Selective Cooperative Perception via Blind Spot Reasoning and Agentic Dialogue with Vision-Language Models
Selective Cooperative Perception via Blind Spot Reasoning and Agentic Dialogue with Vision-Language Models
This paper introduces a VLM-driven agentic framework for selective cooperative perception in multi-agent traffic environments. The system integrates conventional object detection, vision-language reasoning for occlusion identification, and a physics-based geometric module to align reasoning with visibility constraints. Using real-world data from connected vehicles in urban traffic, the authors evaluate four state-of-the-art VLMs, reporting over 80% accuracy in driving-critical blind spot detection and over 90% success in dialogue-driven perception sharing. The work aims to provide a scalable, interpretable, and bandwidth-efficient alternative to conventional cooperative perception pipelines.
The authors propose a VLM-driven framework for selective cooperative perception in multi-agent traffic, combining object detection with vision-language reasoning and geometric modules; reported metrics (over 80% accuracy in blind spot detection and over 90% success in dialogue-driven perception sharing) are based on experiments using real-world data from connected vehicles in urban traffic.
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
Reported accuracy
>80%
View original evidence
od achieves over 80% accuracy in driving-critical blind spot detection and over 90% success in dialogue-driven perception sharing. This work provides a scalable, interpretable, and bandwidth-efficient alternative to conventional CP pipelines, and offers new insights into agentic communication design for future connected traffic systems.
Open source S5Reported accuracy
>90%
View original evidence
od achieves over 80% accuracy in driving-critical blind spot detection and over 90% success in dialogue-driven perception sharing. This work provides a scalable, interpretable, and bandwidth-efficient alternative to conventional CP pipelines, and offers new insights into agentic communication design for future connected traffic systems.
Open source S5
Dataset details reported by the source
- Modalities
- Vision-Language Models Open source S2Open source S3conventional object detection Open source S3
- Tasks
- blind spot reasoning Open source S3Open source S5
- Embodiments
- connected vehicles operating in urban traffic Open source S4
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Dataset licensing and commercial-use rights are not established here.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
n dynamic and uncertain environments, making them a promising tool for this selective CP task. This study proposes a VLM-driven agentic framework for blind spot reasoning and dialogue-based CP. A mixed-model architecture is designed that integrates conventional object detection for stable perception, vision-language reasoning for identifying impactful occlusions, and a physics-based geometric module to align reasonin
Open source S3
arXiv:2611.10819v1 Announce Type: new Abstract: Real-time cooperative perception (CP) in multi-agent traffic environments is highly resource-intensive, which posing scalability challenges for large-scale deployment. Efficiency can be significantly improved by selectively performing CP only in safety-critical scenarios and for key occluding objects. Vision-Language Models (VLMs) are well-suited for complex reasoning i
Open source S2
od achieves over 80% accuracy in driving-critical blind spot detection and over 90% success in dialogue-driven perception sharing. This work provides a scalable, interpretable, and bandwidth-efficient alternative to conventional CP pipelines, and offers new insights into agentic communication design for future connected traffic systems.
Open source S5
g with real-world visibility constraints. The framework also incorporates a Chain-of-Thought (CoT) prompting mechanism to enhance interpretability and intent-aware decision-making. We collect real-world data from connected vehicles operating in urban traffic and compare the driving-critical blind spot identification and dialogue performance of four state-of-the-art VLMs. Experimental results demonstrate that our meth
Open source S4
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org