SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
This paper introduces SAGE (Semantic-to-Action Grounded Execution), a read-decide-execute-check framework that integrates vision-language model trajectories with geometric path candidates to navigate temporary traffic control zones. Trained on 2,306 real-world ROADWork validation episodes using MUTCD-compliant supervision, SAGE reduces average displacement error by 8.3% and final displacement error by 12.0% relative to a geometric ranker, while reducing hard-constraint violations by 37%. The system achieves a path within 10 pixels of human demonstrations in 87% of episodes and outperforms four other adapted driving VLMs in safety measures.
The study presents SAGE, a hybrid framework combining vision-language models with geometric predictors to navigate temporary traffic control zones, validated on 2,306 real-world episodes where it reduced displacement errors by 8.3% and hard-constraint violations by 37% compared to baseline rankers.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
average displacement error reduction
8.3
View original evidence
e a path within 10 px of the human demonstration in 87% of episodes, yet selection regret accounts for 53% of the geometric ranker's error. SAGE reduces average and final displacement errors by 8.3% and 12.0% relative to the ranker and hard-constraint violations by 37%. The trajectory opinion improves all four tested generator-selector combinations. SAGE is comparable to state-of-the-art VLM modules in accuracy, with
Open source S5final displacement error reduction
12
View original evidence
e a path within 10 px of the human demonstration in 87% of episodes, yet selection regret accounts for 53% of the geometric ranker's error. SAGE reduces average and final displacement errors by 8.3% and 12.0% relative to the ranker and hard-constraint violations by 37%. The trajectory opinion improves all four tested generator-selector combinations. SAGE is comparable to state-of-the-art VLM modules in accuracy, with
Open source S5
- code: not_reported
- weights: not_reported
- dataset: not_reported
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ctory. Supervision structured around the Manual on Uniform Traffic Control Devices (MUTCD) trains SAGE-VLM to state the lane status and hazard side before its passage decision and trajectory. The predicted hazard side enters image-space predicates derived from MUTCD provisions, which support a final intervention bounded in score and displacement. On 2,306 real-world ROADWork validation episodes, the candidates includ
Open source S4
n), a read-decide-execute-check framework that separates path construction, path preference, and control compliance within a shared candidate space. The central idea is to use a vision-language model's (VLM's) trajectory as a preference over intact geometric candidates. A role-decoupled generator constructs the candidates, and rank fusion combines each candidate's geometric score with its agreement with the VLM traje
Open source S3
e a path within 10 px of the human demonstration in 87% of episodes, yet selection regret accounts for 53% of the geometric ranker's error. SAGE reduces average and final displacement errors by 8.3% and 12.0% relative to the ranker and hard-constraint violations by 37%. The trajectory opinion improves all four tested generator-selector combinations. SAGE is comparable to state-of-the-art VLM modules in accuracy, with
Open source S5
SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
Open source S1
arXiv:2610.31835v2 Announce Type: replace-cross Abstract: Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a continuous passing path. Geometric predictors provide several plausible paths, yet selecting the one consistent with the temporary control remains difficult. We propose SAGE (Semantic-to-Action Grounded Executio
Open source S2
a faster-responding VLM, and outperforms four other adapted driving VLMs in displacement error and safety measures. Project page: https://hhjj233.github.io/SAGE-page/.
Open source S6
Source：arXiv Robotics — research abstracts · arxiv.org