinematics
- `simulation.py` — PyBullet simulation wrapper
- `GlobalVariables.py` — shared runtime state and comms
- `DataTypes.py` — typed arrays and control intent
- `RobotState/idle.py` — idle robot state
- `RobotState/walking.py` — walking robot state
- `EspCommunication.py` — ESP32 communication
- `ArduinoCommunication.py` — Arduino communication
- `JackBotUrdf.urdf` — robot model file
Multi-robot evaluation with custom stance pose:
```bash
python ml/run_eval.py --model ml/checkpoints/ppo_joint_command.zip --episodes 3 --gui --num-robots 4 --robot-spacing 0.8 --start-pose init_deg
```
## Notes
---
- `GlobalVariables.py` initializes either `Simulation()` or the selected hardware comm class.
- `DataTypes.py` declares `PosArray`, `DegArray`, `RadArray`, `RobotCommand`, and `ControlIntent`.
- `Controller.py` updates `gv.vector_dirmov` and `gv.robot_state` from joystick input.
- `kinematics.py` loads leg chains from `JackBotUrdf.urdf` and computes IK.
## Environment Mechanics & Telemetry (`ml/env.py`)
## Troubleshooting
When training with `--gui`, `JackBotEnv` includes dynamic visual feedback mechanisms:
- If `pygame` installation fails on Windows, use Python 3.12 and upgrade `pip setuptools wheel` first.
- If `python` is not found on Windows, install Python and enable "Add Python to PATH".
- If the program crashes on startup, verify `JackBotUrdf.urdf` path and `config.py` settings.
## Suggested improvements
- Add a `requirements.txt` or `pyproject.toml`.
- Add a `LICENSE` file before sharing the project.
- Document hardware wiring and packet formats for ESP32/Arduino.
* **Failure Detection & Graying:** Robots are continuously evaluated for roll/pitch tilt ($> 0.7\text{ rad}$) or base collapse ($< 0.05\text{ m}$ height). When a robot fails, its state mask is flagged and its 3D mesh automatically turns **semi-transparent dark gray**.
* **Leader Crown ($\text{👑}$):** A floating crown indicator tracks and sits directly above the robot currently achieving the highest cumulative reward in the multi-robot grid.
* **Termination Threshold:** The environment episode terminates automatically when the percentage of failed robots exceeds the configured threshold (default: $30\%$).
-59
View File
@@ -1,59 +0,0 @@
JackBot ML training and evaluation
Quick-start
1. Create a Python virtualenv and activate it:
```bash
python -m venv .venv
source .venv/bin/activate
```
2. Install dependencies (GPU users should install `torch` appropriate for their CUDA):
```bash
pip install -r requirements.txt
```
3. Quick training (short, for smoke test):
```bash
python ml/run_train.py --timesteps 50000 --model ml/checkpoints/ppo_joint_command
```
Use multi-robot training with `--num-robots` and `--robot-spacing`:
```bash
python ml/run_train.py --timesteps 50000 --model ml/checkpoints/ppo_joint_command --num-robots 3 --robot-spacing 0.75
```
Choose the start pose at reset with `--start-pose`:
```bash
python ml/run_train.py --timesteps 50000 --model ml/checkpoints/ppo_joint_command --start-pose init_deg
```
If you want to watch the agent train in the PyBullet window, add `--gui`:
```bash
python ml/run_train.py --timesteps 50000 --model ml/checkpoints/ppo_joint_command --gui
```
4. Evaluate the trained model in GUI mode:
```bash
python ml/run_eval.py --model ml/checkpoints/ppo_joint_command.zip --episodes 3 --gui
```
For evaluation with multiple robots and start pose:
```bash
python ml/run_eval.py --model ml/checkpoints/ppo_joint_command.zip --episodes 3 --gui --num-robots 2 --robot-spacing 0.6 --start-pose init_deg
```
Notes
- `ml/env.py` exposes a `JackBotEnv` gym environment that uses your `JackBotUrdf.urdf`.
- The observation is `[joint_angles..., vx, vy, vz, omega]` and the action is per-joint delta in [-1,1].
- Start with small timesteps and in `use_gui=False` to speed up iteration. Increase timesteps and tune the reward for better walking quality.
- Keep the trained models off hardware until they behave well in simulation.
+1 -1
View File
@@ -13,7 +13,7 @@ def parse_args():
parser.add_argument("--device", type=str, default="auto", help="Device to use: 'cpu', 'cuda', or 'auto' to autodetect")
parser.add_argument("--use-gui", action="store_true", help="Enable PyBullet GUI during training")
parser.add_argument("--num-robots", type=int, default=1, help="Number of robots in the training environment")
parser.add_argument("--robot-spacing", type=float, default=0.5, help="Spacing between robots in meters")
parser.add_argument("--robot-spacing", type=float, default=3.0, help="Spacing between robots in meters")
parser.add_argument("--start-pose", type=str, choices=["init_deg", "init90_deg"], default="init_deg", help="Initial robot pose at reset")
return parser.parse_args()