Skip to main content

Simulation-to-reality bridge for AI agents with environment adapters

Project description

agent-sim-bridge

Simulation-to-reality bridge for AI agents with environment adapters

CI PyPI version Python versions License

Part of the AumOS open-source agent infrastructure portfolio.


Features

  • TransferBridge applies a CalibrationProfile (per-dimension linear scale + offset + noise model) to translate observations and actions between simulator coordinates and real-world distributions
  • Calibrator fits calibration profiles by regression on paired sim/real observation datasets, with support for iterative recalibration as new data arrives
  • DomainRandomization perturbs simulation parameters (friction, mass, sensor noise, lighting) across configurable ranges to produce policies that transfer without fine-tuning
  • Simulation scenario recorder and replay engine lets you capture real-world trajectories, replay them in simulation, and measure the fidelity gap
  • SafetyMonitor enforces physical and policy constraints during both simulated and real execution, with configurable boundary definitions and emergency stop hooks
  • Sensor fusion module combines readings from multiple simulated or real sensors with configurable noise injection and covariance-weighted fusion
  • Backend adapters for Gazebo and PyBullet expose a uniform SimulationEnvironment interface so agents can be tested against either simulator without code changes

Quick Start

Install from PyPI:

pip install agent-sim-bridge

Verify the installation:

agent-sim-bridge version

Basic usage:

import agent_sim_bridge

# See examples/01_quickstart.py for a working example

Documentation

Enterprise Upgrade

For production deployments requiring SLA-backed support and advanced integrations, contact the maintainers or see the commercial extensions documentation.

Contributing

Contributions are welcome. Please read CONTRIBUTING.md before opening a pull request.

License

Apache 2.0 — see LICENSE for full terms.


Part of AumOS — open-source agent infrastructure.

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

agent_sim_bridge-0.2.0.tar.gz (135.8 kB view details)

Uploaded Source

Built Distribution

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

agent_sim_bridge-0.2.0-py3-none-any.whl (115.2 kB view details)

Uploaded Python 3

File details

Details for the file agent_sim_bridge-0.2.0.tar.gz.

File metadata

  • Download URL: agent_sim_bridge-0.2.0.tar.gz
  • Upload date:
  • Size: 135.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for agent_sim_bridge-0.2.0.tar.gz
Algorithm Hash digest
SHA256 d03810214291038da1a2477840c8978817322f86a81b78cb87dc289c0661ed58
MD5 ea73d4f14dafac33f4c23472e1bd8079
BLAKE2b-256 0ea734d74b9daef1c955ee6bac8ce00a3eacf8f767e7063405d8132b23d84a38

See more details on using hashes here.

File details

Details for the file agent_sim_bridge-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for agent_sim_bridge-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f1428c520e8a76c7b7c46db1574cf3b1762497c816a7624c5c8187ad65939cdc
MD5 bdc3a07112bb15fa398aab58a6eabce1
BLAKE2b-256 1d82e931a3e4401913fbfccf141aaa2bf250455d3927fb6dda57e10e080a780a

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