arXiv · 2611.21924
GridDriver: On-Board BEV-Based Language Planning and Reasoning
Abstract
Bird's-Eye-View (BEV)-conditioned large language models (LLMs) enable language-interactive driving, but onboard deployment requires efficient perception and continuous planning alongside autoregressive language generation. We present GridDriver, an efficient BEV-conditioned LLM framework combining trajectory prediction, structured driving indicators, natural-language navigation, driving explanations, and scene question answering. Lightweight spatio-temporal BEV perception and spatially structured tokens provide scene context to a shared LLM, while frame-wise scheduling interleaves trajectory prediction with asynchronous language generation. GridDriver achieves competitive performance on public benchmarks, reaching 87.9% PDMS on NAVSIM and 57.6% accuracy on nuScenes-QA with a shared planning and QA checkpoint. Spatial representation analyses demonstrate improved geometric information retention and trajectory prediction compared with Q-Former compression. The system achieves 32.7 ms standalone planning latency and 9.4 plans/s in an onboard ROS 2 pipeline. We further evaluate planning on our own data recordings and demonstrate open-loop onboard operation on a research vehicle. Across public benchmarks and real-world evaluations, we identify strengths and limitations of the BEV-based approach.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Katharina Winter, William Engel, Zain A. Alishammat, Fabian B. Flohr. 2026-11-16. GridDriver: On-Board BEV-Based Language Planning and Reasoning. https://searcharxiv.com/abs/2611.21924
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.