A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

A generative world for general-purpose robotics & embodied AI learning.

PyTorch implementation of paper: GaussNav: Gaussian Splatting for Visual Navigation

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Pre-training Reusable Representations for Robotic Manipulation Using Diverse Human Video Data

[CoRL 2024] Official implementation for "MaIL: Improving Imitation Learning with Selective State Space Models"

Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

RialTo Policy Learning Pipeline

[CoRL 2024] HumanPlus: Humanoid Shadowing and Imitation from Humans

HaMeR: Reconstructing Hands in 3D with Transformers

Learning Robot Geometry as Distance Fields: Applications to Whole-body Manipulation

F3RM: Feature Fields for Robotic Manipulation. Official repo for the paper "Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation" (CoRL 2023).

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

[ECCV 2024] Implementation of latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

Modified 3D Gaussian rasterizer for latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.

xsens_mvn_ros contains the relevant packages for the XSens MVN software development tools. (alongside with the ROS middleware)

[RSS 2024] "DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation" code repository

Source code of LHMap-loc

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

[ICCV 2023] DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

Mamba SSM architecture

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

Ultralytics YOLO11 🚀

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation, RA-L IROS 2022

Dynamic Movement Primitive based Motion Retargeting, along with the sign language robot constituted by ABB's YuMi dual-arm collaborative robot and Inspire Robotics' multi-fingered hands.