Xincao Xu (Chinese character 许新操 or 許新操), also known as Neil Xu received his Ph.D. degree in Computer Science from the College of Computer Science at Chongqing University (CQU), Chongqing, China, in 2023. He previously earned his B.S. degree in Network Engineering from the School of Computer and Control Engineering at the North University of China (NUC), Taiyuan, China, in 2017. Dr. Xu is currently a Postdoctoral Research Fellow, working in cooperation with Prof. Shaohua Wan at the Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China (UESTC), in Shenzhen. He has authored and co-authored more than 15 papers with total google scholar .

His research is primarily focused on several cutting-edge areas, including:

• AI for Driving, covering aspects like heterogeneous information fusion, cooperative sensing, multimodal deep learning, and driving behavior control.
• Vehicular Networks, with a focus on cooperative transmission and computing, integrated sensing and communications, and resource allocation.
• Vehicular Cyber-Physical Systems, encompassing sensing, transmitting, modeling, and controlling.
• Edge Computing, emphasizing the offloading of communication, computing, and caching abilities from the cloud to the network edge.
• Deep Reinforcement Learning, including multi-agent DRL, hierarchical DRL, and the integration of DRL with other technologies such as game theory and evaluation algorithms.
• Game Theory, with a specific interest in potential games, matching, auctions, and related concepts.

🔥 News

December 2023

• Grant Award 💰: Delighted to announce my selection for the 2023 National Postdoctoral Research Fellowship Program (Tier C). Celebrating this momentous occasion! 🌟🎉

November 2023

• Journal Acceptance 📚: Thrilled to announce that one of our paper titled “Cooperative Sensing and Heterogeneous Information Fusion in VCPS: A Multi-agent Deep Reinforcement Learning Approach” has been accepted by the prestigious IEEE Transactions on Intelligent Transportation Systems (T-ITS)! 🎉🚀
• Grant Award 💰: Successfully secured the 74th general project grant from the China Postdoctoral Science Foundation.

October 2023

• Conference Acceptance : One of our paper titled “Quality-Cost Trade-off on Constructing Logical Views for Vehicular Cyber-Physical Systems: A Deep Reinforcement Learning Approach” has been accepted for presentation at the 2023 IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-AS).

September 2023

• Journal Acceptance : A paper titled “Cooperative Sensing and Uploading for Quality-Cost Tradeoff of Digital Twins in VEC” has been accepted by the IEEE Transactions on Consumer Electronics (TCE). 🎊

October 2022

• Journal Acceptance : A paper titled “Joint Task Offloading and Resource Optimization in NOMA-Based Vehicular Edge Computing: A Game-Theoretic DRL Approach” has been accepted for publication in the Journal of Systems Architecture (JSA).
• Citation Milestone 🌟: Reached a significant milestone with 100 citations on Google Scholar. A testament to the impact of our work in the scientific community.

September 2022

• Patent Approval : Received official approval for an invention patent from the China National Intellectual Property Administration. A proud moment that highlights our innovative contributions.

June 2022

• Conference Acceptance : Excited to have a conference paper titled “Age of View: A New Metric for Evaluating Heterogeneous Information Fusion in Vehicular Cyber-Physical Systems” accepted at the 2022 IEEE International Conference on Intelligent Transportation Systems (ITSC).

🔬 Research

VCPS

System Model

Cooperative Sensing and Heterogeneous Information Fusion in VCPS: A Multi-agent Deep Reinforcement Learning Approach
Xincao Xu, Kai Liu^*, Penglin Dai, Ruitao Xie, Jingjing Cao, and Jiangtao Luo

• A novel problem is investigated to maximize the quality of VCPS by integrating the sensing, uploading, modeling and evaluation of heterogeneous information in VCPS. In particular, a cooperative sensing model is derived based on the multi-class M/G/1 priority queue and the Shannon theory. On this basis, a new metric called Age of View (AoV) is designed to quantitatively measure the quality of information fusion by evaluating the timeliness, completeness, and consistency of heterogeneous information in VCPS. To the best of our knowledge, this is the first work on quantitatively evaluating the quality of VCPS with the consideration of unique characteristics captured by the newly designed metic AoV.
• A dedicated solution named multi-agent difference-reward based actor-critic with V2I bandwidth allocation (MDRAC-VBA) is proposed based on multi-agent actor-critic. Specifically, vehicles act as independent agents with action space of sensing frequencies and uploading priorities. The system state consists of vehicle sensed information, edge cached information, and view requirements. The system reward is defined as the achieved VCPS quality. Then, a difference reward (DR) based credit assignment scheme is designed to evaluate the contributions of individual vehicles on view construction by dividing the system reward into difference rewards, so as to enhance the evaluation accuracy in term of the action of each agent. Further, the solution manages to achieve smaller action space of each agent and speed up the convergency compared with conventional DRL algorithms. Meanwhile, a V2I bandwidth allocation (VBA) scheme is designed at the edge node based on vehicle trajectories and view requirements.
• A comprehensive performance evaluation is conducted based on real-world vehicular trajectories. The proposed MDRAC-VBA algorithm and four competitive algorithms, including random allocation (RA), centralized deep deterministic policy gradient (C-DDPG), multi-agent actor-critic (MAC) and MAC with VBA scheme (MAC-VBA) are implemented. The simulation results demonstrated that MDRAC-VBA outperforms RA, C-DDPG, MAC, and MAC-VBA by around 61.8%, 23.8%, 22.0%, and 8.0%, respectively, in terms of maximizing the VCPS quality, and speeds up the convergence by around 6.8x, 1.4x and 1.3x compared with C-DDPG, MAC, and MAC-VBA, respectively.
• Accepted by IEEE Transactions on Intelligent Transportation Systems [JCR Q1|SCI Q1]

DT-VEC

MAMO

Cooperative Sensing and Uploading for Quality-Cost Tradeoff of Digital Twins in VEC
Kai Liu^*, Xincao Xu^*, Penglin Dai, and Biwen Chen

• We formulate a bi-objective problem for enabling Digital Twins in Vehicular Edge Computing (DT-VEC), where a cooperative sensing model and a V2I uploading model are derived, and novel metrics for quantitatively evaluating system quality and cost are designed.
• We propose a multi-agent multi-objective (MAMO) deep reinforcement learning model, which determines the sensing objects, sensing frequency, uploading priority, and transmission power of vehicles, as well as the V2I bandwidth allocation of edge nodes. The model includes distributed actors interacting with the environment and storing their interaction experiences in the replay buffer, a learner with a dueling critic network for evaluating actions of vehicles and edge nodes.
• We give comprehensive performance evaluation by implementing three representative algorithms, including random allocation (RA), distributed distributional deep deterministic policy gradient (D4PG) and multi-agent D4PG (MAD4PG), and the simulation results demonstrate that the proposed MAMO significantly outperforms existing solutions under different scenarios with respect to both maximizing system quality and saving system cost.
• Accepted by IEEE Transactions on Consumer Electronics [JCR Q2|SCI Q2]

NOMA-based VEC

GT-DRL

Joint Task Offloading and Resource Optimization in NOMA-based Vehicular Edge Computing: A Game-Theoretic DRL Approach
Xincao Xu, Kai Liu^*, Penglin Dai, Feiyu Jin, Hualing Ren, Choujun Zhan, and Songtao Guo

• We present a NOMA-based VEC architecture, where the vehicles share the same frequency of bandwidth resources and communicate with the edge node with the allocated transmission power. The tasks arrive stochastically at vehicles and are heterogeneous regarding computation resource requirements and deadlines, which are uploaded by vehicles via V2I communications. Then, the edge nodes with heterogeneous computation capabilities, i.e., CPU clock speed, can either execute the tasks locally with allocated computation resources or offload the tasks to neighboring edge nodes through a wired network.
• We propose a cooperative resources optimization (CRO) problem by jointly offloading tasks and allocating communication and computation resources to maximize the service ratio, which is the number of tasks serviced before the deadlines divided by the number of requested tasks. Specifically, a V2I transmission model considering both intra-edge and inter-edge interference and a task offloading model considering the heterogeneous resources and cooperation of edge nodes are theoretically modeled, respectively.
• We decompose the CRO problem into two subproblems: 1) task offloading game model and 2) resource allocation convex problem. Specifically, we model the first subproblem as a non-cooperative game among edge nodes, which is further proved as an EPG with the existence and convergence of NE. Then, we design a MAD4PG algorithm, a multi-agent version of D4PG, to achieve the NE, where edge nodes act as independent agents to determine the task offloading decisions and receive the achieved potential as rewards. Further, we model the second subproblem as two independent convex problems and derive an optimal mathematical solution based on the gradient-based iterative method and KKT condition.
• Accepted by Journal of Systems Architecture [JCR Q1|SCI Q2|CCF B]

📖 Publication

JCR: Journal Citation Reports by Clarivate Com.
SCI: Journal Partition List by National Science Library, Chinese Academy of Sciences
CCF: Recommended Publications by China Computer Federation
*: Corresponding Author

Journal

1. Xincao Xu, Kai Liu^*, Penglin Dai, Ruitao Xie, Jingjing Cao, and Jiangtao Luo, Cooperative Sensing and Heterogeneous Information Fusion in VCPS: A Multi-agent Deep Reinforcement Learning Approach, IEEE Transactions on Intelligent Transportation Systems (T-ITS), early access, doi: 10.1109/TITS.2023.3340334. IF: 8.5 (2022), 9 (5-year) [JCR Q1|SCI Q1|CCF B]
2. Kai Liu^*, Xincao Xu^*, Penglin Dai, and Biwen Chen, Cooperative Sensing and Uploading for Quality-Cost Tradeoff of Digital Twins in VEC, IEEE Transactions on Consumer Electronics (TCE), early access, doi: 10.1109/TCE.2023.3318853. IF: 4.3 (2022), 3.9 (5-year) [JCR Q2|SCI Q2]
3. Xincao Xu, Kai Liu^*, Penglin Dai, Feiyu Jin, Hualing Ren, Choujun Zhan, and Songtao Guo, Joint Task Offloading and Resource Optimization in NOMA-Based Vehicular Edge Computing: A Game-Theoretic DRL Approach, Journal of Systems Architecture (JSA), volume 134, pp. 102780, January 2023. IF: 4.5 (2022), 4 (5-year) [JCR Q1|SCI Q2|CCF B]
4. Chunhui Liu, Kai Liu^*, Hualing Ren, Xincao Xu, Ruitao Xie, and Jingjing Cao, RtDS: Real-time Distributed Strategy for Multi-period Task Offloading in Vehicular Edge Computing Environment, Neural Computing and Applications (NCA), volume 35, pp. 12373–12387, March 2021. IF: 6 (2022), 5.6 (5-year) [JCR Q1|SCI Q2]
5. Ke Xiao, Kai Liu^*, Xincao Xu, Liang Feng, Zhou Wu, and Qiangwei Zhao, Cooperative Coding and Caching Scheduling via Binary Particle Swarm Optimization in Software Defined Vehicular Networks, Neural Computing and Applications (NCA), volume 33, pp. 1467-1478, May 2021. IF: 6 (2022), 5.6 (5-year) [JCR Q1|SCI Q2]
6. Ke Xiao, Kai Liu^*, Xincao Xu, Yi Zhou, and Liang Feng, Efficient Fog-assisted Heterogeneous Data Services in Software Defined VANETs, Journal of Ambient Intelligence and Humanized Computing (JAIHC), volume 12, issue 1, pp.261-273, January 2021. [SCI Q3]
7. Xincao Xu, Kai Liu^*, Ke Xiao, Liang Feng, Zhou Wu, and Songtao Guo, Vehicular Fog Computing Enabled Real-time Collision Warning via Trajectory Calibration, Mobile Networks and Applications (MONET), volume 25, issue 6, pp. 2482-2494, December 2020. IF: 3.8 (2022), 3.3 (5-year) [JCR Q2|CCF C]
8. Kai Liu^*, Xincao Xu, Mengliang Chen, Bingyi Liu^*, Libing Wu, and Victor Lee, A Hierarchical Architecture for the Future Internet of Vehicles, IEEE Communications Magazine (ComMag), volume 57, issue 7, pp. 41-47, July 2019. IF: 11.2 (2022), 11.2 (5-year) [JCR Q1|SCI Q1]

Conference

1. Junyuan Wu, Xincao Xu^*, Chuzhao Li, Hao Zhang, Ke Xiao, and Kai Liu, Quality-Cost Trade-off on Constructing Logical Views for Vehicular Cyber-Physical Systems: A Deep Reinforcement Learning Approach, IEEE International Symposium on Product Compliance Engineering-Asia (IEEE ISPCE-AS’23), Shanghai, China, November 3-5, 2023.
2. Xincao Xu, Kai Liu^*, Qisen Zhang, Hao Jiang, Ke Xiao, and Jiangtao Luo, Age of View: A New Metric for Evaluating Heterogeneous Information Fusion in Vehicular Cyber-Physical Systems, IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC’22), Macau, China, October 8-12, 2022.
3. Chunhui Liu, Kai Liu^*, Xincao Xu, Hualing Ren, Feiyu Jin, and Songtao Guo, Real-time Task Offloading for Data and Computation Intensive Services in Vehicular Fog Computing Environments, IEEE International Conference on Mobility, Sensing and Networking (IEEE MSN’20), Tokyo, Japan, December 17-19, 2020.
4. Yi Zhou, Kai Liu^*, Xincao Xu, Chunhui Liu, Liang Feng, and Chao Chen, Multi-period Distributed Delay-sensitive Tasks Offloading in a Two-layer Vehicular Fog Computing Architecture, International Conference on Neural Computing and Applications (NCAA’20), Shenzhen, China, July 3-6, 2020.
5. Yi Zhou, Kai Liu^*, Xincao Xu, Songtao Guo, Zhou Wu, Victor Lee, and Sang Son, Distributed Scheduling for Time-Critical Tasks in a Two-layer Vehicular Fog Computing Architecture, IEEE Consumer Communications and Networking Conference (IEEE CCNC’20), Las Vegas, USA, January 11-14, 2020.
6. Xincao Xu, Kai Liu^*, Ke Xiao, Hualing Ren, Liang Feng, and Chao Chen, Design and Implementation of a Fog Computing Based Collision Warning System in VANETs, IEEE International Symposium on Product Compliance Engineering-Asia (IEEE ISPCE-CN’18), Hong Kong/Shenzhen, China, December 5-7, 2018. (Best Paper Award)

Chinese Papers

1. Xincao Xu, Kai Liu^*, Chunhui Liu, Hao Jiang, Songtao Guo, and Weiwei Wu, Potential Game Based Channel Allocation for Vehicular Edge Computing, Tien Tzu Hsueh Pao/Acta Electronica Sinica (电子学报), volume 49, issue 5, pp.851-860, July 2021. [CCF T1]
2. Xincao Xu, Yi Zhou, Kai Liu^*, Chaocen Xiang, Yantao Li, and Songtao Guo, Potential Game based Distributed Channel Allocation in Vehicular Fog Computing Environments, 14th China Conference on Internet of Things (CWSN’20), Dunhuang, China, September 18-21, 2020. (Best Paper Candidate)

Dissertation

• Xincao Xu, Research on Key Techniques for Modeling and Optimization of Vehicular Cyber-Physical Systems, Chongqing University, Doctoral Dissertation, June 2023.

🏆 Grants

NSFC: National Natural Science Foundation of China
CPSF: China Postdoctoral Science Foundation

Principal Investigator

1. CPSF, National Postdoctoral Research Fellowship Program (Tier C), “Research on Integrated Sensing and Communications based Vehicle-Infrastructure Cooperation System for Vehicular Digital Twin Networks”, GZC20230384, 240,000 CNY, Jan 2024 - Jun 2025.
2. CPSF, General Fund, “Modeling and Optimization of Cyber-Physical System for Vehicular Edge Computing”, 2023M740515, 80,000 CNY, Jan 2024 - Jun 2025.

Participation

1. NSFC, General Project, “Computing Model Deployment and Collaborative Cross Domain Optimization for Edge Intelligence of Internet of Vehicles”, 62172064, 590,000 CNY, Jan 2022 - Dec 2025.
2. NSFC, General Project, “Research on High Performance Data Transmission and Reception Mechanism of Wireless Energy-capable Communication Network Based on Successive Interference Cancellation”, 62072064, 580,000 CNY, Jan 2021 - Dec 2024.
3. NSFC, General Project, “Research on Continuous Authentication Method and Key Technologies for Mobile Users Based on Behavioral Characteristics”, 62072061, 580,000 CNY, Jan 2021 - Dec 2024.
4. NSFC, General Project, “Research on Intelligent Multitask High-Performance Optimization Algorithms Based on Transfer Learning”, 61876025, 620,000 CNY, Jan 2019 – Dec 2022.
5. NSFC, General Project, “Research on Architecture and Protocols for Large-scale Data Services in Converged Heterogeneous Internet of Vehicles”, 61872049, 640,000 CNY, Jan 2019 – Dec 2022.

✨ Others

📄 Patents

• Xincao Xu, Kai Liu, Dong Li, “A Control Plane View Construction Method for Software-Defined Vehicular Networks”, Chinese Invention Patent, ZL202110591822.1, 2022.
• Liu Kai, Zhang Lang, Xincao Xu, Ren Hualing, Zhou Yi, “An Edge Computing Based Collision Warning Method for Vehicles in Blind Areas”, Chinese Invention Patent, ZL201910418745.2, 2021.
• Ren Hualing, Liu Kai, Chen Mengliang, Zhou Yi, Xincao Xu, “A Fog Computing-based Information Acquisition, Computing, and Transmission Architecture”, Chinese Invention Patent, ZL201910146357.3, 2021.

📺 Demo

• Non-Light-of-Sight Collision Warning System

📢 Call for Papers

*: Estimated Date

👨🏻‍💻 Experience

💼 Work

• Jul 2023 - Jun 2025 (now): Postdoctoral Research Fellow, Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China. In cooperation with Prof. Shaohua Wan.

🎓 Education

• Sep 2019 - Jun 2023: Ph.D. in Computer Science, College of Computer Science, Chongqing University, Chongqing, China. Supervised by Prof. Kai Liu.
• Sep 2017 - Jun 2019: Postgraduate student (Joined the successive postgraduate-doctor program in 2019), Computer Science, College of Computer Science, Chongqing University, Chongqing, China.
• Sep 2013 - Jun 2017: Bachelor in Network Engineering, College of Computer and Control Engineering, North University of China, Taiyuan, China.

😎 Membership

• Sep 2023 - now: Member #G0818M, China Computer Federation (CCF).
• Oct 2023 - now: Member #3120145, Association for Computing Machinery (ACM).
• Sep 2023 - now: Member #99619216, Institute of Electrical and Electronics Engineers (IEEE).
• Nov 2020 - Aug 2023: Student Member #G0818G, China Computer Federation (CCF).

👀 Reviewer

Journal

• IEEE Transactions on Intelligent Transportation Systems (T-ITS)
• IEEE Transactions on Consumer Electronics (TCE)
• IEEE Transactions on Vehicular Technology (TVT)
• Journal of Systems Architecture (JSA)
• Neural Computing and Applications (NCAA)
• The Journal of Supercomputing (TJSC)
• Journal of Computer Research and Development
• Tien Tzu Hsueh Pao/Acta Electronica Sinica

Conference

• IEEE Vehicular Technology Conference (VTC-Fall’23)
• International Conference on Artificial Intelligence of Things and Systems (AIoTSys’23)
• IEEE International Conference on Intelligent Transportation Systems (ITSC’22,23)
• IEEE Global Communications Conference (GLOBECOM’21,23)
• International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP’21)
• China Conference on Internet of Things (Wireless Sensor Network) (CWSN’21)
• IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom’20)
• IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-CN’20)

📦 Resources

Shareable Materials

• Conference Proceedings and Journals Related to Internet of Vehicles
• Handbook for Research Beginner 01: Research Tools and Paper Reading (in Chinese)
• Handbook for Research Beginner 02: Paper Architecture and Writting (in Chinese)
• Handbook for Research Beginner 03: Patent Drafting (in Chinese)

Courses

• Introduction to Algorithms by MIT
• Meachine Learning by Prof. Hung-yi Lee
• Meachine Learning by Prof. Richard Xu
• Deep Learning by Prof. Andrew Ng
• Deep Reinforcement Learning by Dr. Shusen Wang

Books

	Meachine Learning Prof. Zhi-Hua Zhou Tsinghua University Press, 2016 ISBN: 9787302423287 🇨🇳Chinese
	Machine Learning Yearning Prof. Andrew NG Free Ebook, 2018 🇬🇧English | 🇨🇳Chinese
	Deep Learning Dr. Ian Goodfellow, Prof. Yoshua Bengio, and Prof. Aaron Courville MIT Press, 2016 ISBN: 9780262035613 🇬🇧English | 🇨🇳Chinese
	Dive into Deep Learning Dr. Aston Zhang, Dr. Zachary C. Lipton, Dr. Mu Li, and Dr. Alexander I. Smola Cambridge University Press, 2023 ISBN: 1009389432 🇬🇧English | 🇨🇳Chinese

Research

• Google Scholar: Largest Search Engine for Academic Publishing
• dblp: Computer Science Bibliography
• Conference PartnerConference Partner: Information about Academic Conferences
• LetPub: Information about SCI Journals
• Academic Accelerator: Wonderful Tool to Accelerate Your Scientific Research
• WikiCFP: A Wiki for Calls for Papers
• Zotero: Personal Research Assistant
• IEEE Template Selector: Find the Right IEEE Article Template for Your Target Publication

Grant

• NSFC Big Data: Official Big Data Knowledge Management Service Portal of National Natural Science Foundation
• LetPub: Scientific Fund Results Inquiry System
• NSFC Proposal Template: Unofficial LaTeX Format Template for National Natural Science Foundation of China Grant Applications
• Full Names of Related Funds: Chinese-English Comparison
• Funding, Award, and Scholarship Translation summarized by Xovee Xu

Coding

• Python Tutorial by Xuefeng Liao 🇨🇳Chinese
• Python Documentation 🇬🇧English 🇨🇳Chinese
• Python for Beginners 🇨🇳Chinese

🧩 Interests

🎵 Music

• Recently on Repeat

• Favorite Albums

The 400 Blows Sigle	Aqua Hotel Sigle	Summer Time EP	Bedazzling	Real Love Is...	David Tao	Sense+	Bye Bye That's All
Roy Wang	Roy Wang	Roy Wang	Roy Wang	The Chairs	David Tao	The Life Journey	Bad Sweetheart
2020	2020	2021	2022	2020	1997	2018	2021

• Step into his world of melodious favorites and discover a carefully curated music collection.
  
• Explore his Replay 2023 playlist, a journey through his most played tracks on

🎬 Movies

The Secret Life of Walter Mitty	Romeo + Juliet	Moulin Rouge!	Call Me by Your Name	A Clockwork Orange
Ben Stiller	Baz Luhrmann	Baz Luhrmann	Luca Guadagnino	Stanley Kubrick
2013	1996	2001	2017	1971

🏃 Sports

Passionate about fitness, he has earned a series of accolades in his active lifestyle. Take a glimpse at his Apple Fitness achievements:

Four-week continuous Fitness+ workout streak award	Daily Move goal reached 100 times award	50th Fitness+ Treadmill workout accomplishment	50-time winner of the 7-workouts-per-week challenge	Top cycling calorie burner award (525 Calories)	Peak calorie burn on the elliptical award (645 Calories)	Maximum calories burned running award (579 Calories)	Highest calories burned swimming award (157 Calories)
Aug 15, 2023	Nov 30, 2021	Aug 7, 2023	Sep 22, 2023	May 17, 2023	Jan 21, 2023	Aug 16, 2023	Jun 13, 2023

🎮 Gaming

His world of gaming spans across various consoles, offering endless adventures and excitement.

• Connect with him on by adding his Friend Code: SW-2057-0942-7707
  • The Legend of Zelda: Breath of the Wild
  • The Legend of Zelda: Tears of the Kingdom
  • Super Smash Bros.
  • Splatoon 3
  • Mario Kart 8 Deluxe
  • Animal Crossing: New Horizons
• Nintendo Year in Review 2023

• Join him on by adding him PSN ID: near_dws
  • The Last of Us Part I
  • Final Fantasy VII Remake
  • Detroit: Become Human
  • Life is Strange 2
  • Life is Strange: True Colors

📱 Tech

His interest in digital gadgets extends to a wide range of applications and tools.

Hardware

Software