Learning to play table tennis from scratch using muscular robots

D Büchler, S Guist, R Calandra… - IEEE Transactions …, 2022‏ - ieeexplore.ieee.org
Dynamic tasks such as table tennis are relatively easy to learn for humans, but pose
significant challenges to robots. Such tasks require accurate control of fast movements and …

Semi-parametric musculoskeletal model for reinforcement learning-based trajectory tracking

H Xu, J Fan, H Ma, Q Wang - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
This article aims to solve the trajectory tracking task of the pneumatic musculoskeletal robot
within a model-based reinforcement learning framework. Considering the limited sensors …

Machine learning for musculoskeletal modeling of upper extremity

R Sharma, A Dasgupta, R Cheng, C Mishra… - IEEE Sensors …, 2022‏ - ieeexplore.ieee.org
We propose a novel machine learning (ML)-driven methodology to estimate biomechanical
variables of interest traditionally obtained from upper-extremity musculoskeletal (MSK) …

Utilising redundancy in musculoskeletal systems for adaptive stiffness and muscle failure compensation: a model-free inverse statics approach

E Almanzor, T Sugiyama, A Abdulali… - Bioinspiration & …, 2024‏ - iopscience.iop.org
Vertebrates possess a biomechanical structure with redundant muscles, enabling
adaptability in uncertain and complex environments. Harnessing this inspiration …

Robust continuous motion strategy against muscle rupture using online learning of redundant intersensory networks for musculoskeletal humanoids

K Kawaharazuka, M Nishiura, Y Toshimitsu… - Robotics and …, 2022‏ - Elsevier
Musculoskeletal humanoids have various biomimetic advantages, of which redundant
muscle arrangement is one of the most important features. This feature enables variable …

Learning to control highly accelerated ballistic movements on muscular robots

D Büchler, R Calandra, J Peters - Robotics and Autonomous Systems, 2023‏ - Elsevier
High-speed and high-acceleration movements are inherently hard to control. Applying
learning to the control of such motions on anthropomorphic robot arms can improve the …

A learnable safety measure

S Heim, A von Rohr, S Trimpe… - Conference on Robot …, 2020‏ - proceedings.mlr.press
Failures are challenging for learning to control physical systems since they risk damage,
time-consuming resets, and often provide little gradient information. Adding safety …

Characterization of continuum robot arms under reinforcement learning and derived improvements

R Morimoto, M Ikeda, R Niiyama… - Frontiers in Robotics and …, 2022‏ - frontiersin.org
In robotics, soft continuum robot arms are a promising prospect owing to their redundancy
and passivity; however, no comprehensive study exists that examines their characteristics …

Model-based reinforcement learning for trajectory tracking of musculoskeletal robots

H Xu, J Fan, Q Wang - 2023 IEEE International Instrumentation …, 2023‏ - ieeexplore.ieee.org
This paper aims to solve the trajectory tracking task of the pneumatic musculoskeletal robot
within a model-based reinforcement learning framework. Considering the limited sensors …

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 …