RoboCopilot: Human-in-the-Loop Interactive Imitation Learning

Authors: Philipp Wu, Yide Shentu, Qiayuan Liao, Ding Jin, Menglong Guo, Koushil Sreenath, Xingyu Lin, Pieter Abbeel Submitted: March 2025

Overview

Addresses the limitation of passive demonstration collection (record-then-train) by building an interactive system where a human teacher and an autonomous robot policy share control of a bimanual robot. The human can seamlessly intervene, correct, and hand back control during task execution.

Key Design

  • Bilateral teleoperation interface: compliant, force-reflecting — human feels what the robot feels
  • Dynamic control switching: human ↔ autonomous policy transitions happen in real-time without stopping the task
  • Interactive imitation learning: every human intervention becomes a training signal for the policy

Why This Matters

Traditional LfD:

  1. Collect all demonstrations passively
  2. Train policy offline
  3. Deploy and evaluate

RoboCopilot approach:

  1. Deploy initial policy
  2. Human intervenes when policy fails
  3. Intervention becomes new training data
  4. Policy improves with each correction

This is DAgger (Dataset Aggregation) in hardware — the human teacher provides on-policy corrections, directly addressing the covariate shift problem.

Results

Validated on bimanual manipulation tasks in simulation and on hardware. Interactive teaching achieves faster skill acquisition than passive collection alone.