Kevin Zakka's Projects
A curated list of awesome robot descriptions
My blog's code repository.
An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities
dataloading is my passion
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Standalone library of frequently-used wrappers for dm_env environments.
[ICRA 2020] Train generalizable policies for kit assembly with self-supervised dense correspondence learning.
HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation
A PyTorch implementation of Implicit Behavioral Cloning
Learning about various image blurring techniques.
Learning some numerical linear algebra.
Learning about RANSAC.
Learning about volumetric fusion.
Project Page for Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
This code corresponds to simulation environments used as part of the MimicGen project.
Python inverse kinematics based on MuJoCo
A browser-based 3D viewer for MuJoCo
Minimal, clean, single-file implementations of common robotics controllers in MuJoCo.
Multi-Joint dynamics with Contact. A general purpose physics simulator.
A 3x3x3 puzzle cube model for MuJoCo.
A collection of high-quality models for the MuJoCo physics engine, curated by DeepMind.
MuJoCo Models for Google's Scanned Objects Dataset
A tiny reinforcement learning codebase for continuous control, built on top of JAX.
A CLI for processing composite Wavefront OBJ files for use in MuJoCo.
PyTorch Boilerplate For Research
A PyTorch Implementation of "Recurrent Models of Visual Attention"
robomimic: A Modular Framework for Robot Learning from Demonstration
[CoRL '23] Dexterous piano playing with deep reinforcement learning.