ARO: Large Language Model Supervised Robotics Text2Skill Autonomous Learning
This addresses the scalability and cost issues in robotics skill learning, though it is incremental as it builds on existing language model applications.
The paper tackles the problem of high human reliance in robotics learning by introducing the ARO framework, which uses large language models to autonomously design reward functions and evaluate performance, enabling partial task completion without human intervention.
Robotics learning highly relies on human expertise and efforts, such as demonstrations, design of reward functions in reinforcement learning, performance evaluation using human feedback, etc. However, reliance on human assistance can lead to expensive learning costs and make skill learning difficult to scale. In this work, we introduce the Large Language Model Supervised Robotics Text2Skill Autonomous Learning (ARO) framework, which aims to replace human participation in the robot skill learning process with large-scale language models that incorporate reward function design and performance evaluation. We provide evidence that our approach enables fully autonomous robot skill learning, capable of completing partial tasks without human intervention. Furthermore, we also analyze the limitations of this approach in task understanding and optimization stability.