Recent Development and Applications of SUMO - Simulation of Urban MObility

By Daniel Krajzewicz, Jakob Erdmann, Michael Behrisch, Laura Bieker. 2012

2,342 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Ziyang Tang
2. Qiang Liu
3. Lihong Li
4. Cathy Wu
5. Nathan Kallus
6. Dengyong Zhou
7. Sergey Levine
8. Eugene Vinitsky

Citations in the corpus

• Selective Experience Replay for Lifelong Learning (2018, background): “The Sumo simulator (Krajzewicz et al. 2012) allows for the creation of a variety of different driving tasks with varying levels of difficulty, many of which benefit from transfer while being sufficiently different that adaptation is necessary for good performance (Isele and Cosgun 2017).”
• Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation (2018, background): “SUMO Traffic Simulator SUMO [15] is an open source traffic simulator; see Figure 4(a) for an illustration.”
• Coordinated Deep Reinforcement Learners for Traffic Light Control (2016, methodology): “To evaluate the effectiveness of the approach, we use SUMO [7], an open source traffic simulator.”
• Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles (2020, background): “In modeling the traffic environment, the most popular choice is SUMO (Simulation of Urban MObility), which is a microscopic, inter-and multi-modal, space-continuous and time-discrete traffic flow simulation platform [29].”
• Flow: A Modular Learning Framework for Mixed Autonomy Traffic (2017, methodology): “The implementation builds upon SUMO ( S imulation of U rban MO bility) [102] for traffic modeling, Ray RLlib [103] for RL methods, and OpenAI gym [101] for the MDP interface.”
• A Deep Reinforcement Learning Network for Traffic Light Cycle Control (2018, background): “The proposed model also outperforms others in learning speed, which is shown in extensive simulation in SUMO and TensorFlow.”
• Using a Deep Reinforcement Learning Agent for Traffic Signal Control (2016, unknown): “22 [22].”
• A Survey on Recent Advances in Vehicular Network Security, Trust, and Privacy (2019, methodology): “Second, it has a remote control interface to efficiently simulate single junctions and whole cities [116].”
• Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control (2017, methodology): “The first of those open-source tools is SUMO ( S imulation of U rban MO bility) [43].”
• Multi-Agent Reinforcement Learning: A Review of Challenges and Applications (2021, methodology): “The algorithm was tested in an open-source traffic simulator SUMO [63], showing promising results, particularly in a low-traffic setting.”
• V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving (2022, methodology): “To generate V2X-Sim, we employ SUMO [16], a micro-traffic simulation, to produce numerically-realistic traffic flow, and CARLA [17], a widely-used open-source simulator for autonomous driving research, to retrieve well-synchronized sensor streams from multiple vehicles as well as the road-side unit…”
• LTE and IEEE 802.11p for vehicular networking: a performance evaluation (2014, methodology): “The vehicles' routes and movement patterns are generated using the SUMO tool [39].”
• Transferring Autonomous Driving Knowledge on Simulated and Real Intersections (2017, methodology): “Experiments were run using the Sumo simulator (Krajzewicz et al., 2012), which is an open source traffic simulation package.”
• Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learning (2017, methodology): “We have used the SUMO [42] tool to simulate traffic in all experiments.”
• VANET via Named Data Networking (2014, methodology): “The cars mobility is generated using SUMO [11].”
• Learning Distilled Collaboration Graph for Multi-Agent Perception (2021, methodology): “4.1 V2X-Sim 1.0: A multi-agent 3D object detection dataset Since there is no public dataset to support the research on multi-agent 3D object detection in selfdriving scenarios, we build such a dataset named as V2X-Sim 1.02, based on both SUMO [15], a micro-traffic simulation, and CARLA [6], a widely”
• Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps (2022, methodology): “V2X-Sim [9] is a vehicle-to-everything collaborative perception dataset, co-simulated by SUMO [32] and Carla, including 10K frames of 3D LiDAR point clouds and 501K 3D boxes.”
• Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control (2019, background): “Result: V. MA2C FOR T RAFFIC S IGNAL C ONTROL This section describes the implementation details of MA2C for ATSC, under the microscopic traffic simulator SUMO [41].”
• Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends (2020, background): “Recent efforts to introduce similar capabilities within transportation can be seen in frameworks such as Flow [103], which attempts to integrate various environments such as SUMO [55] (Simulation of Urban MObility).”
• AVE: Autonomous Vehicular Edge Computing Framework with ACO-Based Scheduling (2017, methodology): “1) Simulation Tools and Traffic Simulation: To better emulate real traffic, we used Simulation of Urban MObility (SUMO)[30] as the traffic simulator.”