PhD @ UC Berkeley.
mink. Python inverse kinematics based on MuJoCo.
1.4kspatial-transformer-network. A Tensorflow implementation of Spatial Transformer Networks.
1kpytorch-goodies. PyTorch Boilerplate For Research
607recurrent-visual-attention. A PyTorch Implementation of "Recurrent Models of Visual Attention"
476mjctrl. Minimal, clean, single-file implementations of common robotics controllers in MuJoCo.
439torchnca. A PyTorch implementation of Neighbourhood Components Analysis.
398obj2mjcf. A CLI for processing composite Wavefront OBJ files for use in MuJoCo.
367mujoco_scanned_objects. MuJoCo Models for Google's Scanned Objects Dataset
283clip_playground. An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities
178torchkit. Research boilerplate for PyTorch.
150tsne-viz. Python Wrapper for t-SNE Visualization
136ibc. A PyTorch implementation of Implicit Behavioral Cloning
113form2fit. [ICRA 2020] Train generalizable policies for kit assembly with self-supervised dense correspondence learning.
84blog-code. My blog's code repository.
76learn-linalg. Learning some numerical linear algebra.
72mjc_viewer. A browser-based 3D viewer for MuJoCo
63robopianist-rl. RL code for training piano-playing policies for RoboPianist.
60x-magical. [CoRL 2021] A robotics benchmark for cross-embodiment imitation.
60torchsdf-fusion. Benchmarking PyTorch variants of TSDF fusion.
50mujoco_cube. A 3x3x3 puzzle cube model for MuJoCo.
36robopianist-demo. C
26learn-ransac. Learning about RANSAC.
21dm_env_wrappers. Standalone library of frequently-used wrappers for dm_env environments.
19nanorl. A tiny reinforcement learning codebase for continuous control, built on top of JAX.
15software. My open-source software contributions.
9awesome-robot-descriptions. A curated list of awesome robot descriptions
7mujoco_utils. Python
6mujoco_menagerie. A collection of high-quality models for the MuJoCo physics engine, curated by DeepMind.
4learn-volumetric-fusion. Learning about volumetric fusion.
3learn-blur. Learning about various image blurring techniques.
3robot_descriptions.py. Import robot descriptions as Python modules
3rscope. RL training visualizer for Mujoco Playground environments + Brax training
2whole_body_tracking. Python
2brax. Massively parallel rigidbody physics simulation on accelerator hardware.
1mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.
1controls. Toy implementations of algorithms for path planning, system modelling, optimal control, estimation, and more.
1mujoco_warp. GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.
1