EasyMimic: A Low-Cost Framework for Robot Imitation Learning from Human Videos

2026-02-12

AI Summary

This work proposes an efficient imitation learning framework that enables low-cost household robots to acquire manipulation skills from human demonstration videos using only a standard RGB camera. By extracting 3D hand trajectories and mapping them into the robot gripper’s control space, the approach integrates lightweight hand visual enhancement and a human–robot motion alignment module to facilitate cross-modal action transfer. The method substantially reduces reliance on expensive real-robot data while achieving strong performance across multiple manipulation tasks on the LeRobot platform. These results demonstrate the feasibility of enabling affordable domestic robots to learn complex skills directly from human videos, thereby lowering both the data acquisition costs and technical barriers associated with deploying intelligent robotic systems in home environments.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Robot imitation learning is often hindered by the high cost of collecting large-scale, real-world data. This challenge is especially significant for low-cost robots designed for home use, as they must be both user-friendly and affordable. To address this, we propose the EasyMimic framework, a low-cost and replicable solution that enables robots to quickly learn manipulation policies from human video demonstrations captured with standard RGB cameras. Our method first extracts 3D hand trajectories from the videos. An action alignment module then maps these trajectories to the gripper control space of a low-cost robot. To bridge the human-to-robot domain gap, we introduce a simple and user-friendly hand visual augmentation strategy. We then use a co-training method, fine-tuning a model on both the processed human data and a small amount of robot data, enabling rapid adaptation to new tasks. Experiments on the low-cost LeRobot platform demonstrate that EasyMimic achieves high performance across various manipulation tasks. It significantly reduces the reliance on expensive robot data collection, offering a practical path for bringing intelligent robots into homes. Project website: https://zt375356.github.io/EasyMimic-Project/.

Problem

• robot imitation learning
• low-cost robots
• human video demonstrations
• data collection cost
• domain gap

Innovation

• imitation learning
• low-cost robot
• 3D hand trajectory
• domain adaptation
• co-training