Data-Efficient Learning from Human Interventions for Mobile Robots

TL; DR

We train two mobile robots in real world in real time via human-in-the-loop learning! Our method:

Learns from online human intervention and demonstration!

Trains from scratch, without reward!

Safe Navigation

A delivery robot (Unitree Go2) learns to navigate safely in a real-world environment, avoiding collisions with static or dynamic obstacles. Even though the observation is RGB-D image, training can be done in 20 minutes and the robot can generalize to unseen environments.

Human Following

We train a quadruped robot (Unitree Go2) to follow a human subject in a real-world environment. Training is completed within 10 minutes.

Zero-shot Deployment

We have successfully deployed the learned policies to unseen environments.

Safe Navigation:

Human Following:

Full Training Footage

@article{peng2025data,
  title={Data-Efficient Learning from Human Interventions for Mobile Robots},
  author={Peng, Zhenghao and Liu, Zhizheng and Zhou, Bolei},
  journal={arXiv preprint arXiv:2503.04969},
  year={2025}
}