[CoRL 2026] Official code for Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation.
https://kaipengfang.github.io/sim-and-human/ โ HEALTH ? 59 / Quiet
// momentum
// why it's here
- Active: last commit today
- Built almost entirely by one person
- Health 59/100 with only 36 stars
// how to help
// readme
SimHum co-trains a bimanual manipulation policy on simulated robot trajectories and real-world human demonstrations, then fine-tunes it on a small real-robot dataset. Simulation supplies robot-valid actions, and human data supplies real-world observations. With only 80 real-robot episodes per task, SimHum reaches 62.5% success on held-out OOD scenes across four bimanual tabletop tasks, 53.7% higher than Real only in absolute success rate. Under matched data-collection time, it improves over the best single-source pre-training baseline by 35.0% in absolute success rate.
Installation
git clone https://github.com/kaipengfang/SimHum.git
cd SimHum
conda env create -f env.yml
conda activate dit
Data Preparation
Convert raw HDF5 episodes to replay buffer format: