Get Started
Home
Topics
Search
Library
Research questionHow can vehicle-infrastructure cooperative driving be evaluated for error accumulation under occlusion without costly full simulation?At urban intersections, infrastructure observations can help when vehicles are occluded, but cooperating agents still make decisions with incomplete and heterogeneous information. Open-loop tests miss deviations that compound over time, while closed-loop simulation can be expensive and difficult to scale.
Computer Vision
Evaluation & Benchmarks
Multi-agent Systems
Robotics
Latest papersRecent research connected to this question, newest first.VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-SimulationThe source presents VIPS, a pseudo-simulation benchmark that integrates vehicle and infrastructure observations to evaluate robustness and error propagation in cooperative V2I planning without full simulation. It also reports CoS-V2X, which uses sparse representations for communication and planning under heterogeneous observations.research paper · Sep 2, 2026
Related questions
How can edge systems fuse occlusion-limited vehicle observations and predict trajectories within strict freshness limits at scale?How can autonomous-driving planners be stress-tested in realistic closed-loop scenarios that expose failures missed by nominal benchmarks?How can LLM-based vehicle negotiation avoid premature agreement when multiple driving decisions are viable?How can low-cost platforms enable reproducible testing of end-to-end autonomous-driving policies across simulation and physical vehicles?