Servovision in Bioinspired Soft Robotic Fish

• Grant number: 22/07309-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2022
• End date: October 31, 2023
• Field of knowledge: Engineering - Mechanical Engineering - Mechanical Engineering Design
• Principal Investigator: Maira Martins da Silva
• Grantee: Matheus Araujo Kurokawa
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

There is an increasing demand for subsea inspections to assess environmental risks and extreme events. During these inspections, devices can acquire data that can enrich such analyses. Underwater robots can perform this task, and for that, they need to be maneuverable and energy-efficient. Locomotion in complex and unstructured environments is the main reason for the development of soft robotics. In this context, the present project will contribute to designing a soft, aquatic, and bio-inspired robotic system capable of mimicking undulatory and oscillatory movements. Recently, the project coordinator built a structure made of carbon fiber and actuated by pairs of Piezoelectric Macro-Fiber Composites capable of performing such movements. However, due to its construction, the maneuverability of this structure is limited. A promising strategy for improving the maneuvering ability of this system is the use of multistable mechanisms. These mechanisms, which can be manufactured by 3D printing, may be responsible for controlling the direction in which the propulsion will act. This system should pursue a target to be identified by computer vision. The current IC project aims to study the most appropriate methodology for this sensing. For this, the beneficiary will compare mono and stereo computer vision techniques. The beneficiary will program an image processing algorithm in embedded systems for the chosen sensing and implement the required data acquisition to implement control actions.