|
|
 |
| |
|
|
|
A Mathematical and Computational Framework for the Adoption of AI-Driven Cloud Robotics Systems |
|
|
|
PP: 1659-1667 |
|
|
doi:10.18576/amis/200613
|
|
|
|
Author(s) |
|
|
|
Khaled Omar Al-Sheyyab,
Hasan Al-Refai,
Mohammed Salem Ahmed Amayreh,
Rizik Al-Sayyed,
Ghassan Samara,
Sawsan S. Badrakhan,
Mahmoud Odeh,
|
|
|
|
Abstract |
|
|
| Cloud technology gave rise to the advent of AI-Driven Cloud Robotics, which is essentially the amalgamation of AI, Robotics and cloud computing. This makes it possible to configure a robotic system in such a way that multiple robotic agents can share computational resources, data, models through cloud infrastructures. These systems continue to encounter a multitude of bottlenecks, distinctly stemming from communication barriers of which the most prevalent is the increased time caused by latency in transferring information between the robotic agent and the cloud, energy expenditure caused by the robotic agent battery, the possibility of successfully completing missions, usage and cloud cost requirements. This research therefore presents a quantitative decision- making mathematical and computational model for studying and adopting the optimal use of next-generation AI-Driven Cloud Robotics systems. The goal of the research is to develop a formally scalable mathematical model an open-problem for the exceedingly vague AI-Driven Cloud Robotics domains. The Adoption Readiness Index (ARI) is defined as a bounded multivariable optimization problem that considers all of mission success probability, time delay in transferring information, energy expenditure and cost per energy load for cloud usage. The unified task and cloud, latency and energy usage representation are described in the form of a directed acyclic graph-based task modeling process. The graph-based task representation can also be used in formulating the designs for distributed cloud system control for coordinating tasks between the cloud and the edge. Rigorous simulation studies are utilized, which highlight that the new immediate obsolescence cost benefits optimization problem will advance the state of the art for the development of scalable computer-aided task planning new missions and robotic systems in the decision-making developmental phase with a high level of detail. |
|
|
|
|
|
|
|
