cpaxton
Robotics research scientist at Meta AI (formerly NVIDIA). Trying to make robots that can solve interesting problems alongside people.
Pittsburgh, PA, USA
Pinned Repositories
costar_stack
Integrated ROS capabilities for planning, predicate inference, gripper control, and perception for use with the KUKA LBR IIWA and Universal Robots.
dmp
This ROS package is a general, robot-agnostic implementation of dynamic movement primitives (DMPs).
grid_matlab
MATLAB code for learning primitive actions from human demonstrations and using these for planning complex tasks, applied to levels of the Needle Master android game.
grid_planning
Integrated task and motion planning using grounded actions learned from observing expert demonstrations.
hab_stretch
Habitat2 compatible version of the Hello Robot Stretch urdf
needlemaster
Free Android game for experiments in learning task structure from human demonstrations. User performances can be saved and exported for research use.
reflexxes_type2
Version of the Reflexxes libraries set up so that you can build them as a ROS package. This is aimed at supporting ROS development using Reflexxes under Indigo and up.
two_arm_collaboration
Two-robot collaboration experiment setup for the Barrett WAM arm. This package includes teleoperation and creation of SMACH task plans as well as other UI code. Meant for use with the JHU LCSR WAM simulation.
lcsr_assembly
Simple assembly primitives and simulation.
sp_segmenter
Superpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.
cpaxton's Repositories
cpaxton/hab_stretch
Habitat2 compatible version of the Hello Robot Stretch urdf
cpaxton/contact_graspnet
Efficient 6-DoF Grasp Generation in Cluttered Scenes
cpaxton/stretch_ros
ROS-related code for the Stretch RE1 mobile manipulator from Hello Robot Inc.
cpaxton/ACT
Action Chunking Transformer implementation for low cost robot
cpaxton/cpaxton.github.io
Website
cpaxton/dobb-e
Dobb·E: An open-source, general framework for learning household robotic manipulation
cpaxton/vim_config
my vim folder
cpaxton/clip-fields
Teaching robots to respond to open-vocab queries with CLIP and NeRF-like neural fields
cpaxton/cow
Implementation of CoW appearing at CVPR 2023
cpaxton/fairo
A modular embodied agent architecture and platform for building embodied agents
cpaxton/GrasperNet
cpaxton/graspnet-baseline
Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)
cpaxton/habitat-lab
A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.
cpaxton/home-robot
Mobile manipulation research tools for roboticists
cpaxton/LangSplat
Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting"
cpaxton/MiDaS
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
cpaxton/mj_envs
A collection of MuJoCo based environments.
cpaxton/peract_colab
Annotated Tutorial for PerAct
cpaxton/Pointnet2_PyTorch
PyTorch implementation of Pointnet2/Pointnet++
cpaxton/pyorbbecsdk
OrbbecSDK python binding
cpaxton/PyRep
A toolkit for robot learning research.
cpaxton/pytorch_6dof-graspnet
cpaxton/ros_numpy
Tools for converting ROS messages to and from numpy arrays - cross-platform
cpaxton/stable-diffusion
cpaxton/theseus
A library for differentiable nonlinear optimization.
cpaxton/UnseenObjectClustering
Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
cpaxton/uois
cpaxton/urdfpy
Python parser for URDFs
cpaxton/usa
Language-based navigation project
cpaxton/vqgan_clip_tests_v1