Simulation of DACH-Style Detector-Actuated Traffic Signal Control in SUMO
summary
A Python middleware directly imports LISA+® logic files and maps signal groups, phase sequences and timing to SUMO controllers while translating SUMO states into the OMTC message format. Simulated sensors include E2 loop detectors for loops, beacon placement for buses, and a pedestrian push‑button emulation; R09 public‑transport telegrams are generated and parsed. A high‑fidelity digital twin reproduces historic detector timelines, and a residual reinforcement‑learning controller adjusts green by -2 to +8 s to cut public‑transport delay while keeping overall performance acceptable.
AI-written summary · about
chapters (11)
- 0:00Introduction and group overview
- 1:33Laboratory and research assets
- 4:43PyLiSuM development background
- 7:47Communication architecture
- 9:28Data message formats
- 10:14Modeling sensors and inputs
- 11:54Comparison with historical data
- 12:36Digital twin applications
- 14:42Reinforcement learning testing
- 16:52Performance evaluation
- 17:25Field deployment and conclusion
related talks
19mSensor-based Flow Optimization on connected real-world intersections via a SUMO Feature Gap Analysis
16mAutomated Calibration of Traffic Demand and Traffic Lights in SUMO Using Real-World Observations
14mAnalysis and Modelling of Road Traffic Using SUMO to Optimize the Arrival Time of Emergency Vehicles
14mThe state of Bicycle Modeling in SUMO
15mSUMO and the Transportation GeoXchange (TGX)
17mSignal priority for improving fluidity and decreasing fuel consumption
21mChallenges in Reward Design for Reinforcement Learning-based Traffic Signal Control
25mErlang-based Desynchronised Urban Traffic Simulation (...)