Robot Playing Kendama with Model-Based and Model-Free Reinforcement Learning
This work addresses a specific challenge in robotics for precise manipulation tasks, but it is incremental as it combines existing methods without introducing a fundamentally new approach.
The paper tackled the problem of robot trajectory learning for precise tasks with discontinuous dynamics and high speed, such as Kendama manipulation, by proposing a framework that optimizes trajectories from human demonstration using DDP and PoWER, resulting in successful task completion.
Several model-based and model-free methods have been proposed for the robot trajectory learning task. Both approaches have their benefits and drawbacks. They can usually complement each other. Many research works are trying to integrate some model-based and model-free methods into one algorithm and perform well in simulators or quasi-static robot tasks. Difficulties still exist when algorithms are used in particular trajectory learning tasks. In this paper, we propose a robot trajectory learning framework for precise tasks with discontinuous dynamics and high speed. The trajectories learned from the human demonstration are optimized by DDP and PoWER successively. The framework is tested on the Kendama manipulation task, which can also be difficult for humans to achieve. The results show that our approach can plan the trajectories to successfully complete the task.