Optimal Stroke Learning with Policy Gradient Approach for Robotic Table Tennis

09/07/2021
by   Yapeng Gao, et al.
0

Learning to play table tennis is a challenging task for robots, due to the variety of the strokes required. Current advances in deep Reinforcement Learning (RL) have shown potential in learning the optimal strokes. However, the large amount of exploration still limits the applicability when utilizing RL in real scenarios. In this paper, we first propose a realistic simulation environment where several models are built for the ball's dynamics and the robot's kinematics. Instead of training an end-to-end RL model, we decompose it into two stages: the ball's hitting state prediction and consequently learning the racket strokes from it. A novel policy gradient approach with TD3 backbone is proposed for the second stage. In the experiments, we show that the proposed approach significantly outperforms the existing RL methods in simulation. To cross the domain from simulation to reality, we develop an efficient retraining method and test in three real scenarios with a success rate of 98

READ FULL TEXT
research
11/06/2020

Sample-efficient Reinforcement Learning in Robotic Table Tennis

Reinforcement learning (RL) has recently shown impressive success in var...
research
11/29/2015

Robotic Search & Rescue via Online Multi-task Reinforcement Learning

Reinforcement learning (RL) is a general and well-known method that a ro...
research
02/14/2020

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

We introduce a sampling perspective to tackle the challenging task of tr...
research
03/08/2020

Deep Adversarial Reinforcement Learning for Object Disentangling

Deep learning in combination with improved training techniques and high ...
research
06/24/2020

DISK: Learning local features with policy gradient

Local feature frameworks are difficult to learn in an end-to-end fashion...
research
10/29/2020

Performance Indicators Contributing To Success At The Group And Play-Off Stages Of The 2019 Rugby World Cup

Performance indicators that contributed to success at the group stage an...
research
03/07/2023

Learning Bipedal Walking for Humanoids with Current Feedback

Recent advances in deep reinforcement learning (RL) based techniques com...

Please sign up or login with your details

Forgot password? Click here to reset