Abstract

These days, autonomous vehicles (AVs) technology has been improved dramatically. However, even though the AVs require no human intervention in most situations, AVs may fail in certain situations. In such cases, it is desirable that humans can operate the vehicle manually to recover from a failure situation through remote driving. Furthermore, we believe that remote driving can enhance the current transportation system in various ways. In this paper, we consider a revolutionary transportation platform, where all the vehicles in an area are controlled by some remote controllers or drivers so that transportation can be performed in a more efficient way. For example, road capacity can be effectively utilized and fuel efficiency can be increased by centralized remote control. However, one of the biggest challenges in such remote driving is the communication latency between the remote driver and the vehicle. Thus, selecting appropriate locations of the remote drivers is very important to avoid any type of safety problem that might happen due to large communication latency. Furthermore, the selection should reflect the traffic situation created by multiple vehicles in an area. To tackle these challenges, in this paper, we propose several algorithms that select remote drivers’ locations for a given transportation schedules of multiple vehicles. We consider two objectives in this system and evaluate the performance of the proposed algorithms through simulations. The results show that the proposed algorithms perform better than some baseline algorithms.

Highlights

  • Autonomous vehicles (AVs) technology has obtained a lot of attention, as it has significant effect on transportation systems

  • We assume a transportation environment of 3000 base stations, i.e., |B| = 3000 and 500 candidate remote driving locations, i.e., |F | = 500, in the area of 1000 × 1000, where base stations and remote driver are uniformly randomly distributed over the entire area

  • Since the main objective of proposing Extended Remote Driver Selection for Multiple Paths (ERDSMP) is to reduce the average distance for the same number of remote driving locations, we evaluate the average distances of the algorithms

Read more

Summary

Introduction

Autonomous vehicles (AVs) technology has obtained a lot of attention, as it has significant effect on transportation systems. A human with advanced perceptual and cognitive skills could be added to the AV control loop via remote driving. This improves AVs’ dependability and efficacy [4]. We describe many related works showing the feasibility of remote driving under the current communication infrastructures such as LTE and Wi-Fi. A truly autonomous vehicle was first suggested by S. Because of the remarkable benefits, local governments and several automobile manufacturers have invested in growing self-driving automobiles since 1977 These days, autonomous vehicles have mature hardware capabilities to allow absolute self-driving, but the driving emphalgorithms are still immature.

Objectives
Results
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.