Effectiveness of Digital Twin Computing on Path Tracking Control of Unmanned Vehicle by Cloud Server

Yoshimoto, Yudai; Watanabe, Takahiro; Nakamura, Ryohei; Hadama, Hisaya

doi:10.1587/transcom.2021ebp3204

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, vehicles' limited computational resources and storage space may not suffice for many latency-sensitive and computationally intensive tasks in real-world scenarios [3]. To achieve this goal, early research [4][5][6] combined the Internet of Vehicles with cloud computing, using the powerful computing storage resources of the cloud to process vehicle tasks. However, outsourcing all computing tasks to the cloud may lead to network congestion, as cloud servers are typically located far from vehicles.…”

Section: Introductionmentioning

confidence: 99%

A joint task caching and computation offloading scheme based on Deep Reinforcement Learning

Tian,

Zhu,

Tan

2024

Preprint

View full text Add to dashboard Cite

Considering the dynamic variability of the vehicular edge environment and the limited edge servers resources, this paper proposes a joint task caching and computation offloading scheme based on deep reinforcement learning (DRL). Considering that the motion trajectories of different vehicles overlap and their task requests may be the same, this paper designs a vehicle-edge-cloud computing framework to fully use the cache resources of vehicles, edge servers, and clouds to reduce task processing delays and energy consumption. Secondly, this paper adopts a method of partial offloading and collaboration between edge servers, which fully utilizes the computing resources of vehicles, edge servers, and the cloud, reducing the burden of vehicles and edge servers. In addition, this paper proposes a DRL-based task offloading scheme to obtain better task caching and offloading strategies. The simulation results show that the scheme proposed in this article performs better compared to other schemes and effectively reduces the latency and energy consumption of task processing.

show abstract

Section: Introductionmentioning

confidence: 99%

A joint task caching and computation offloading scheme based on Deep Reinforcement Learning

Tian,

Zhu,

Tan

2024

Preprint

View full text Add to dashboard Cite

show abstract

A Real Time Tracking Method for Unmanned Traffic Vehicle Paths Based on Electronic Tags

Zhou,

Yuan

2024

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

An experimental study on digital twin computing for cloud-based remote path tracking control of unmanned vehicle

et al. 2022

View full text Add to dashboard Cite

Our previous study quantitatively evaluated that digital twin computing was effective for remote control of a small vehicle by a cloud server through simulations. To confirm the effectiveness, we realized an experimental remote control system with digital twin model (DTM) of a small vehicle. Then, we evaluated the vehicle control accuracy on remote path tracking control. This letter shows the results. We confirmed that the DTM improved the control accuracy when there existed one-way transmission delay of 500 ms. In addition, we evaluated reduction of the control accuracy due to modeling error between the DTM and the real vehicle.

show abstract

Effectiveness of Digital Twin Computing on Path Tracking Control of Unmanned Vehicle by Cloud Server

Cited by 4 publications

References 15 publications

A joint task caching and computation offloading scheme based on Deep Reinforcement Learning

A joint task caching and computation offloading scheme based on Deep Reinforcement Learning

A Real Time Tracking Method for Unmanned Traffic Vehicle Paths Based on Electronic Tags

An experimental study on digital twin computing for cloud-based remote path tracking control of unmanned vehicle

Contact Info

Product

Resources

About