@mastersthesis{Tiwari24-M-Forces,
  title = {Estimating Contact Forces Across Soft Capacitive Tactile Sensors Using Machine Learning},
  abstract = {Robots have become an essential part of the modern world, playing a crucial role in applications from manufacturing to healthcare. Despite significant advancements, the operational range of robots remains relatively narrow, often limited to controlled environments and simple, predetermined tasks. Tactile sensors show promise in broadening this range by enhancing a robot's performance in fine manipulation tasks. These sensors enable robots to perceive contact, providing a more nuanced understanding of their environment in real time. The challenge, however, lies in deriving meaningful and interpretable insights from these sensors, such as contact location and force, which are crucial for dexterous manipulation tasks.
  To address this challenge, this thesis develops machine learning-based software that achieves precise real-time contact location and force sensing across the entire surface of a grid-based soft capacitive tactile sensor, enabling rapid and straightforward deployment and facilitating transferability to other sensor instances, all while retaining the advantageous attributes of capacitance technology.
  Machine learning models were trained using data captured by indenting the sensor surface and measuring the sensor responses and the applied normal forces. Convolutional neural networks (CNNs) were selected for their low prediction errors in contact force estimation with the collected dataset. Two distinct models were developed: one for estimating contact forces at a single point and another for estimating normal force distributions. The transferability of the trained models across different sensor instances was evaluated and improved. The single point contact force estimation model's practical utility was demonstrated through real-time closed-loop control of a Franka Emika Panda robot arm through two specific tasks: tactile servoing in 1D and active object centering in 2D.
  This research contributes to enhancing the accessibility of soft tactile sensors in robotic applications through machine learning and demonstrates that this approach can improve the capabilities of tactile sensors.},
  pages = {1--99},
  degree_type = {Master},
  school = {Saarland University},
  address = {Saarbrücken, Germany},
  month = jul,
  year = {2024},
  note = {M.Sc. in Embedded Systems},
  slug = {tiwari24-m-forces},
  author = {Tiwari, Arekh},
  month_numeric = {7}
}