Pocket Science Lab - Scripts for Sensor Experiments
Repository Index
132,241 visible repositories in the index
1–22 of 22 · Most stars
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies
- autonomous-driving
- autonomous-vehicles
- closed-loop-simulation
- computer-vision
Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".
- generalist-robot-policies
- pretraining
- robotics
- world-action-model
An open-source framework for real-time anomaly detection using Python, ElasticSearch and Kibana
- anomaly
- kibana
- elasticsearch
- data-stream
Lightweight, pure-Python Text User Interface (TUI) widget toolkit with minimal dependencies. Dedicated to the Pycopy project.
- python
- micropython
- tui
- unbloated
🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.
- huggingface
- vla
- generalist-robot-policies
- visual-language-action-model
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
- deep-learning
- neural-architecture-search
- pytorch
- tinyml
The last Micro Web Server for IoTs (MicroPython) or large servers (CPython), that supports WebSockets, routes, template engine and with really optimized architecture (mem allocations, async I/Os). Ready for ESP32, STM32 on Pyboard, Pycom's chipsets (WiPy, LoPy, ...). Robust, efficient and documented!
- websockets
- micropython
- esp32
- microwebsrv
Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot learning policies. The framework enables developers to rapidly prototype and test robotic tasks with various robot embodiments, objects, and environments.
A simulation benchmarking platform for evaluating generalist robot policies
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
- gym
- gym-environment
- marl
- multi-agent
Ultra-Efficient Humanoid Control with Differentiable Simulation.
Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0
- aloha
- flow-matching
- icra2026
- jax
Modbus master which publishes via MQTT
XAsyncSockets is an efficient Python/MicroPython library of managed asynchronous sockets.
- python
- asynchronous
- sockets
- tcp
Memory efficient MicroPython fonts for the Pico Pi and SSD1306 OLED Display
- micropython
- micropython-rpi-pico
- pico
- ssd1309
A home-based IoT irrigation system for efficient plant care.
- iot
- raspberry-pi
- arduino
- python
An efficient micropython WS2812 (NeoPixel) driver
Data acquisition for Raspberry Pi and Micropython
An asyncio-based, memory-efficient HTTP/HTTPS/SOCKS4/SOCKS5 forward proxy server for MicroPython, compatible with CPython
Homebrew micropython driver for msa301 3-axis accelerometer. Tested on Raspberry Pico.
- accelerometer
- driver
- micropython
- pico