Force Estimation
Force estimation aims to accurately determine the forces acting on a robot or other system, crucial for safe and effective interaction with the environment. Current research heavily emphasizes data-driven approaches, employing neural networks (including convolutional autoencoders and recurrent decoders) and Gaussian processes to model complex system dynamics and compensate for sensor limitations, often integrating visual information for improved accuracy. These advancements are significantly impacting robotics, particularly in areas like minimally invasive surgery, human-robot interaction, and soft robotics, enabling more precise control and safer operation in challenging environments.
Papers
An Effectiveness Study Across Baseline and Neural Network-based Force Estimation Methods on the da Vinci Research Kit Si System
Hao Yang, Ayberk Acar, Keshuai Xu, Anton Deguet, Peter Kazanzides, Jie Ying Wu
Predicting Ship Responses in Different Seaways using a Generalizable Force Correcting Machine Learning Method
Kyle E. Marlantes, Piotr J. Bandyk, Kevin J. Maki