One of the challenges in autonomous driving is limited sensing from a single vehicle that causes spurious warnings and dead-lock situations. We posit that cloud-based vehicle control system[1] is promising when a number of vehicles must be controlled, since we can collect information from sensors across multiple vehicles for coordination. However, since cloud based control has inherent challenge in long-haul communication susceptible to prolonged latency and packet loss caused by congestion, mobile edge computing (MEC)[2] recently attracts attention in ITS in the next generation mobile network such as 5G. Although edge servers can perform data processing from the vehicles in ultra low latency in MEC, computational resources at edge servers are limited compared to cloud. Therefore, dynamic resource allocation and coordination between edge and cloud servers are necessary. In this paper, we propose infrastructure-based vehicle control system that shares internal states between edge and cloud servers, dynamically allocates computational resources and switches necessary computation on collected sensors according to network conditions in order to achieve safe driving. We implement a prototype system using micro-cars and evaluate the stability of infrastructure-based vehicle control. We show that proposed system mitigates instability of cloud control caused by latency fluctuation. As a result, when controlled from the cloud with 150ms latency, micro-cars deviate by over 0.095m from the course for the 40% of the entire trajectory possibly causing car accidents. On the other hand, MEC-based control stabilizes the driving trajectory. Also, our proposed system automatically switches control from cloud and from edge server according to the network condition without degrading the stability in driving trajectory. Even when the ratio of time of control by edge server to that by cloud is suppressed to 54%, we can achieve almost the same stability as in full control by edge controller.
[1]
EDDIE KOHLER,et al.
The click modular router
,
2000,
TOCS.
[2]
Ch. Ramesh Babu,et al.
Internet of Vehicles: From Intelligent Grid to Autonomous Cars and Vehicular Clouds
,
2016
.
[3]
Swarun Kumar,et al.
CarSpeak: a content-centric network for autonomous driving
,
2012,
SIGCOMM '12.
[4]
Alberto Broggi,et al.
Autonomous vehicles control in the VisLab Intercontinental Autonomous Challenge
,
2012,
Annu. Rev. Control..
[5]
Makido Satoshi,et al.
Vehicle Control System based on Mobile-Edge Computing -- Evaluation of driving performance in the case of network error
,
2016
.
[6]
C. Knospe,et al.
PID control
,
2006,
IEEE Control Systems.