Utilizing AI planning on the edge

Abstract

The convergence between AI planning techniques and the Internet of Things (IoT) can solve various operational and business challenges. However, IoT systems’ stringent requirements such as latency and scalability have introduced several challenges to execute and scale planners in cloud environments. Edge computers placed close to the IoT domain (e.g., sensors) can be leveraged for implementing planners and overcoming scalability issues. We propose a conceptual framework highlighting executing Expressive Numeric Heuristic Search Planner on distributed devices in edge networks. As a proof of concept, we develop a simulator to show the applicability and feasibility of running planners on the edge. As a case study, we simulate a waste management problem and find the optimal route for disposing of? waste bins in a city. Throughout the experiments, the user can discover insightful information regarding the planner’s applicability on the edge.