Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation
cs.RO, cs.AI
Submitted: 2026-01-27
Updated: 2026-09-17
Comments: Accepted by 10th Annual Conference on Robot Learning (CoRL2026)
Project page: https://kaipengfang.github.io/sim-and-human
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation
- EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
- Masquerade: Learning from In-the-wild Human Videos using Data-Editing
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Policy Contrastive Decoding for Robotic Foundation Models
- Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
- Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation
- MuJoCo Playground
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- The Ingredients for Robotic Diffusion Transformers
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving