close
Skip to main content
Springer Nature Link
Log in

Physical Intelligence on the Edge: A Vision for the Decade Ahead

  • Perspective
  • Special Issue: Celebrating the 40th Anniversary of JCST
  • Published:
Save article
View saved research
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

This article examines key challenges in computing systems research under the emerging paradigm of Physical Intelligence on the Edge (PIE), in which raw sensor streams are transformed into real-time, safety-critical intelligence that can act in the physical world. It traces the evolution of computing architectures from centralized systems to distributed systems and edge computing, and argues that PIE constitutes a qualitative shift: the edge becomes the primary platform for tightly integrating sensing, reasoning, and actuation under stringent real-time constraints. The article identifies five emerging research thrusts—embodied spatial reasoning, embodied temporal reasoning, edge-native customization, symbiosis, and sustainability. Using a hypothetical PIE scenario, it exposes a fundamental gap between the capabilities of current systems and the requirements of future PIE-enabled autonomy: while today’s edge platforms can execute individual components of perception and inference, they remain unable to autonomously close the sense-think-act loop with certifiable guarantees on timing and safety. This vision is further substantiated by recent industrial progress, including several compelling demonstrations showcased at CES 2026 by leading companies such as NVIDIA and AMD. The article concludes by calling for a paradigm shift in systems thinking—from efficiently transporting and processing data (bits) to predictably and safely influencing the physical world (atoms)—thereby positioning edge-native system design as a foundational enabler of next-generation autonomous and robotic systems.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+
from $39.99 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

References

  1. Shi W, Cao J, Zhang Q, Li Y, Xu L. Edge computing: Vision and challenges. IEEE Internet of Things Journal, 2016, 3(5): 637–646. DOI: https://doi.org/10.1109/JIOT.2016.2579198.

    Article  Google Scholar 

  2. Chiang M, Zhang T. Fog and IoT: An overview of research opportunities. IEEE Internet of Things Journal, 2016, 3(6): 854–864. DOI: https://doi.org/10.1109/JIOT.2016.2584538.

    Article  Google Scholar 

  3. Mao Y, You C, Zhang J, Huang K, Letaief K B. A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials, 2017, 19(4): 2322–2358. DOI: https://doi.org/10.1109/COMST.2017.2745201.

    Article  Google Scholar 

  4. Satyanarayanan M. The emergence of edge computing. Computer, 2017, 50(1): 30–39. DOI: https://doi.org/10.1109/MC.2017.9.

    Article  Google Scholar 

  5. Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J. Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 2019, 107(8): 1738–1762. DOI: https://doi.org/10.1109/JPROC.2019.2918951.

    Article  Google Scholar 

  6. Cong J, Ghodrat M A, Gill M, Grigorian B, Reinman G. CHARM: A composable heterogeneous accelerator-rich microprocessor. In Proc. the 2012 ACM/IEEE International Symposium on Low Power Electronics and Design, Jul. 2012, pp.379–384. DOI: https://doi.org/10.1145/2333660.2333747.

    Chapter  Google Scholar 

  7. Ji S, Chen X, Zhuang J, Zhang W, Yang Z, Schultz S, Song Y, Hu J, Jones A, Dong Z, Zhou P. ART: Customizing accelerators for DNN-enabled real-time safety-critical systems. In Proc. the 2025 Great Lakes Symposium on VLSI, Jul. 2025, pp.442–449. DOI: https://doi.org/10.1145/3716368.3735215.

    Chapter  Google Scholar 

  8. Ji S, Yang Z, Chen X, Zhang W, Zhuang J, Jones A, Dong Z, Zhou P. DERCA: DetERministic cycle-level accelerator on reconfigurable platforms in DNN-enabled real-time safety-critical systems. In Proc. the 2025 IEEE Real-Time Systems Symposium, Dec. 2025, pp.392–405. DOI: https://doi.org/10.1109/RTSS66672.2025.00039.

    Chapter  Google Scholar 

  9. Atat R, Liu L, Chen H, Wu J, Li H, Yi Y. Enabling cyber-physical communication in 5G cellular networks: Challenges, spatial spectrum sensing, and cyber-security. IET Cyber-Physical Systems: Theory & Applications, 2017, 2(1): 49–54. DOI: https://doi.org/10.1049/iet-cps.2017.0010.

    Article  Google Scholar 

  10. Kim M J, Pertsch K, Karamcheti S, Xiao T, Balakrishna A, Nair S, Rafailov R, Foster E P, Sanketi P R, Vuong Q, Kollar T, Burchfiel B, Tedrake R, Sadigh D, Levine S, Liang P, Finn C. OpenVLA: An open-source vision-language-action model. In Proc. the 8th Conference on Robot Learning, Nov. 2024.

    Google Scholar 

  11. Sumaiya, Jafarpourmarzouni R, Lu S, Dong Z. Enhancing real-time inference performance for time-critical software-defined vehicles. In Proc. the 2024 IEEE International Conference on Mobility, Operations, Services and Technologies, May 2024, pp.101–113. DOI: https://doi.org/10.1109/MOST60774.2024.00019.

    Google Scholar 

  12. Sumaiya, Jafarpourmarzouni R, Luo Y, Lu S, Dong Z. Toward real-time and efficient perception workflows in software-defined vehicles. IEEE Internet of Things Journal, 2025, 12(6): 7240–7258. DOI: https://doi.org/10.1109/JIOT.2024.3492801.

    Article  Google Scholar 

  13. Roa M A, Berenson D, Huang W. Mobile manipulation: Toward smart manufacturing [TC spotlight]. IEEE Robotics & Automation Magazine, 2015, 22(4): 14–15. DOI: https://doi.org/10.1109/MRA.2015.2486583.

    Article  Google Scholar 

  14. Chevalier A, Copot C, De Keyser R, Hernandez A, Ionescu C. A multi agent system for precision agriculture. In Handling Uncertainty and Networked Structure in Robot Control, Busoniu L, Tamás L (eds.), Springer, 2015, pp.361–386. DOI: https://doi.org/10.1007/978-3-319-26327-4_15.

    Chapter  Google Scholar 

  15. Lee J, Kang S, Lee J, Shin D, Han D, Yoo H J. The hardware and algorithm co-design for energy-efficient DNN processor on edge/mobile devices. IEEE Trans. Circuits and Systems I: Regular Papers, 2020, 67(10): 3458–3470. DOI: https://doi.org/10.1109/TCSI.2020.3021397.

    Google Scholar 

  16. Nowshin F, Dong Z, Yi Y. Memory-augmented autoencoder with reservoir computing for edge-based anomaly detection in autonomous systems. IEEE Internet Computing, 2025. DOI: https://doi.org/10.1109/MIC.2025.3594330.

  17. Jafarpourmarzouni R, Sumaiya F, Li R, Guan N, Wang G, Zhou P, Dong Z. Reaction latency analysis of message synchronization in edge-assisted autonomous driving. ACM Trans. Embedded Computing Systems, 2025. DOI: https://doi.org/10.1145/3736412.

  18. Liu T, Wang S, Li B, Dong Z, Wang G, Gong W, He T. Real-batch: Real-time adaptive batch processing for accurate object detection in autonomous driving. IEEE Trans. Mobile Computing, 2025. DOI: https://doi.org/10.1109/TMC.2025.3625072.

  19. Qian L, Luo Z, Du Y, Guo L. Cloud computing: An overview. In Proc. the 1st International Conference on Cloud Computing, Dec. 2009, pp.626–631. DOI: https://doi.org/10.1007/978-3-642-10665-1_63.

    Google Scholar 

  20. Waldo J, Wyant G, Wollrath A, Kendall S. A note on distributed computing. In Lecture Notes in Computer Science 1222, Vitek J, Tschudin C (eds.), Springer, 1997, pp.49–64. DOI: https://doi.org/10.1007/3-540-62852-5_6.

    Google Scholar 

  21. Birman K P. The process group approach to reliable distributed computing. Communications of the ACM, 1993, 36(12): 37–53. DOI: https://doi.org/10.1145/163298.163303.

    Article  Google Scholar 

  22. Wang Q, Yao Y, Shi W. Edge-assisted object perception for autonomous vehicles under challenging exposure and blur conditions. In Proc. the 3rd IEEE International Conference on Mobility, Operations, Services and Technologies, May 2025, pp.12–21. DOI: https://doi.org/10.1109/MOST65065.2025.00011.

    Google Scholar 

  23. Wu C, Gong Y, Liu L, Li M, Wu Y, Shen X, Li Z, Yuan G, Shi W, Wang Y. AyE-Edge: Automated deployment space search empowering accuracy yet efficient real-time object detection on the edge. In Proc. the 43rd IEEE/ACM International Conference on Computer-Aided Design, Oct. 2024, Article No. 178 DOI: https://doi.org/10.1145/3676536.3676655.

    Google Scholar 

  24. Bhattacharjee A, Mahmood H, Lu S, Ammar N, Ganlath A, Shi W. Edge-assisted over-the-air software updates. In Proc. the 9th IEEE International Conference on Collaboration and Internet Computing, Nov. 2023, pp.18–27. DOI: https://doi.org/10.1109/CIC58953.2023.00013.

    Google Scholar 

  25. Hao Y, Yang F, Fang N, Liu Y S. EMBOSR: Embodied spatial reasoning for enhanced situated question answering in 3D scenes. In Proc. the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct. 2024, pp.9811–9816. DOI: https://doi.org/10.1109/IROS58592.2024.10801720.

    Google Scholar 

  26. Vila L. A survey on temporal reasoning in artificial intelligence. AI Communications, 1994, 7(1): 4–28. DOI: https://doi.org/10.3233/AIC-1994-7102.

    Article  Google Scholar 

  27. Zhang M, Cao J, Yang L, Zhang L, Sahni Y, Jiang S. ENTS: An edge-native task scheduling system for collaborative edge computing. In Proc. the 7th IEEE/ACM Symposium on Edge Computing, Dec. 2022, pp.149–161. DOI: https://doi.org/10.1109/SEC54971.2022.00019.

    Google Scholar 

  28. Ajoudani A, Zanchettin A M, Ivaldi S, Albu-Schäffer A, Kosuge K, Khatib O. Progress and prospects of the human-robot collaboration. Autonomous Robots, 2018, 42(5): 957–975. DOI: https://doi.org/10.1007/s10514-017-9677-2.

    Article  Google Scholar 

  29. Li W, Yang T, Delicato F C, Pires P F, Tari Z, Khan S U, Zomaya A Y. On enabling sustainable edge computing with renewable energy resources. IEEE Communications Magazine, 2018, 56(5): 94–101. DOI: https://doi.org/10.1109/MCOM.2018.1700888.

    Article  Google Scholar 

  30. Duan J, Yu S, Tan HL, Zhu H, Tan C. A survey of embodied AI: From simulators to research tasks. IEEE Transactions on Emerging Topics in Computational Intelligence, 2022, 6(2): 230–244. DOI: https://doi.org/10.1109/TETCI.2022.3141105.

    Article  Google Scholar 

  31. Liu T, Wang S, Dong Z, Li B, He T. From perception to computation: Revisiting delay optimization for connected autonomous vehicles. ACM Computing Surveys, 2025, 57(8): Article No. 200. DOI: https://doi.org/10.1145/3718361.

  32. Tian Z, Xia L, Shi W. EMATO: Energy-model-aware trajectory optimization for autonomous driving. In Proc. the 2025 IEEE International Conference on Robotics and Automation, May 2025, pp.9682–9688. DOI: https://doi.org/10.1109/ICRA55743.2025.11127833.

    Google Scholar 

  33. Bouguettaya A, Kechida A, Taberkit A M. A survey on lightweight CNN-based object detection algorithms for platforms with limited computational resources. International Journal of Informatics and Applied Mathematics, 2019, 2(2): 28–44.

    Google Scholar 

  34. Ouyang Y, Wu X, Yang M, Han R, Luo A, Liu C, Chen J, Guo Y. EdgeTail: Mitigating long-tail visual problems in continual learning at edge. ACM Trans. Internet of Things, 2025. DOI: https://doi.org/10.1145/3786774.

  35. Zhang Y, Kang B, Hooi B, Yan S, Feng J. Deep longtailed learning: A survey. IEEE Trans. Pattern Analysis and Machine Intelligence, 2023, 45(9): 10795–10816. DOI: https://doi.org/10.1109/TPAMI.2023.3268118.

    Article  Google Scholar 

  36. Kaelbling L P, Littman M, Moore A W. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 1996, 4: 237–285. DOI: https://doi.org/10.5555/1622737.1622748.

    Article  Google Scholar 

  37. Lakoff G. Cognitive semantics. In Meaning and Mental Representations, Eco U, Santambrogio M, Violi P (eds.), Indiana University Press, 1988, pp.119–154.

    Google Scholar 

  38. Talmy L. Toward a cognitive semantics. Concept Structuring Systems, volume 1. MIT Press, 2000.

    Google Scholar 

  39. Ball R, North C, Bowman D A. Move to improve: Promoting physical navigation to increase user performance with large displays. In Proc. the 2007 SIGCHI Conference on Human Factors in Computing Systems, Apr. 28–May 3, 2007, pp.191–200. DOI: https://doi.org/10.1145/1240624.1240656.

    Chapter  Google Scholar 

  40. Chen T, Yao Y, Hofstee H P, Shi W. Open-vocabulary object detection with driving-aware multi-scale feature fusion for autonomous driving. In Proc. the 10th ACM/IEEE Symposium on Edge Computing, Dec. 2025, Article No. 66. DOI: https://doi.org/10.1145/3769102.3774632.

    Google Scholar 

  41. Liu L, Dong Z, Wang Y, Shi W. Prophet: Realizing a predictable real-time perception pipeline for autonomous vehicles. In Proc. the 2022 IEEE Real-Time Systems Symposium, Dec. 2022, pp.305–317. DOI: https://doi.org/10.1109/RTSS55097.2022.00034.

    Chapter  Google Scholar 

  42. Zhou Z, Li Y, Liu J, Li G. Equality constrained robust measurement fusion for adaptive Kalman-filter-based heterogeneous multi-sensor navigation. IEEE Trans. Aerospace and Electronic Systems, 2013, 49(4): 2146–2157. DOI: https://doi.org/10.1109/TAES.2013.6621807.

    Article  Google Scholar 

  43. Micucci D, Marchese F, Sorrenti D, Tisato F. A time-sensitive approach to mobile robot autonomous navigation. In Proc. the 2004 International Conference on Computing, Communications and Control Technologies, Aug. 2004, pp.377–382.

    Google Scholar 

  44. Kaplan R, Friston K J. Planning and navigation as active inference. Biological Cybernetics, 2018, 112(4): 323–343. DOI: https://doi.org/10.1007/s00422-018-0753-2.

    Article  Google Scholar 

  45. Li R, Jiang X, Dong Z, Wu J M, Xue C J, Guan N. Worst-case latency analysis of message synchronization in ROS. In Proc. the 2023 IEEE Real-Time Systems Symposium, Dec. 2023, pp.185–197. DOI: https://doi.org/10.1109/RTSS59052.2023.00025.

    Chapter  Google Scholar 

  46. Xu Y, Musgrave Z, Noble B, Bailey M. Bobtail: Avoiding long tails in the cloud. In Proc. the 10th USENIX Symposium on Networked Systems Design and Implementation, Apr. 2013, pp.329–341. DOI: https://doi.org/10.5555/2482626.2482658.

    Google Scholar 

  47. Marti P, Fuertes J M, Fohler G, Ramamritham K. Jitter compensation for real-time control systems. In Proc. the 22nd IEEE Real-Time Systems Symposium, Dec. 2001, pp.39–48. DOI: https://doi.org/10.1109/REAL.2001.990594.

    Google Scholar 

  48. Tong L, Li Y, Gao W. A hierarchical edge cloud architecture for mobile computing. In Proc. the 35th Annual IEEE International Conference on Computer Communications, Apr. 2016. DOI: https://doi.org/10.1109/INFOCOM.2016.7524340.

    Google Scholar 

  49. Herbert S, Marculescu D. Analysis of dynamic voltage/frequency scaling in chip-multiprocessors. In Proc. the 2007 International Symposium on Low Power Electronics and Design, Aug. 2007, pp.38–43. DOI: https://doi.org/10.1145/1283780.1283790.

    Chapter  Google Scholar 

  50. Choudhary T, Mishra V, Goswami A, Sarangapani J. A comprehensive survey on model compression and acceleration. Artificial Intelligence Review, 2020, 53(7): 5113–5155. DOI: https://doi.org/10.1007/s10462-020-09816-7.

    Article  Google Scholar 

  51. Luo Q, Luan T, Shi W, Fan P. Deep reinforcement learning based computation offloading and trajectory planning for multi-UAV cooperative target search. IEEE Journal on Selected Areas in Communications, 2023, 41(2): 504–520. DOI: https://doi.org/10.1109/JSAC.2022.3228558.

    Article  Google Scholar 

  52. Wu Z, Wang S, Bao Y, Shi W. Tentacles: A middleware with multi-network communication reliability for vehicleinfrastructure cooperative autonomous driving. In Proc. the 100th IEEE Vehicular Technology Conference, Oct. 2024. DOI: https://doi.org/10.1109/VTC2024-Fall63153.2024.10758047.

    Google Scholar 

  53. Luo Q, Luan T, Shi W, Fan P. Edge computing enabled energy-efficient multi-UAV cooperative target search. IEEE Trans. Vehicular Technology, 2023, 72(6): 7757–7771. DOI: https://doi.org/10.1109/TVT.2023.3238040.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer and Information Sciences, University of Delaware, Newark, DE, 19716, USA

    Weisong Shi

  2. Department of Computer Science, Wayne State University, Detroit, MI, 48202, USA

    Zheng Dong

  3. School of Engineering, Brown University, Providence, RI, 02912, USA

    Peipei Zhou

Authors
  1. Weisong Shi
    View author publications

    Search author on:PubMed Google Scholar

  2. Zheng Dong
    View author publications

    Search author on:PubMed Google Scholar

  3. Peipei Zhou
    View author publications

    Search author on:PubMed Google Scholar

Corresponding authors

Correspondence to Weisong Shi, Zheng Dong or Peipei Zhou.

Ethics declarations

Conflict of Interest Weisong Shi is an editorial board member for Journal of Computer Science and Technology and was not involved in the editorial review of this article. The authors declare that there are no other competing interests.

Additional information

Weisong Shi is an Alumni Distinguished Professor and Chair of the Department of Computer and Information Sciences at the University of Delaware (UD), Newark, where he leads the Connected and Autonomous Research (CAR) Laboratory. He is an internationally renowned expert in edge computing, autonomous driving, and connected health. He is the Editor-in-Chief of IEEE Internet Computing Magazine and Elsevier Smart Health. He is the founding steering committee chair of three conferences, including the ACM/IEEE Symposium on Edge Computing (SEC), the IEEE/ACM International Conference on Connected Health (CHASE), and the IEEE International Conference on Mobility (MOST).

Zheng Dong is an associate professor in the Department of Computer Science at Wayne State University, Detroit. He received his B.S. degree from Wuhan University, Wuhan, in 2007, his M.S. degree from the University of Science and Technology of China, Hefei, in 2011, and his Ph.D. degree from The University of Texas at Dallas, Richardson, in 2019. His research interests include real-time embedded AI systems, edge computing, and connected and autonomous driving systems. He received the Outstanding Paper Award at the 38th IEEE Real-Time Systems Symposium (RTSS) and a Best Paper nomination at the 23rd IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA). He serves as a Steering Committee Co-Chair of the IEEE Workshop on Physical Intelligence: Systems and Applications (PISA) and is a recipient of the NSF CAREER Award and the NSF CRII Award.

Peipei Zhou is currently an assistant professor at the School of Engineering, Brown University, Providence. She received her Ph.D. degree in computer science and her M.S. degree in electrical and computer engineering from University of California, Los Angeles, in 2019 and 2014, respectively, and her B.S. degree in electrical and computer engineering from Southeast University, Nanjing, in 2012. Her research investigates architecture, programming abstraction, and design automation tools for reconfigurable computing and heterogeneous computing. She has published 40 papers in IEEE/ACM computer system and design automation conferences and journals. Her work has won the 2025 IEEE/ACM ICCAD 10-Year Retrospective Most Influential Paper Award and the 2019 IEEE TCAD Donald O. Pederson Best Paper Award. Other awards include the 2024 ACM/IEEE IGSC Best Viewpoint Paper, the 2025 ACM/SIGDA FPGA Best Paper Nominee, the 2018 IEEE ISPASS Best Paper Nominee, and the 2018 IEEE/ACM ICCAD Best Paper Nominee.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shi, W., Dong, Z. & Zhou, P. Physical Intelligence on the Edge: A Vision for the Decade Ahead. J. Comput. Sci. Technol. 41, 67–82 (2026). https://doi.org/10.1007/s11390-026-6292-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1007/s11390-026-6292-8

Keywords