Interactively shaping robot behaviour with unlabeled human instructions
This work addresses the challenge of making robot training more intuitive and less labor-intensive for human teachers, though it appears incremental as it builds on existing paradigms.
The paper tackles the problem of enabling robots to learn tasks more efficiently by interactively incorporating unlabeled human instructions alongside predefined rewards and feedback, resulting in accelerated learning and reduced teaching signals.
In this paper, we propose a framework that enables a human teacher to shape a robot behaviour by interactively providing it with unlabeled instructions. We ground the meaning of instruction signals in the task-learning process, and use them simultaneously for guiding the latter. We implement our framework as a modular architecture, named TICS (Task-Instruction-Contingency-Shaping) that combines different information sources: a predefined reward function, human evaluative feedback and unlabeled instructions. This approach provides a novel perspective for robotic task learning that lies between Reinforcement Learning and Supervised Learning paradigms. We evaluate our framework both in simulation and with a real robot. The experimental results demonstrate the effectiveness of our framework in accelerating the task-learning process and in reducing the number of required teaching signals.