One Stop Autonomization: Generative AI-driven embodiment/Autonomisierung aus einer Hand: Wie generative KI humanoide Roboter zum universellen Agenten macht

Inhaltsverzeichnis

Bibliographische Infos

Cover der Ausgabe: wt Werkstattstechnik online Jahrgang 115 (2025), Heft 09
Open Access Vollzugriff

wt Werkstattstechnik online

Jahrgang 115 (2025), Heft 09

Autor:innen:
Verlag
VDI fachmedien, Düsseldorf
Copyrightjahr
2025
ISSN-Online
1436-4980
ISSN-Print
1436-4980

Kapitelinformationen

Open Access Vollzugriff

Jahrgang 115 (2025), Heft 09

One Stop Autonomization: Generative AI-driven embodiment/Autonomisierung aus einer Hand: Wie generative KI humanoide Roboter zum universellen Agenten macht

Autor:innen:
ISSN-Print
1436-4980
ISSN-Online
1436-4980
Kapitelvorschau:

Dieser Beitrag stellt das Konzept der „One Stop Autonomization“ unter Verwendung verkörperter, generativer KI-Agenten vor. Diese humanoiden Roboter agieren flexibel in realen Umgebungen und ermöglichen eine skalierbare, sichere und menschzentrierte Automatisierung. Der Schwerpunkt liegt auf der Erklärbarkeit, der simulationsbasierten Validierung und der Unterstützung der Fachkräfte, was ein neues Paradigma für kollaborative Autonomie in der Industrie und darüber hinaus darstellt.

Literaturverzeichnis

  1. [1] Github: Model Context Protocol. Date: 2025. Internet: github.com/modelcontextprotoco. Accessed: 11.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  2. [2] Agent2Agent (A2A) Protocol: A2A Protocol. Internet: a2a-protocol.org/latest/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  3. [3] Schmidt, S.; Beck, J.; Höltge, L. et al.: Humanoid Robots – Game Changer or hype? Study. Date: 2025. Internet: www.ipa.fraunhofer.de/content/dam/ipa/en/documents/Humanoid-Robots-Study_AI-Innovation-Center.pdf. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  4. [4] Tong, Y.; Liu, H.; Zhang, Z.: Advancements in Humanoid Robots: A Comprehensive Review and Future Prospects. IEEE/CAA Journal of Automatica Sinica 11 (2024) 2, pp. 301–328 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  5. [5] Sheng, Q.; Zhou, Z.; Li, J. et al.: A Comprehensive Review of Humanoid Robots. SmartBot 1 (2025) 1, doi.org/10.1002/smb2.12008 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  6. [6] Brollo, F.; Dabla-Norris, E.; de Mooij, R. et al: Broadening the Gains from Generative AI: The Role of Fiscal Policies. IMF Staff Discussion Notes 2024 (2024) 002, doi.org/10.5089/9798400277177.006 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  7. [7] OECD: OECD-Bericht zu Künstlicher Intelligenz in Deutschland. Paris: OECD Publishing 2024, doi.org/10.1787/8fd1bd9d-de. Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  8. [8] Reiser, U.; Connette, C.; Fischer, J. et al.: Care-O-bot ® 3 – creating a product vision for service robot applications by integrating design and technology. 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009), St. Louis, MO, USA, 2009, pp. 1992–1998 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  9. [9] Graf, B.; Reiser, U.; Hagele, M. et al.: Robotic home assistant Care-O-bot® 3 – product vision and innovation platform. 2009 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO), Tokyo/ Japan, 2009, pp. 139–144 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  10. [10] Nellis, S.: Nvidia CEO: Humanoid robot revolution is closer than you think. Date: 2025. Internet: www.reuters.com/technology/nvidia-ceo-humanoid-robot-revolution-is-closer-than-you-think-2025–03–19/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  11. [11] Yaman, A.; Schwab, J.; Nitsche, C. et al.: Comparison of Large Language Models for Deployment Requirements. Proceedings of the First International Conference on Generative Pre-trained Transformer Models and Beyond, 2024, pp. 41–44, doi.org/10.48550/arXiv.2508.00185 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  12. [12] Szot, A.; Mazoure, B.; Attia, O. et al.: From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons. arXiv 2024, doi.org/10.48550/arXiv.2412.08442 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  13. [13] Bargmann, D.; Kraus, W.; Huber, M. F.: Enabling Maintainablity of Robot Programs in Assembly by Extracting Compositions of Force- and Position-Based Robot Skills from Learning-from-Demonstration Models. 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, United Arab Emirates, 2024, pp. 9227–9234 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  14. [14] Alt, B.; Aumann, F.; Gienger, L. et al.: Modulare, datengetriebene Roboterprogrammierung für die Lösung komplexer Handhabungsaufgaben in Alltagsumgebungen. Date: 2020, Internet: publica.fraunhofer.de/bitstreams/b488fed0–04d3–40d8–8a0e-004c1c0ba2d6/download. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  15. [15] Albus, M.; Hornek, T.; Kraus, W. et al.: Towards scalability for resource reconfiguration in robotic assembly line balancing problems using a modified genetic algorithm. Journal of Intelligent Manufacturing 36 (2025) 2, pp. 1175–1199 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  16. [16] Surapaneni, R.; Jha, M.; Vakoc, M. et al.: Announcing the Agent2Agent Protocol (A2A). A new era of Agent Interoperability. Date: 09.04.2025. Internet: developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  17. [17] GEAR @ NVIDIA Research: GEAR. Generalist Embodied Agent Research. Internet: research.nvidia.com/labs/gear/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  18. [18] Mosbach, M.; Moraw, K.; Behnke, S.: Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations. ArXiv 2022, doi.org/10.48550/arXiv.2212.02126 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  19. [19] Zhu, X.; Liu, Y.; Li, H. et al.: Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt. ArXiv 2025, doi.org/10.48550/arXiv.2505.20795 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  20. [20] He, T.; Luo, Z.; Xiao, W. et al.: Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation. ArXiv 2024, doi.org/10.48550/arXiv.2403.04436 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  21. [21] NVidia: NVidia Omniverse. Develop the Next Generation of Physical AI-Enabled Applications. Internet: www.nvidia.com/en-us/omniverse/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  22. [22] Azhar, A.: The Rise of Intelligent Machines: Nvidia Accelerates Physical AI Progress. Stand: 20.03.2025. Internet: www.bigdatawire.com/2025/03/20/the-rise-of-intelligent-machines-nvidia-accelerates-physical-ai-progress/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  23. [23] Hitbot: Hitbot releases universal embodied intelligent operating system HITBOT OS, reshaping the robotics industry landscape. Internet: www.hitbotrobot.com/embodied-intelligence-operating-system/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  24. [24] CyberCortex Robotics: CyberCortex AI: Lightweight Robotics OS. Internet: cybercortex.ai/. Accessed: 06.08.2025 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  25. [25] Mori, M.: The Uncanny Valley. Energy 7 (1970) 4, pp. 33–35 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  26. [26] Fresz, B.; Dubovitskaya, E.; Brajovic, D. et al.: How Should AI Decisions Be Explained? Requirements for Explanations from the Perspective of European Law. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society 7 (2024), pp. 438–450 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  27. [27] Wagner, P.; Mehari, T.; Haverkamp, W. et al.: Explaining deep learning for ECG analysis: Building blocks for auditing and knowledge discovery. Computers in biology and medicine 176 (2024), #108525 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  28. [28] Letzgus, S.; Wagner, P.; Lederer, J. et al.: Toward Explainable Artificial Intelligence for Regression Models: A methodological perspective. IEEE Signal Processing Magazine 39 (2022) 4, pp. 40–58 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  29. [29] Wu, X.; Wedernikow, E.; Huber, M. F.: Data-Efficient Uncertainty-Guided Model-Based Reinforcement Learning with Unscented Kalman Bayesian Neural Networks. 2024 American Control Conference (ACC), Toronto, ON, Canada, 2024, pp. 104–110 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  30. [30] Wu, X.; Wagner, P.; Huber, M. F.: Quantification of Uncertainties in Neural Networks. In: Shajek, A.; Hartmann, E. A. (eds.): New Digital Work. Cham: Springer International Publishing 2023, pp. 276–287 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  31. [31] Chen, R.; Sun, Y.; Liu, C.: Dexterous Safe Control for Humanoids in Cluttered Environments via Projected Safe Set Algorithm. AxXiv 2025, doi.org/10.48550/arXiv.2502.02858 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  32. [32] Mickens, J.; Radway, S.; Netravali, R.: Guillotine: Hypervisors for Isolating Malicious AIs. ArXiv 2025, doi.org/10.48550/arXiv.2504.15499 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  33. [33] Scianca, N.; Ferrari, P.; Simone, D. de et al.: A behavior-based framework for safe deployment of humanoid robots. Autonomous Robots 45 (2021) 4, pp. 435–456 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  34. [34] Bauer, D.; Umgelter, D.; Schlereth, A. et al.: Complex Job Shop Simulation “CoJoSim”—A Reference Model for Simulating Semiconductor Manufacturing. Applied Sciences 13 (2023) 6, #3615, doi.org/10.3390/app13063615 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  35. [35] Fresz, B.; Göbels, V. P.; Omri, S. et al.: The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis. ArXiv 2024, doi.org/10.48550/arXiv.2408.02379 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61
  36. [36] Assran, M.; Bardes, A.; Fan, D. et al.: V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning. ArXiv 2025, doi.org/10.48550/arXiv.2506.09985 Google Scholar öffnen DOI: 10.37544/1436-4980-2025-09-61

Zitation

Download RIS Download BibTex

Downloads

Download Kapitel (PDF)

Hinweis

Dieses Werk ist urheberrechtlich geschützt und darf nur nach den Vorgaben der Nutzungs- und Lizenzvereinbarung genutzt werden. Jede darüber hinaus gehende Nutzung des Werkes ist ausdrücklich untersagt und wird verfolgt.

Per E-Mail teilen

Medien