Towards table tennis with a quadrotor autonomous learning robot and onboard vision

Silva, Rui; Melo, Francisco S.; Veloso, Manuela

doi:10.1109/iros.2015.7353441

Cited by 17 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is because making decisions directly in the control space is difficult to migrate to the real world. [17] brings the learning method into reality and builds a library of "hitting motions" to determine the best hitting motion. But the success rate of interception is too low, which is because the decision does not consider the feasibility of quadrotor motion planning.…”

Section: Related Workmentioning

confidence: 99%

Catch Planner: Catching High-Speed Targets in the Flight

Yu¹,

Wang²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Catching high-speed targets in the flight is a complex and typical highly dynamic task. In this paper, we propose Catch Planner, a planning-with-decision scheme for catching. For sequential decision making, we propose a policy search method based on deep reinforcement learning. In order to make catching adaptive and flexible, we propose a trajectory optimization method to jointly optimize the highly coupled catching time and terminal state while considering the dynamic feasibility and safety. We also propose a flexible constraint transcription method to catch targets at any reasonable attitude and terminal position bias. The proposed Catch Planner provides a new paradigm for the combination of learning and planning and is integrated on the quadrotor designed by ourselves, which runs at 100hz on the onboard computer. Extensive experiments are carried out in real and simulated scenes to verify the robustness of the proposed method and its expansibility when facing a variety of high-speed flying targets.

show abstract

Section: Related Workmentioning

confidence: 99%

Catch Planner: Catching High-Speed Targets in the Flight

Yu¹,

Wang²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In [15], a simple simulation was built on top of MATLAB. To make use of robotic drivers and devices, [16] implemented a quadrotor model in the Gazebo simulator, which can be easily combined with ROS. [17] developed a hybrid simulation and real training for muscular robots.…”

Section: A Simulation For Robotic Table Tennismentioning

confidence: 99%

Optimal Stroke Learning with Policy Gradient Approach for Robotic Table Tennis

Gao,

Tebbe,

Zell

2021

Preprint

View full text Add to dashboard Cite

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%.

show abstract

“…The problem of catching objects has been studied in the robotics community. Quadrocopters have been used for juggling a ball [33], throwing and catching a ball [40], playing table tennis [44], and catching a flying ball [47]. [20] consider the problem of catching in-flight objects with uneven shapes.…”

Section: Related Workmentioning

confidence: 99%

Visual Reaction: Learning to Play Catch with Your Drone

Zeng

Mottaghi

Weihs

et al. 2019

Preprint

View full text Add to dashboard Cite

In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agents itself. Visual reaction entails predicting the future changes in a visual environment and planning accordingly. We study the problem of visual reaction in the context of playing catch with a drone in visually rich synthetic environments. This is a challenging problem since the agent is required to learn (1) how objects with different physical properties and shapes move, ( 2) what sequence of actions should be taken according to the prediction, (3) how to adjust the actions based on the visual feedback from the dynamic environment (e.g., when objects bouncing off a wall), and (4) how to reason and act with an unexpected state change in a timely manner. We propose a new dataset for this task, which includes 30K throws of 20 types of objects in different directions with different forces. Our results show that our model that integrates a forecaster with a planner outperforms a set of strong baselines that are based on tracking as well as pure model-based and model-free RL baselines.

show abstract

Towards table tennis with a quadrotor autonomous learning robot and onboard vision

Cited by 17 publications

References 16 publications

Catch Planner: Catching High-Speed Targets in the Flight

Catch Planner: Catching High-Speed Targets in the Flight

Optimal Stroke Learning with Policy Gradient Approach for Robotic Table Tennis

Visual Reaction: Learning to Play Catch with Your Drone

Contact Info

Product

Resources

About