Enabling Autonomous and Connected Vehicles at the 5G Network Edge

Connected and automated vehicles currently rely on on-board resources to implement autonomous functions, leaving the mobile network for non-mission-critical applications. At the same time, the ultra-low latency, the increased bandwidth, and the softwarization and virtualization technologies of 5G systems are opening the door to multiple applications in the context of connected and automated vehicles. The deployment of applications at the edge of the mobile network under the Multi-access Edge Computing (MEC) paradigm becomes an excellent option for meeting the latency requirements imposed by connected mobility. In this context, this demonstration showcases how remote and autonomous driving applications, such as lane tracking and object detection, can be offloaded to a MEC-enabled 5G network without impairing their effectiveness, and the change in the latency perceived by end-users with respect to a cloud deployment.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Roberto Riggio,et al.  Enabling Computation Offloading for Autonomous and Assisted Driving in 5G Networks , 2019, 2019 IEEE Global Communications Conference (GLOBECOM).

[3]  Eddie Kohler,et al.  The Click modular router , 1999, SOSP.

[4]  Roberto Riggio,et al.  5G-EmPOWER: A Software-Defined Networking Platform for 5G Radio Access Networks , 2019, IEEE Transactions on Network and Service Management.

[5]  Roberto Riggio,et al.  lightMEC: A Vendor-Agnostic Platform for Multi-access Edge Computing , 2018, 2018 14th International Conference on Network and Service Management (CNSM).

[6]  Cüneyt Güzelis,et al.  Object recognition and detection with deep learning for autonomous driving applications , 2017, Simul..