Meszaros, Anna and Franzese, Giovanni and Kober, Jens, Teaching Robots to Grasp Like Humans: An Interactive Approach , 2021. [PDF] [Video] [Website]
Teaching Robots Interactively (TERI)
Abstract:
Programming and re-programming robots is extremely time-consuming and expensive, which presents a major bottleneck for new industrial, agricultural, care, and household robot applications. My goal is to realize a scientific breakthrough in enabling robots to learn how to perform manipulation tasks from few human demonstrations, based on novel interactive machine learning techniques.
Current robot learning approaches focus either on imitation learning (mimicking the teacher’s movement) or on reinforcement learning (self-improvement by trial and error). Learning even moderately complex tasks in this way still requires infeasibly many iterations or task-specific prior knowledge that needs to be programmed in the robot. To render robot learning fast, effective, and efficient, I propose to incorporate intermittent robot-teacher interaction, which so far has been largely ignored in robot learning although it is a prominent feature in human learning. This project will deliver a completely new and better approach: robot learning will no longer rely on initial demonstrations only, but it will effectively use additional user feedback to continuously optimize the task performance. It will enable the user to directly perceive and correct undesirable behavior and to quickly guide the robot toward the target behavior. In my previous research I have made ground-breaking contributions to the existing learning paradigms and I am therefore ideally prepared to tackle the three-fold challenge of this project: developing theoretically sound techniques which are at the same time intuitive for the user and efficient for real-world applications.
The novel framework will be validated with generic real-world robotic force-interaction tasks related to handling and (dis)assembly. The potential of the newly developed teaching framework will be demonstrated with challenging bi-manual tasks and a final study evaluating how well novice human operators can teach novel tasks to a robot.
Project Type: ERC Starting Grant; 2019-2023
Members: dr. Zlatan Ajanović , dr. Carlos E. Celemin Paez , dr. Marta Ferraz , ing. Giovanni Franzese , Dr.-Ing. Jens Kober , dr. Ravi Prakash , dr. Leandro de Souza Rosa
Publications
Franzese, Giovanni and Meszaros, Anna and Peternel, Luka and Kober, Jens, ILoSA: Interactive Learning of Stiffness and Attractors , IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 7778--7785, 2021. [DOI] [PDF] [Video] [Website]
Celemin, Carlos and Kober, Jens, Uncertainties Based Queries for Interactive Policy Learning with Evaluations and Corrections , Companion Publication of the 2021 International Conference on Multimodal Interaction, 192--193, 2021. [DOI] [Website]
Bootsma, Bart and Franzese, Giovanni and Kober, Jens, Interactive Learning of Sensor Policy Fusion , 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN), 665-670, 2021. [DOI] [Website]
Perez-Dattari, Rodrigo and Celemin, Carlos E. and Franzese, Giovanni and Ruiz-del-Solar, Javier and Kober, Jens, Interactive Learning of Temporal Features for Control: Shaping Policies and State Representations From Human Feedback , IEEE Robotics & Automation Magazine, 27 (2), 46--54, 2020. [DOI] [PDF] [Video] [Code]
Jauhri, Snehal and Celemin, Carlos E. and Kober, Jens, Interactive Imitation Learning in State-Space , Proceedings of the 2020 Conference on Robot Learning (CoRL), 155, 682--692, 2020. [PDF] [Video] [Code] [Website]
Franzese, Giovanni and Celemin, Carlos E. and Kober, Jens, Learning Interactively to Resolve Ambiguity in Reference Frame Selection , Proceedings of the 2020 Conference on Robot Learning, 155, 1298--1311, 2020. [PDF] [Video] [Website]