Data-Driven and Compliance-Based Fault-Tolerance for a Flexible and Extendable Robotic Implant Coupled to a Growing Tissue

Abstract

Robotic implants for real-time and long-term monitoring and therapies are being researched and could open new frontiers in the medical field. For these devices to see widespread adoption, though, key challenges still need to be overcome, including reliability. Over the years, many computational techniques have been developed to impart fault-tolerance to robots and industrial plants. However, the application of these approaches to robotic implants is still challenging, due to the lack of information about the complex behavior of soft tissue (e.g. growth, viscoelasticity) and robot-tissue interaction. In this paper, a novel fault detection framework for a flexible extendable robotic implant is presented. Based on Canonical Correlation Analysis, the approach exploits the flexibility of the robot to extrapolate information for fault identification purposes. The experiments are conducted with a soft tissue simulator, which can emulate the viscoelastic properties of tissue as well as its growth, providing a realistic testing platform. The experiments prove the reliability of the flexible extendable robotic implant and its robustness to system-level external disturbances. Long-term tests are also presented, where the implant extends 80 mm, to its full length, counteracting simulated hardware faults over a 24-hour period, and provide a promising basis for future in-vivo trials.