EUVIMEDEUVIMED entdecken
Crossref

DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multimodal Reinforcement Learning

I Made Aswin Nahrendra, Byeongho Yu, Minho Oh, Dongkyu Lee, Seunghyun Lee, Hyeonwoo Lee, Hyungtae Lim, Hyun Myung

IEEE Transactions on Robotics · 2026 · 42 · 819-836

DOI: 10.1109/tro.2026.3653774 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2026. Verfasst von I Made Aswin Nahrendra und 7 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: Korea Evaluation Institute of Industrial Technology, Korea Government, Dynamic and Atypical Environments for Real Application.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quadrupedal robots hold promising potential for applications in navigating cluttered environments with resilience akin to their animal counterparts. However, their floating-base configuration makes them susceptible to real-world uncertainties, presenting substantial challenges in locomotion control. Deep reinforcement learning has emerged as a viable alternative for developing robust locomotion controllers. However, approaches relying solely on proprioception often sacrifice collision-free locomotion, as they require front-foot contact to detect stairs and adapt the gait. Meanwhile, incorporating exteroception necessitates a precisely modeled map observed by exteroceptive sensors over time. This work proposes a novel method for fusing proprioception and exteroception through a resilient multimodal reinforcement learning framework. The proposed method yields a controller demonstrating agile locomotion on a quadrupedal robot across diverse real-world courses, including rough terrains, steep slopes, and high-rise stairs, while maintaining robustness in out-of-distribution situations.

Förderung

  • Korea Evaluation Institute of Industrial Technology
  • Korea Government
  • Dynamic and Atypical Environments for Real Application
  • Korea Forest Service
  • R&D Program for Forest Science Technology

Zitieren

APA

Nahrendra, I. M. A., Yu, B., Oh, M., Lee, D., Lee, S., Lee, H., Lim, H., & Myung, H. (2026). DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multimodal Reinforcement Learning. IEEE Transactions on Robotics, 42, 819-836. https://doi.org/10.1109/tro.2026.3653774

Vancouver

Nahrendra IMA, Yu B, Oh M, Lee D, Lee S, Lee H, et al. DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multimodal Reinforcement Learning. IEEE Transactions on Robotics. 2026;42:819-836. doi:10.1109/tro.2026.3653774

BibTeX
@article{Nahrendra2026,
  author = {Nahrendra, I Made Aswin and Yu, Byeongho and Oh, Minho and Lee, Dongkyu and Lee, Seunghyun and Lee, Hyeonwoo and Lim, Hyungtae and Myung, Hyun},
  title = {DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multimodal Reinforcement Learning},
  journal = {IEEE Transactions on Robotics},
  year = {2026},
  volume = {42},
  pages = {819--836},
  doi = {10.1109/tro.2026.3653774}
}
Kostenlos starten →