Software stack for embedding soft optical tactile sensors in aerial physical interaction paradigm

MSc assignment

Soft optical tactile (SOT) sensors have recently received increasing attention in the control community for contact-based tasks. Indeed, tactile feedback can be used to estimate the pose of the end-effector or to detect slippage [1]. Moreover, open-source SOT sensors are cheap, light, and can be built in-house, e.g. Tac-Tip https://softroboticstoolkit.com/tactip/fabrication. These characteristics make them suitable for application to aerial robotics physical interaction tasks, e.g. contact-based inspection [2]. However, state-of-the-art simulators and control pipelines do not support onboard SOT sensors yet.

This thesis investigates the integration of tactile sensors onboard UAVs. Exploiting the SOT measurements will allow maintaining stable contact during the interaction task using the minimum amount of force required to prevent slippage, thus improving the endurance, reliability, and adaptability of flying end-effectors [3]. To this aim, this thesis tackles the intermediate challenges of embedding reliable simulation of the Tac-Tip sensor in the aerial robotic simulation environment and adapting the control architecture for physical interaction relying on tactile feedback.

Expected outcomes:
  • A contact-based control scheme for UAV based on tactile sensor data
  • Simulation-based results showing stable contact
  • If feasible within the project timeframe, deployment and testing of the developed framework in real-world experiments

The student working on the project should have good programming skills in Python.

[1] J. W. James and N. F. Lepora, "Slip Detection for Grasp Stabilization With a Multifingered Tactile Robot Hand," in IEEE Transactions on Robotics, vol. 37, no. 2, pp. 506-519, April 2021, doi: 10.1109/TRO.2020.3031245
[2] M. Tognon et al., "A Truly-Redundant Aerial Manipulator System With Application to Push-and-Slide Inspection in Industrial Plants," in IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 1846-1851, April 2019, doi: 10.1109/LRA.2019.2895880.
[3] Ryll M, Muscio G, Pierri F, et al. 6D interaction control with aerial robots: The flying end-effector paradigm. The International Journal of Robotics Research. 2019;38(9):1045-1062. doi:10.1177/0278364919856694