Microscopic Traffic Simulation using SUMO
By Pablo Álvarez López, Michael Behrisch, Laura Bieker-Walz, Jakob Erdmann, Y. Flötteröd, Robert Hilbrich, L. Lücken, Johannes Rummel, Peter Wagner, Evamarie WieBner. 2018
3,209 citations recorded by the source corpus.
Microscopic traffic simulation is an invaluable tool for traffic research. In recent years, both the scope of research and the capabilities of the tools have been extended considerably. This article presents the latest developments concerning intermodal traffic solutions, simulator coupling and model development and validation on the example of the open source traffic simulator SUMO.
Subfields: Control and Systems Engineering, Electrical and Electronic Engineering, Transportation, Robotics & Control
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Control and Systems Engineering
In Electrical and Electronic Engineering
In Transportation
In Robotics & Control
- Ibrahim Sobh
- Patrick Pérez
- Sergio Casas
- Odinaldo Rodrigues
- Michael Luck
- Nathan Gavenski
- Raquel Urtasun
- Senthil Kumar Yogamani
Citations in the corpus
- The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models (2022, methodology): “We use the Flow traffic simulator, implemented by Wu et al. (2021) and Vinitsky et al. (2018), which extends the popular SUMO traffic simulator (Lopez et al., 2018).”
- Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, methodology): “Simulator Description CARLA [79] Urban simulator, Camera & LIDAR streams, with depth & semantic segmentation, Location information TORCS [103] Racing Simulator, Camera stream, agent positions, testing control policies for vehicles AIRSIM [104] Camera stream with depth and semantic segmentation, supp”
- CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario (2019, methodology): “Unlike SUMO [7], we use ballistic position update rule instead of Euler position update.”
- MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning (2021, background): “…[10] SUMMIT [4] MACAD [34] GTA V [28] Highway-env [22] TORCS [57] Flow [55] CityFlow [60] Sim4CV [31] Duckietown [6] SMARTS [61] AIRSIM [47] SUMO [27] MADRaS [42] Udacity [53] DriverGym [20] DeepDrive [52] MetaDrive [54] are widely studied in single-agent RL tasks, and in multi-agent RL the…”
- TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors (2021, methodology): “Microscopic traffic simulators [30] employ heuristic-based models [39, 20, 25] to simulate traffic flow.”
- Dense reinforcement learning for safety validation of autonomous vehicles (2023, methodology): “To simulate the NDE, we developed a simulation platform based on an open-source traffic simulator SUMO.”
- Imitation Learning: A Survey of Learning Methods, Environments and Metrics (2024, neutral): “…easy to identify which episodes are near optimality in the CartPole environment [77] (where performance is considered optimal when the accumulated rewards match the number of steps), it is much more challenging to evaluate how ‘good’ an agent is in autonomous driving scenarios, such as SUMO [89].”
- Integrating Independent and Centralized Multi-agent Reinforcement Learning for Traffic Signal Network Optimization (2019, methodology): “We evaluated the performance of our method against a large set of baselines on multiple road networks under a variety of traffic conditions in the SUMO simulator [14, 25].”
- A Review of Safe Reinforcement Learning: Methods, Theories, and Applications (2024, neutral): “Restrictions apply.”
- A Review of Safe Reinforcement Learning: Methods, Theory and Applications (2022, methodology): “They use the transportation, SUMO [169], as a simulation platform and the real HighD data set [143] to verify the effectiveness of their methods.”
- A Survey of Imitation Learning Methods, Environments and Metrics (2024, background): “…be easy to identify which episodes are near optimality in the CartPole environment [9] (where performance is considered optimal when the accumulated rewards match the number of steps), it is much more challenging to evaluate how ‘good’ an agent is in autonomous driving scenarios, such as SUMO [60].”
- CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning (2018, methodology): “Built in the SUMO traffic simulator with fine sublane resolution [18], this experiment requires agent vehicles to learn double-merge maneuvers to reach goal lane assignments (Figure 4).”