Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse Data using a Learning-based Unscented Kalman Filter

A Schperberg, Y Tanaka, F Xu… - … on Ubiquitous Robots …, 2023 - ieeexplore.ieee.org
Achieving highly accurate dynamic or simulator models that are close to the real robot can
facilitate model-based controls (eg, model predictive control or linear-quadradic regulators) …

Cycloidal Quasi-Direct Drive Actuator Designs with Learning-based Torque Estimation for Legged Robotics

A Zhu, Y Tanaka, F Rafeedi, D Hong - arXiv preprint arXiv:2410.16591, 2024 - arxiv.org
This paper presents a novel approach through the design and implementation of Cycloidal
Quasi-Direct Drive actuators for legged robotics. The cycloidal gear mechanism, with its …

[PDF][PDF] Scaler-b: A multimodal versatile robot for simultaneous locomotion and grasping

Y Tanaka, A Schperberg, A Zhu, D Hong - IEEE International Conference … - researchgate.net
In our video, we present SCALER-B, a multi-modal versatile climbing robot that is a
quadruped robot capable of standing up, bipedal locomotion, bipedal climbing, and pullups …

Towards Intelligent Robotic Systems: Unifying Model-based Optimization and Machine Learning for Planning, Control, and Estimation

AV Schperberg - 2024 - search.proquest.com
The goal of this work is to formulate algorithms that can address three key ingredients I
believe are necessary towards making robots autonomous and smart:(1) The robot needs to …

[图书][B] Optimization-based Planning and Control for Robust and Dexterous Locomotion and Manipulation through Contact

Y Shirai - 2024 - search.proquest.com
Although robotic locomotion and manipulation have shown some remarkable progress in
the real world, the current locomotion and manipulation algorithms are inefficient in …