makeecat/Peng

A minimal quadrotor autonomy framework in Rust (Mac, Linux, Windows)

What it solves

Peng provides a minimal, high-performance framework for quadrotor autonomy, allowing developers to simulate, plan, and control drones in a virtual environment without needing physical hardware immediately.

How it works

Written in Rust for memory safety and efficiency, the framework combines a high-fidelity dynamics simulator (supporting RK4 integration) with a suite of trajectory planners and a PID-based control system. It simulates essential hardware components like IMUs and depth sensors, and uses rerun.io for real-time 3D visualization and telemetry logging.

Who it’s for

It is designed for robotics researchers and developers who need a lightweight, efficient tool for testing quadrotor flight algorithms, trajectory planning, and autonomous navigation.

Highlights

  • Diverse Trajectory Planning: Includes minimum jerk, Lissajous curve, circular, obstacle avoidance, and minimum snap waypoint navigation planners.
  • High-Fidelity Simulation: Features configurable quadrotor dynamics and multi-threaded depth rendering.
  • Real-time Visualization: Integrated with rerun.io for 3D state telemetry and depth map rendering.
  • Robust Control: Implements PID control for position and attitude with integral windup prevention.

Related

  • Project
    learnsyslab/gym-pybullet-drones

    A Gymnasium‑compatible PyBullet simulator for single‑ and multi‑drone control, with examples for PID, downwash, and PPO reinforcement learning, plus optional Betaflight SITL integration.

  • Project
    copper-project/copper-rs

    Copper is a Rust runtime for building static, zero‑allocation robot task graphs that can run on anything from Linux to bare‑metal MCUs. It records execution into a replayable log, offers ROS 2 interop, and provides tooling (project templates, visualisation, replay) for deterministic, real‑time robot software.

  • Project
    microsoft/AirSim

    An open-source simulator for drones and cars built on Unreal Engine, designed as a platform for AI research in deep learning, computer vision, and reinforcement learning.

  • Project
    tracel-ai/burn

    Burn is a Rust‑native deep‑learning framework that unifies training and inference under a single API. It offers PyTorch‑like ergonomics, automatic differentiation, JIT‑compiled kernel fusion, and a flexible backend system (CUDA, ROCm, Metal, Vulkan, WebGPU, CPU, and no‑std). With tools for ONNX import, weight loading, a terminal training dashboard, and support for embedded and browser environments, Burn lets you write a model once and run it anywhere.

  • Project
    ctu-mrs/mrs_uav_system

    A ROS2-based control, estimation, and simulation system for multirotor helicopters designed for reproducible robotics research and real-world deployment.