Augmented Reality Demonstrations for Scalable Robot Imitation Learning
This addresses the scalability problem in robot imitation learning for non-experts, though it is incremental as it builds on existing AR and IL methods.
The paper tackles the challenge of requiring trained operators for robot imitation learning by introducing an Augmented Reality-assisted framework that enables non-roboticist users to provide demonstrations using devices like HoloLens 2, resulting in successful task execution by a real robot on reach, push, and pick-and-place tasks.
Robot Imitation Learning (IL) is a widely used method for training robots to perform manipulation tasks that involve mimicking human demonstrations to acquire skills. However, its practicality has been limited due to its requirement that users be trained in operating real robot arms to provide demonstrations. This paper presents an innovative solution: an Augmented Reality (AR)-assisted framework for demonstration collection, empowering non-roboticist users to produce demonstrations for robot IL using devices like the HoloLens 2. Our framework facilitates scalable and diverse demonstration collection for real-world tasks. We validate our approach with experiments on three classical robotics tasks: reach, push, and pick-and-place. The real robot performs each task successfully while replaying demonstrations collected via AR.