Novel Path Planning Algorithms and Smart Navigation Strategies of Multiple Autonomous Robots for the Visual Inspection of Asset Integrity in Confined Space
Robotic and autonomous systems (RAS) have received the increasing interests both in onshore and offshore applications where harsh environment (e.g. confined space to deploy and access) has been a challenging issue particularly in the oil and gas industry for numerous reasons. Among them, health, safety and environmental concerns are the key drivers for the deployment of RAS technology. The inspection of key assets in harsh environment (e.g., in the oil and gas industry) is critical both for safety and business reasons. With the current need to deploy an engineer into these environments, safety is of utmost importance and as a result, much preparatory work and additional safety assessments must be performed prior to human entry. In addition, RASs have enabled machines with greater levels of flexibility and adaptability, allowing them to perform various tasks more efficiently than the human counterpart. Multiple Autonomous Robots (MARs) (e.g., Unmanned aerial vehicles, UAVs, climbing mobile robots, etc) within the realm of RASs in particular have emerged as highly agile systems that can be deployed in swarms to perform lightweight tasks quickly and efficiently. With the rising safety, time and cost concerns relating to the inspection of important industrial equipment and infrastructures, the use of small, lightweight MAR that can be deployed quickly to assess the internal and external conditions are highly desirable.
This project is to fundamentally investigate the novel path planning algorithms and smart navigation strategies for developing a feasible solution to the autonomous visual inspection and assessment of internal and external surface conditions in confined spaces through the use of a MAR equipped with on-board cameras. The proposed path planning algorithms and smart navigation strategies consist of an intelligent MAR controller and coverage path planner that determines an optimal path to fully inspect the assets such as vessel surfaces in which confined space has raised the significant challenges in both academic and industrial domains . It is also proposed that the MAR will have obstacle avoidance capabilities to avoid collision with external obstructions and internal features such as weirs and vane packs etc. Toward this end, smart navigation strategies will be playing a key role.
Small MARs are cost-effective for deployment in completing a task for a large area. Their agile locomotion system enables a high degree of mobility such that obstacle avoidance and complex path following can be realised. This project aims to develop a fast and cost-effective solution to the path planning and navigation problem of MAR for the visual inspection of asset integrity in confined spaces by carrying out a PhD-level fundamental research programme in the targeted domain with the focus of addressing the gaps in applying robotics and autonomous systems (RAS) to the Oil and Gas industry for widening RAS’s social and economic impact.
To achieve this aim, the proposed project will be focusing on the following three research objectives: 1) To investigate how to automatically detect and intelligently recognize the hazardous situations within the inspection areas of the asset in confined spaces. 2) To investigate how the MAR can be controlled and navigated in a smarter manner in the confined space to fulfil a series of challenging tasks such as obstacle avoidance, positioning, path tracking, and coordinated control of each autonomous vehicles (robots) in the MAR . 3) To develop an intelligent coverage path planning (CPP) algorithm for MAR’s visual inspection of both internal and external asset (e.g., a vessel) surfaces. The proposed CPP is intended to enable the MAR to visually inspect the entire area of the asset surface and takes into account the MAR motions as well as the field of view of the on-board inspection instruments (in this case a camera).
International Students applying must be able to provide evidence and pay the difference between the UK Home Fee and International Fee.
A minimum of 2 references are required