VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections

TL;DR

VITAL introduces an interactive imitation learning framework that combines simulation data augmentation, human-in-the-loop corrections, and real-world data to efficiently train robust robotic policies for diverse manipulation tasks.

Contribution

The paper presents a scalable method for generating large imitation datasets from limited demonstrations using simulation and human corrections, improving policy robustness and generalization.

Findings

Effective learning of robust policies from limited demonstrations.

Human-in-the-loop corrections significantly enhance policy performance.

Framework generalizes well to new manipulation tasks.

Abstract

Imitation Learning (IL) has emerged as a powerful approach in robotics, allowing robots to acquire new skills by mimicking human actions. Despite its potential, the data collection process for IL remains a significant challenge due to the logistical difficulties and high costs associated with obtaining high-quality demonstrations. To address these issues, we propose a large-scale data generation from a handful of demonstrations through data augmentation in simulation. Our approach leverages affordable hardware and visual processing techniques to collect demonstrations, which are then augmented to create extensive training datasets for imitation learning. By utilizing both real and simulated environments, along with human-in-the-loop corrections, we enhance the generalizability and robustness of the learned policies. We evaluated our method through several rounds of experiments in both simulated and real-robot settings, focusing on tasks of varying complexity, including bottle collecting, stacking objects, and hammering. Our experimental results validate the effectiveness of our approach in learning robust robot policies from simulated data, significantly improved by human-in-the-loop corrections and real-world data integration. Additionally, we demonstrate the framework's capability to generalize to new tasks, such as setting a drink tray, showcasing its adaptability and potential for handling a wide range of real-world manipulation tasks. A video of the experiments can be found at: https://youtu.be/YeVAMRqRe64?si=R179xDlEGc7nPu8i