Skip to main content

Physics-informed robotics control using The Well dataset and NWO Robotics API

Project description

The Well ร— NWO Robotics Integration

License: MIT Python 3.8+ The Well

Physics-informed robotics control using pre-trained surrogate models from The Well dataset

๐ŸŽฏ Overview

This integration brings 15TB of physics simulations from The Well (Polymathic AI) to the NWO Robotics API, enabling robots to predict physical phenomena 100-1000x faster than traditional simulators.

Key Capabilities (Phase 1)

  • โšก 12ms predictions vs 45s full simulations
  • ๐ŸŒŠ Fluid dynamics for drones and underwater robots
  • ๐Ÿ”Š Acoustic scattering for sonar navigation
  • ๐Ÿงฒ Magnetohydrodynamics for space robotics
  • ๐Ÿฆ  Active matter for swarm coordination

๐Ÿ“ฆ Installation

pip install the-well-nwo

Or from source:
git clone https://github.com/RedCiprianPater/the-well-nwo-integration.git
cd the-well-nwo-integration
pip install -e .

๐Ÿš€ Quick Start

from the_well_nwo import PhysicsPredictor, NWOClient

# Initialize
predictor = PhysicsPredictor(model="FNO-fluid_dynamics")
client = NWOClient(api_key="your_api_key")

# Predict physics before robot acts
prediction = predictor.predict(
    scenario="fluid_interaction",
    robot_state={"position": [0, 0, 10], "velocity": [5, 0, 0]}
)

# Send to robot with physics context
client.send_command(
    robot_id="drone_01",
    command="navigate_through_turbulence",
    physics_context=prediction.to_context()
)
๐Ÿ“š Documentation

โ€ข Getting Started
โ€ข API Reference
โ€ข Available Models
โ€ข Examples
โ€ข Contributing

๐Ÿ”ฌ Available Physics Models

| Dataset               | Model | Use Case                 | Latency |
| --------------------- | ----- | ------------------------ | ------- |
| active_matter         | FNO   | Swarm coordination       | 12ms    |
| fluid_dynamics        | TFNO  | Drone/water aerodynamics | 15ms    |
| acoustic_scattering   | U-Net | Sonar navigation         | 18ms    |
| magneto_hydrodynamics | FNO   | Space robotics           | 20ms    |
| turbulence            | TFNO  | High-speed navigation    | 22ms    |

๐Ÿ—๏ธ Architecture

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”     โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”     โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚   NWO Robotics  โ”‚โ”€โ”€โ”€โ”€โ–ถโ”‚  Physics Engine  โ”‚โ”€โ”€โ”€โ”€โ–ถโ”‚   The Well      โ”‚
โ”‚     API         โ”‚     โ”‚   (This Repo)    โ”‚     โ”‚  Pre-trained    โ”‚
โ”‚                 โ”‚โ—€โ”€โ”€โ”€โ”€โ”‚                  โ”‚โ—€โ”€โ”€โ”€โ”€โ”‚   Models        โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜     โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜     โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
        โ”‚                       โ”‚                       โ”‚
        โ–ผ                       โ–ผ                       โ–ผ
   Robot Commands         Predictions            15TB Dataset

๐Ÿ›ฃ๏ธ Roadmap

Phase 1: Basic Integration โœ… (Current)

โ€ข [x] Pre-trained model loading
โ€ข [x] Basic prediction API
โ€ข [x] NWO Robotics client integration
โ€ข [x] Fluid dynamics support
โ€ข [x] Documentation and examples

Phase 2: Fine-tuning for Robotics ๐Ÿšง (Open for Contributions)

โ€ข [ ] Robotics-specific fine-tuning
โ€ข [ ] Real robot data integration
โ€ข [ ] Multi-modal sensor fusion
โ€ข [ ] Custom physics scenarios

Phase 3: Real-time & Publishing ๐Ÿšง (Open for Contributions)

โ€ข [ ] Real-time model updates
โ€ข [ ] Robotics dataset creation
โ€ข [ ] Publish back to The Well
โ€ข [ ] Distributed training

๐Ÿค Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

Priority Areas for Contributors

โ€ข NWO Robotics for the robotics API platform
โ€ข NVIDIA Modulus for FNO/TFNO implementations

๐Ÿ“ž Support

โ€ข Issues: GitHub Issues
โ€ข Discussions: GitHub Discussions
โ€ข Email: support@nworobotics.cloud

โ”€โ”€โ”€

Built with โค๏ธ by the NWO Robotics Community

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

the_well_nwo-0.1.0.tar.gz (19.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

the_well_nwo-0.1.0-py3-none-any.whl (19.3 kB view details)

Uploaded Python 3

File details

Details for the file the_well_nwo-0.1.0.tar.gz.

File metadata

  • Download URL: the_well_nwo-0.1.0.tar.gz
  • Upload date:
  • Size: 19.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for the_well_nwo-0.1.0.tar.gz
Algorithm Hash digest
SHA256 4777d3f342e3ccef4a33b557de459b8837132c280d43375d916876aaf2dd932c
MD5 c0a9a529a6065669cb4cf7a076fd1440
BLAKE2b-256 0970482ee7efb9baa5dbca82a607ea99946dc9d173e0adcb73408db77e66b1b6

See more details on using hashes here.

File details

Details for the file the_well_nwo-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: the_well_nwo-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 19.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for the_well_nwo-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fb6815a7f6a1fc12a8878ed4fdc21ba218f8fad01be3f1972145e0b272f20317
MD5 53cf3271ab5b5163aa048e6269b42d27
BLAKE2b-256 540b2b8c2420fad324cefedf9db9b2a46e65546432e62a9ad73e17f9db181ddd

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page