Robot policies

Research

A visuomotor policy approach using diffusion to generate robot actions.

Research

A generalist robot policy framework for adapting across manipulation tasks.

Research

A policy-learning implementation for bimanual robot manipulation.

Research

Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation

Research

A language-conditioned framework for visual pick-and-place policies.

Research

HoloMotion provides a foundation-model project for whole-body humanoid control.

Research

Robot manipulation model resources from the Allen Institute for AI.

Research

Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies

Research

Official implementation of the paper: "PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System"

Research

Natural Locomotion, Jumping and Recovery of Quadruped Robot A1 with AMP

Research

Being-H is BeingBeyond's family of human-centric embodied foundation models.

Research

3D-CovDiffusion implements a 3D-aware diffusion policy for coverage path planning.

Research

Official Code for "Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning"

Research

Waypoint-Based Imitation Learning for Robotic Manipulation

Research

BFM_Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

Research

Consistency Policy studies visuomotor-policy distillation using consistency models.

Research

Official code repository of paper "CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation"

Research

Official implementation of CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models

Research

A cross-embodiment policy framework for robot learning.

Research

Deep RL Grasping provides training and evaluation code for depth/RGB-D robotic grasping policies.

Research

Official code of GEM: Generative Supervision Helps Embodied Intelligence

Research

HY-Embodied-0.5-X: An Enhanced Embodied Foundation Model for Real-World Agents

Research

This imitation-learning project compares behavior cloning and Diffusion Policy on Panda pick-and-place.

Research

Official implementation of NeurIPS 2021 paper: "Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation". This repo contains a copy of the code for "Universal Humanoid Controller" and…