Reinforcement learning with model-based feedforward inputs for robotic table tennis

H Ma, D Büchler, B Schölkopf, M Muehlebach - Autonomous Robots, 2023‏ - Springer
We rethink the traditional reinforcement learning approach, which is based on optimizing
over feedback policies, and propose a new framework that optimizes over feedforward …

[PDF][PDF] A Learning-based Iterative Control Framework for Controlling a Robot Arm with Pneumatic Artificial Muscles.

H Ma, D Büchler, B Schölkopf… - … Science and Systems, 2022‏ - roboticsproceedings.org
In this work, we propose a new learning-based iterative control (IC) framework that enables
a complex softrobotic arm to track trajectories accurately. Compared to traditional iterative …

Identifying causal structure in dynamical systems

D Baumann, F Solowjow, KH Johansson… - arxiv preprint arxiv …, 2020‏ - arxiv.org
Mathematical models are fundamental building blocks in the design of dynamical control
systems. As control systems are becoming increasingly complex and networked …

Safe & Accurate at Speed with Tendons: A Robot Arm for Exploring Dynamic Motion

S Guist, J Schneider, H Ma, L Chen, V Berenz… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Operating robots precisely and at high speeds has been a long-standing goal of robotics
research. Balancing these competing demands is key to enabling the seamless …

A robust open-source tendon-driven robot arm for learning control of dynamic motions

S Guist, J Schneider, H Ma, V Berenz… - … : Workshop on Robot …, 2023‏ - openreview.net
Human athletic movements, such as those seen in table tennis or soccer, require a dynamic
interplay of power, agility, and precision. They also involve quick reactions to unpredictable …

Synchronizing Machine Learning Algorithms, Realtime Robotic Control and Simulated Environment with o80

V Berenz, F Widmaier, S Guist, B Schölkopf… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Robotic applications require the integration of various modalities, encompassing perception,
control of real robots and possibly the control of simulated environments. While the state-of …