Notes on books I read, talks I watch, articles I study, and papers I love

A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).

ROS wrapper for DM-VIO: Delayed Marginalization Visual-Inertial Odometry

Carbon Language's main repository: documents, design, implementation, and related tools. (NOTE: Carbon Language is experimental; see README)

Universal grid map library for mobile robotic mapping

Qt Node Editor. Dataflow programming framework

The code base that powered India in Pixels' YouTube channel for more than 2 years - now open sourced for you to use on your own projects

A curated list of papers & resources linked to 3D reconstruction from images.

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch

ArduPlane, ArduCopter, ArduRover, ArduSub source

Extract stereo images from MYNT-EYE-S camera with a single script.

A universal flight control tuning framework

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Hardentools simply reduces the attack surface on Microsoft Windows computers by disabling low-hanging fruit risky features.

Python script to stream EEG data from the muse 2016 headset

Material for the BCI Workshop held at District 3 in May 2015 by BCI Montréal.

Perception and AI components for autonomous mobile robotics.

A hover system for Microsoft AirSim using reinforcement learning (Q-learning and SARSA)

Tensorforce: a TensorFlow library for applied reinforcement learning

PlayGround: AI Research into Multi-Agent Learning.

[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl

CUDA Hands-on training material by Jack

Deep Multi-scale CNN for Dynamic Scene Deblurring

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

A TensorFlow implementation of DeepMind's WaveNet paper

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

The Retro Learning Environment (RLE) -- a learning framework for AI

This package provides an end-to-end system to laser-based graph SLAM using laser point clouds.