[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.

UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers

Official implementation of "Data Scaling Laws in Imitation Learning for Robotic Manipulation"

Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223

Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934

Official implementation of paper on Nature Machine Intelligence: "Preserving and Combining Knowledge in Robotic Lifelong Reinforcement Learning"

Code for PerAct², a language-conditioned imitation learning agent designed for bimanual robotic manipulation using the RLBench environment. It includes dataset generation, training scripts, and evaluation tools for 6-DoF control of two robot arms across complex tasks.

NeurIPS 2022 Paper "VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation"

Baxter Pick and Place using GR-ConvNet. IROS 2020.

myGym enables fast prototyping of RL in the area of robotic manipulation and navigation.You can train different robots, in several environments on various tasks. There is automatic evaluation and benchmark tool. From version 2.1 there is support for multi-step tasks, multi-reward training and multi-network architectures.

VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulation (CoRL 2024)

Robotic Manipulation - Learned in the Real World

A collection of RL gymnasium environments for learning to grasp 3D deformable objects.

Official Code for SGRv2 and SGR.

Official PyTorch implementation of "Entity-Centric Reinforcement Learning for Object Manipulation from Pixels", Haramati et al., ICLR 2024

mBEST: Realtime detection of DLOs via minimal bending energy skeleton pixel traversals

[ICRA 2024] SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs

Deep Reinforcement Learning for Robotic Pushing and Picking in Cluttered Environment