Unmanned Aerial Vehicles (UAVs)
play an important role in the
Internet of Things (IoT)
, and form the paradigm of the Internet of UAVs, due to their characteristics of flexibility, mobility and low costs. However, resource constraints such as dynamic wireless channels, limited battery capacities and computation resources of UAVs make traditional methods inefficient in the Internet of UAVs. The thriving of
Mobile Edge Computing (MEC)
and
Machine Learning (ML)
is of great significance, and is promising for real-time resource allocation, trajectory design and intelligent decision making. This survey provides a comprehensive review of key technologies, applications, solutions and challenges based on the integration of MEC and ML in the Internet of UAVs. First, key technologies of MEC and ML are presented. Then, their integration and major issues in the Internet of UAVs are presented. Furthermore, the applications of MEC and ML in the Internet of UAVs under urban, industrial and emergency scenarios are discussed. After that, this survey summarizes the current solutions for MEC and ML in the Internet of UAVs based on the considered issues. Finally, some open problems and challenges are discussed.