Research map / Learning theory and algorithms / Combinatorial and search optimization
Expressive Real-Time Intersection Scheduling
Rick Goldstein, Stephen Smith
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use lane-based expressive model with dual-ring A* search instead of SURTRAC simplified clustering | schedule-driven intersection control · Single intersection, 160 veh/h | time loss (s): 22.9 -> 18.4 | Improved |
| use lane-based expressive model instead of SURTRAC | schedule-driven intersection control · Single intersection, 1600 veh/h | time loss (s): 51.3 -> 49.6 | Improved |
| use ERIS instead of SURTRAC/actuated | intersection control · 3x3 grid, 500 veh/h | time loss (s): 48.5 -> 39.4 | Improved |
| use ERIS instead of SURTRAC | intersection control · 3x3 grid, 5300 veh/h | time loss (s): 146.7 -> 146.0 | No clear effect |
| use ERIS instead of connected fully-actuated control | intersection control · 3x3 grid, 5300 veh/h | time loss (s): 149.0 -> 146.0 | Improved |
| add admissible relaxation-based heuristic to A* (ablation) | ERIS scheduler · Single intersection, 1600 veh/h | mean run-time (ms): 105.0 -> 4.1 (dominance checks only vs heuristic only) | Improved |
| add dominance checks to A* with heuristic (ablation) | ERIS scheduler · Single intersection, 1600 veh/h | mean run-time (ms): 4.1 -> 3.6 | Improved |
Closest papers by meaning
- OAM: An Option-Action Reinforcement Learning Framework for Universal Multi-Intersection Control (AAAI 2022 · similarity 0.85)
- IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning (ICLR 2025 · similarity 0.80)
- Traffic Scenario Logic: A Spatial-Temporal Logic for Modeling and Reasoning of Urban Traffic Scenarios (AAAI 2025 · similarity 0.80)
- VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture (NeurIPS 2025 · similarity 0.80)
- CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control (ICLR 2026 · similarity 0.80)
- π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control (AAAI 2024 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
