TAILOR: Teaching with Active and Incremental Learning for Object Registration
This addresses the challenge of efficient object registration for robots in new tasks, though it appears incremental as it builds on existing active and incremental learning techniques.
The paper tackles the problem of time-consuming and labor-intensive training for robots to detect novel objects by introducing TAILOR, a method for object registration with active and incremental learning, which automatically selects viewpoints and learns new objects without forgetting previously learned ones, demonstrated with a KUKA robot in a real-world gearbox assembly task.
When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor-intensive. We present TAILOR -- a method and system for object registration with active and incremental learning. When instructed by a human teacher to register an object, TAILOR is able to automatically select viewpoints to capture informative images by actively exploring viewpoints, and employs a fast incremental learning algorithm to learn new objects without potential forgetting of previously learned objects. We demonstrate the effectiveness of our method with a KUKA robot to learn novel objects used in a real-world gearbox assembly task through natural interactions.