Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
157 tokens/sec
GPT-4o
43 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Model-Assisted Learning for Adaptive Cooperative Perception of Connected Autonomous Vehicles (2401.10156v1)

Published 18 Jan 2024 in cs.NI and eess.SP

Abstract: Cooperative perception (CP) is a key technology to facilitate consistent and accurate situational awareness for connected and autonomous vehicles (CAVs). To tackle the network resource inefficiency issue in traditional broadcast-based CP, unicast-based CP has been proposed to associate CAV pairs for cooperative perception via vehicle-to-vehicle transmission. In this paper, we investigate unicast-based CP among CAV pairs. With the consideration of dynamic perception workloads and channel conditions due to vehicle mobility and dynamic radio resource availability, we propose an adaptive cooperative perception scheme for CAV pairs in a mixed-traffic autonomous driving scenario with both CAVs and human-driven vehicles. We aim to determine when to switch between cooperative perception and stand-alone perception for each CAV pair, and allocate communication and computing resources to cooperative CAV pairs for maximizing the computing efficiency gain under perception task delay requirements. A model-assisted multi-agent reinforcement learning (MARL) solution is developed, which integrates MARL for an adaptive CAV cooperation decision and an optimization model for communication and computing resource allocation. Simulation results demonstrate the effectiveness of the proposed scheme in achieving high computing efficiency gain, as compared with benchmark schemes.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. W. Zhuang, Q. Ye, F. Lyu, N. Cheng, and J. Ren, “SDN/NFV-empowered future IoV with enhanced communication, computing, and caching,” Proc. IEEE, vol. 108, no. 2, pp. 274–291, 2019.
  2. X. Shen, J. Gao, W. Wu, M. Li, C. Zhou, and W. Zhuang, “Holistic network virtualization and pervasive network intelligence for 6G,” IEEE Commun. Surv. Tutor., vol. 24, no. 1, pp. 1–30, 2021.
  3. Y. Hui, X. Ma, Z. Su, N. Cheng, Z. Yin, T. H. Luan, and Y. Chen, “Collaboration as a service: Digital-twin-enabled collaborative and distributed autonomous driving,” IEEE Internet Things J., vol. 9, no. 19, pp. 18 607–18 619, 2022.
  4. J. Wang, J. Liu, and N. Kato, “Networking and communications in autonomous driving: A survey,” IEEE Commun. Surv. Tutor., vol. 21, no. 2, pp. 1243–1274, 2018.
  5. J. Zhang and K. B. Letaief, “Mobile edge intelligence and computing for the Internet of vehicles,” Proc. IEEE, vol. 108, no. 2, pp. 246–261, 2019.
  6. X. Zheng, S. Li, Y. Li, D. Duan, L. Yang, and X. Cheng, “Confidence evaluation for machine learning schemes in vehicular sensor networks,” IEEE Trans. Wirel. Commun., vol. 22, no. 4, pp. 2833–2846, 2023.
  7. Y. Jia, R. Mao, Y. Sun, S. Zhou, and Z. Niu, “Online V2X scheduling for raw-level cooperative perception,” in Proc. IEEE ICC, 2022, pp. 309–314.
  8. ——, “Mass: Mobility-aware sensor scheduling of cooperative perception for connected automated driving,” IEEE Trans. Veh. Technol., vol. 72, no. 11, pp. 14 962–14 977, 2023.
  9. M. K. Abdel-Aziz, C. Perfecto, S. Samarakoon, M. Bennis, and W. Saad, “Vehicular cooperative perception through action branching and federated reinforcement learning,” IEEE Trans. Commun., vol. 70, no. 2, pp. 891–903, 2022.
  10. Z. Xiao, J. Shu, H. Jiang, G. Min, H. Chen, and Z. Han, “Perception task offloading with collaborative computation for autonomous driving,” IEEE J. Sel. Areas Commun., vol. 41, no. 2, pp. 457–473, 2023.
  11. Y. Sun, J. Xu, and S. Cui, “User association and resource allocation for MEC-enabled IoT networks,” IEEE Trans. Wirel. Commun., vol. 21, no. 10, pp. 8051–8062, 2022.
  12. J. Lin, P. Yang, N. Zhang, F. Lyu, X. Chen, and L. Yu, “Low-latency edge video analytics for on-road perception of autonomous ground vehicles,” IEEE Trans. Industr. Inform., vol. 19, no. 2, pp. 1512–1523, 2022.
  13. X. Zhang, A. Zhang, J. Sun, X. Zhu, Y. E. Guo, F. Qian, and Z. M. Mao, “EMP: Edge-assisted multi-vehicle perception,” in Proc. 27th Annual International Conf. Mobile Computing and Networking, 2021, pp. 545–558.
  14. Q. Chen, S. Tang, Q. Yang, and S. Fu, “Cooper: Cooperative perception for connected autonomous vehicles based on 3D point clouds,” in Proc. IEEE Int. Conf. Distrib. Comput. Syst. (ICDCS), 2019, pp. 514–524.
  15. H. Qiu, P. Huang, N. Asavisanu, X. Liu, K. Psounis, and R. Govindan, “Autocast: Scalable infrastructure-less cooperative perception for distributed collaborative driving,” in Proc. ACM Int. Conf. Mobile Syst., Appl. and Services (MobiSys), 2021, pp. 128–141.
  16. Q. Chen, X. Ma, S. Tang, J. Guo, Q. Yang, and S. Fu, “F-cooper: Feature based cooperative perception for autonomous vehicle edge computing system using 3D point clouds,” in Proc. ACM/IEEE Symp. Edge Comput. (SEC), 2019, pp. 88–100.
  17. T.-H. Wang, S. Manivasagam, M. Liang, B. Yang, W. Zeng, and R. Urtasun, “V2VNeT: Vehicle-to-vehicle communication for joint perception and prediction,” in Proc. Eur. Conf. Comput. Vision (ECCV), 2020, pp. 605–621.
  18. W. Wu, N. Chen, C. Zhou, M. Li, X. Shen, W. Zhuang, and X. Li, “Dynamic RAN slicing for service-oriented vehicular networks via constrained learning,” IEEE J. Sel. Areas Commun., vol. 39, no. 7, pp. 2076–2089, 2021.
  19. W. Zhang, Z. He, L. Liu, Z. Jia, Y. Liu, M. Gruteser, D. Raychaudhuri, and Y. Zhang, “Elf: accelerate high-resolution mobile deep vision with content-aware parallel offloading,” in Proc. ACM MobiCom, 2021, pp. 201–214.
  20. H. Wang, Q. Li, H. Sun, Z. Chen, Y. Hao, J. Peng, Z. Yuan, J. Fu, and Y. Jiang, “Vabus: Edge-cloud real-time video analytics via background understanding and subtraction,” IEEE J. Select. Areas Commun., vol. 41, no. 1, pp. 90–106, 2023.
  21. K. Yang, J. Yi, K. Lee, and Y. Lee, “FlexPatch: Fast and accurate object detection for on-device high-resolution live video analytics,” in IEEE Proc. INFOCOM, 2022, pp. 1898–1907.
  22. S. Teerapittayanon, B. McDanel, and H.-T. Kung, “Distributed deep neural networks over the cloud, the edge and end devices,” in Proc. IEEE ICDCS, 2017, pp. 328–339.
  23. K. Qu, W. Zhuang, W. Wu, M. Li, X. Shen, X. Li, and W. Shi, “Stochastic cumulative DNN inference with RL-aided adaptive IoT device-edge collaboration,” IEEE Internet Things J., vol. 10, no. 20, pp. 18 000–18 015, 2023.
  24. E. Li, L. Zeng, Z. Zhou, and X. Chen, “Edge AI: On-demand accelerating deep neural network inference via edge computing,” IEEE Trans. Wirel. Commun., vol. 19, no. 1, pp. 447–457, 2020.
  25. Z. Liu, Q. Lan, and K. Huang, “Resource allocation for multiuser edge inference with batching and early exiting,” IEEE J. Select. Areas Commun., vol. 41, no. 4, pp. 1186–1200, 2023.
  26. H. Wang, H. Bao, L. Zeng, K. Luo, and X. Chen, “Real-time high-resolution pedestrian detection in crowded scenes via parallel edge offloading,” in Proc. IEEE ICC, 2023.
  27. K. Qu, W. Zhuang, Q. Ye, X. Shen, X. Li, and J. Rao, “Dynamic flow migration for embedded services in SDN/NFV-enabled 5G core networks,” IEEE Trans. Commun., vol. 68, no. 4, pp. 2394–2408, 2020.
  28. R. Lowe, Y. I. Wu, A. Tamar, J. Harb, O. Pieter Abbeel, and I. Mordatch, “Multi-agent actor-critic for mixed cooperative-competitive environments,” in Proc. 30th Adv. Neural Inf. Process. Syst. (NeurIPS), 2017, pp. 6379–6390.
  29. J. Tian, Q. Liu, H. Zhang, and D. Wu, “Multiagent deep-reinforcement-learning-based resource allocation for heterogeneous QoS guarantees for vehicular networks,” IEEE Internet Things J., vol. 9, no. 3, pp. 1683–1695, 2022.
  30. Q. Ye, W. Shi, K. Qu, H. He, W. Zhuang, and X. Shen, “Joint RAN slicing and computation offloading for autonomous vehicular networks: A learning-assisted hierarchical approach,” IEEE Open J. Veh. Technol., vol. 2, pp. 272–288, 2021.
  31. E. Jang, S. Gu, and B. Poole, “Categorical reparameterization with gumbel-softmax,” Proc. ICLR, 2017.
  32. “Simulation of Urban MObility (SUMO) 1.16.0,” https://www.eclipse.org/sumo/, 2023, [Online; accessed 8-January-2024].
  33. 3GPP, “Study on evaluation methodology of new Vehicle-to-Everything (V2X) use cases for LTE and NR,” 3rd Generation Partnership Project (3GPP), Technical Specification (TS) 37.885, 2019, version 15.3.0.
Citations (12)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets