analiza aiqbench
Sem-NaVAE demonstrates a practical advance in outdoor robotics by combining generative trajectory planning with lightweight visual language models to achieve 90% navigation success in unseen environments without relying on pre-existing maps. The system effectively leverages open-vocabulary semantic scoring to select optimal paths in real-time, bridging the gap between exploratory generative models and reliable local planning. This approach offers a promising direction for autonomous agents operating in dynamic, unstructured settings where traditional mapping is infeasible.
Sem-NaVAE: Semantically-Guided Outdoor Mapless Navigation via Generative Trajectory Priors
arXiv:2602.01429v2 Announce Type: replace Abstract: This work presents a mapless navigation approach for outdoor applications. It combines the exploratory capacity of conditional variational autoencoders (CVAEs) to generate trajectories and the semantic segmentation capabilities of a lightweight visual language model (VLM) to select the trajectory to execute. Open-vocabulary segmentation is used to score and select the generated trajectories based on natural language, and a state-of-the-art local planner executes velocity commands. One of the key features of the proposed approach is its ability to generate a large variability of trajectories and select them to navigate in real-time. In real-world outdoor experiments, Sem-NaVAE achieves a 90% success rate across routes of 120-240m in unseen environments, outperforming the nearest baseline by 10% while remaining within 7% of a map-based upper bound. A video showing an experimental run of the system can be found in https://youtu.be/i3R5ey5O2yk.
Abstract:This work presents a mapless navigation approach for outdoor applications. It combines the exploratory capacity of conditional variational autoencoders (CVAEs) to generate trajectories and the semantic segmentation capabilities of a lightweight visual language model (VLM) to select the trajectory to execute. Open-vocabulary segmentation is used to score and select the generated trajectories based on natural language, and a state-of-the-art local planner executes velocity commands. One of the key features of the proposed approach is its ability to generate a large variability of trajectories and select them to navigate in real-time. In real-world outdoor experiments, Sem-NaVAE achieves a 90% success rate across routes of 120-240m in unseen environments, outperforming the nearest baseline by 10% while remaining within 7% of a map-based upper bound. A video showing an experimental run of the system can be found in this https URL.
Accepted for publication in IEEE Robotics and Automation Letters (RA-L). 8 pages, 5 figures
Robotics (cs.RO)
arXiv:2602.01429 [cs.RO]
(or arXiv:2602.01429v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2602.01429 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 243 cuvinte