Simulation based method for the analysis of energy-efficient driving algorithms
summary
A reproducible Python tool-chain couples SUMO + MATLAB energy model to evaluate driving algorithms by simulating a controlled CAV on a real urban test circuit and feeding generated driving cycles into a forward-facing electric-vehicle model parameterized to a Tesla Model S 75D measurements. Validation shows three measured cycles and simulated outputs match within about 1% SOC, 100 random SUMO runs reproduce traffic statistics, and a parameter sweep of Krauss car‑following (20 runs per combo) reveals lower accel/decel reduces energy and high auxiliary use (30% → 80%) shifts results upward.
AI-written summary · about
chapters (7)
- 0:00Research motivation
- 1:10Experimental setup
- 3:24Simulation methodology
- 5:47Validation of results
- 8:48Statistical analysis
- 12:07Application example
- 15:31Outlook and conclusions
related talks
20mSimulating platooned connected autonomous vehicle in a large scale urban scenario
13mExtending SUMO for Lane-Free Microscopic Simulation of Connected and Automated Vehicles
45mKEYNOTE: Traffic simulation modeling: combining generative modeling with transportation science ...
20mEnvironmental Benefits of Efficient Power Moding in Vehicles
18mSUMO Simulations for Federated Learning in Communicating Autonomous Vehicles
20mEnergy Optimized Green Light Assist in Varying Traffic Scenarios Using Reinforcement Learning
42mCost-effective Simulation-based Test Selection in Self-driving Cars SW
19mTestbed for Development of AI Solutions to Boost Operational Efficiency in Transportation Networks