With the advent of e-commerce and logistics industry, numerous goods are delivered every day. Sorting systems play a pivotal role in orders delivery practices. Advanced sorting systems are required nowadays because e-commerce retailers are usually confronted with different orders, each consisting of various items. Integrated sorting systems typically consist of a mix of conveyors tied together which are controlled by the Warehouse Management System (WMS). Traditional objects sorting lines rely on human operators to locate and pick each product by hand. Such systems are labor-consuming and error-prone, resulting in multiple counts to be done on a regular basis. To reduce labor costs and increase efficiency, large enterprises strive to replace their manual sorting systems with automated ones. The automated sorting systems are based on innovative systems such as automatic picking solutions. The main goal of this proposal is to design and develop an autonomous robotic system for sorting packages from a conveyor belt, using computer vision and deep learning techniques.