EIDrive: an efficient and interpretable visual-language framework for low-level control signal prediction in autonomous driving
Abstract
In recent years, end-to-end autonomous driving models have shown promising potential by directly generating waypoints or control signals from sensor data. In particular, low-level control signals, such as steering angle and vehicle speed, directly determine vehicle motion, making their prediction accuracy and interpretability important to the safety and reliability of autonomous driving systems. However, existing methods mainly regress control signals from visual inputs and lack explicit semantic characterization of the basis underlying control generation, making it difficult to establish a traceable link between scene understanding and control outputs. To address this issue, we propose E fficient and I nterpretable Driving (EIDrive), an efficient visual-language framework for low-level control signal prediction in autonomous driving. Given monocular driving videos, EIDrive jointly performs control signal prediction and natural-language explanation generation. Specifically, a sparse orthogonal subspace projection mechanism is introduced to improve feature compactness and structural expressiveness. A lightweight fine-tuned BERT model is employed as a shared semantic backbone, together with a structured control prediction head to model structured correlations among control-related features. On the BDD-X dataset, EIDrive achieves a turning-angle RMSE of 6.1 and a speed prediction accuracy of 88.2% under the 1.0 m/s threshold. It also demonstrates competitive language-generation performance while maintaining a compact computational profile.
Related
- Bridging the Literature-to-Laboratory Gap with Language Models and Active Learning for Reaction Feasibility Prediction and Autonomous Exploration
- BioInteract combines residue-level cross-attention with protein-language and physicochemical priors for interpretable drug–target interaction prediction
- ETPP: An Efficient Traversal Path Planning Framework for Autonomous Robot Exploration in Unknown Environments
- BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding
- Chemistry-infused bandit framework for interpretable autonomous campaign of electrocatalysis
BibTeX
@article{dong2026eidrive,
title = {{EIDrive: an efficient and interpretable visual-language framework for low-level control signal prediction in autonomous driving}},
author = {Wei Dong and Yingfeng Cai and Xiaoqiang Sun and Ze Liu and Hai Wang and Long Chen},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-72906-z},
url = {https://www.nature.com/articles/s41598-026-72906-z},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - EIDrive: an efficient and interpretable visual-language framework for low-level control signal prediction in autonomous driving
AU - Wei Dong
AU - Yingfeng Cai
AU - Xiaoqiang Sun
AU - Ze Liu
AU - Hai Wang
AU - Long Chen
PY - 2026
DA - 2026/10/01
JO - Scientific Reports
DO - 10.1038/s41598-026-72906-z
UR - https://www.nature.com/articles/s41598-026-72906-z
AB - In recent years, end-to-end autonomous driving models have shown promising potential by directly generating waypoints or control signals from sensor data. In particular, low-level control signals, such as steering angle and vehicle speed, directly determine vehicle motion, making their prediction accuracy and interpretability important to the safety and reliability of autonomous driving systems. However, existing methods mainly regress control signals from visual inputs and lack explicit semantic characterization of the basis underlying control generation, making it difficult to establish a traceable link between scene understanding and control outputs. To address this issue, we propose E fficient and I nterpretable Driving (EIDrive), an efficient visual-language framework for low-level control signal prediction in autonomous driving. Given monocular driving videos, EIDrive jointly performs control signal prediction and natural-language explanation generation. Specifically, a sparse orthogonal subspace projection mechanism is introduced to improve feature compactness and structural expressiveness. A lightweight fine-tuned BERT model is employed as a shared semantic backbone, together with a structured control prediction head to model structured correlations among control-related features. On the BDD-X dataset, EIDrive achieves a turning-angle RMSE of 6.1 and a speed prediction accuracy of 88.2% under the 1.0 m/s threshold. It also demonstrates competitive language-generation performance while maintaining a compact computational profile.
SN - 2045-2322
ER -