EUVIMEDEUVIMED entdecken
Crossref

Transferable RL for Real-World Navigation Using Semantic Segmentation and Bird’s-Eye View Abstraction

Benedikt Schlereth-Groh, Sakir Furkan Yöndem, Ramin Tavakoli Kolagari

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 40416-40422

DOI: 10.1609/aaai.v40i47.41484 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Benedikt Schlereth-Groh und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reinforcement Learning (RL) has shown significant promise in developing autonomous navigation algorithms for complex environments. However, the direct application of RL policies trained in simulation to real-world scenarios often faces challenges due to the reality gap. This paper proposes a two-stage system incorporating a segmentation strategy and a bird’s-eye-view (BEV) representation to mitigate the domain gap between simulation and reality. In the first stage, the segmentation transforms sensor data into a simplified and interpretable representation of the surrounding area, facilitating transferability across different deployments. In the second stage, the agent navigates through the BEV map, which can be trained using a vectorized simulation environment---a setup that runs multiple parallel instances of the environment to provide a wide range of training scenarios. This vectorization enables rapid exposure to varied environmental conditions, thereby accelerating and diversifying the training of a deep RL agent to achieve optimal navigation behaviors while maintaining high-speed, in-bound trajectories. The segmentation is crucial because it supports generalization of the learned policy across different robotic platforms. The contribution of this paper lies in combining real-time semantic segmentation with a bird’s-eye-view navigation policy, resulting in a transferable and scalable framework for real-world deployment of RL-based navigation agents. Experimental results demonstrate that agents trained with this methodology exhibit robust navigation performance and adaptability in both simulated and real-world environments, validating the efficacy of combining vectorized simulation with real-world segmentation for practical robotic navigation.

Zitieren

APA

Schlereth-Groh, B., Yöndem, S. F., & Kolagari, R. T. (2026). Transferable RL for Real-World Navigation Using Semantic Segmentation and Bird’s-Eye View Abstraction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 40416-40422. https://doi.org/10.1609/aaai.v40i47.41484

Vancouver

Schlereth-Groh B, Yöndem SF, Kolagari RT. Transferable RL for Real-World Navigation Using Semantic Segmentation and Bird’s-Eye View Abstraction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):40416-40422. doi:10.1609/aaai.v40i47.41484

BibTeX
@article{SchlerethGroh2026,
  author = {Schlereth-Groh, Benedikt and Yöndem, Sakir Furkan and Kolagari, Ramin Tavakoli},
  title = {Transferable RL for Real-World Navigation Using Semantic Segmentation and Bird’s-Eye View Abstraction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {40416--40422},
  doi = {10.1609/aaai.v40i47.41484}
}
Kostenlos starten →