RESPRECT: Speeding-up Multi-Fingered Grasping With Residual Reinforcement Learning
IEEE ROBOTICS AND AUTOMATION LETTERS(2024)
摘要
Deep Reinforcement Learning (DRL) has proven effective in learning control policies using robotic grippers, but much less practical for solving the problem of grasping with dexterous hands - especially on real robotic platforms - due to the high dimensionality of the problem. In this letter, we focus on the multi-fingered grasping task with the anthropomorphic hand of the iCub humanoid. We propose the RESidual learning with PREtrained CriTics (RESPRECT) method that, starting from a policy pre-trained on a large set of objects, can learn a residual policy to grasp a novel object in a fraction (similar to 5 chi faster) of the timesteps required to train a policy from scratch, without requiring any task demonstration. To our knowledge, this is the first Residual Reinforcement Learning (RRL) approach that learns a residual policy on top of another policy pre-trained with DRL. We exploit some components of the pre-trained policy during residual learning that further speed-up the training. We benchmark our results in the iCub simulated environment, and we show that RESPRECT can be effectively used to learn a multi-fingered grasping policy on the real iCub robot.
更多查看译文
关键词
Dexterous manipulation,multifingered hands,reinforcement learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要