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