Data-Driven Traffic Simulation for an Intersection in a Metropolis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917739537367040 |
|---|---|
| author | Zang, Chengbo Turkcan, Mehmet Kerem Zussman, Gil Ghaderi, Javad Kostic, Zoran |
| author_facet | Zang, Chengbo Turkcan, Mehmet Kerem Zussman, Gil Ghaderi, Javad Kostic, Zoran |
| contents | We present a novel data-driven simulation environment for modeling traffic in metropolitan street intersections. Using real-world tracking data collected over an extended period of time, we train trajectory forecasting models to learn agent interactions and environmental constraints that are difficult to capture conventionally. Trajectories of new agents are first coarsely generated by sampling from the spatial and temporal generative distributions, then refined using state-of-the-art trajectory forecasting models. The simulation can run either autonomously, or under explicit human control conditioned on the generative distributions. We present the experiments for a variety of model configurations. Under an iterative prediction scheme, the way-point-supervised TrajNet++ model obtained 0.36 Final Displacement Error (FDE) in 20 FPS on an NVIDIA A100 GPU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00943 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data-Driven Traffic Simulation for an Intersection in a Metropolis Zang, Chengbo Turkcan, Mehmet Kerem Zussman, Gil Ghaderi, Javad Kostic, Zoran Computer Vision and Pattern Recognition We present a novel data-driven simulation environment for modeling traffic in metropolitan street intersections. Using real-world tracking data collected over an extended period of time, we train trajectory forecasting models to learn agent interactions and environmental constraints that are difficult to capture conventionally. Trajectories of new agents are first coarsely generated by sampling from the spatial and temporal generative distributions, then refined using state-of-the-art trajectory forecasting models. The simulation can run either autonomously, or under explicit human control conditioned on the generative distributions. We present the experiments for a variety of model configurations. Under an iterative prediction scheme, the way-point-supervised TrajNet++ model obtained 0.36 Final Displacement Error (FDE) in 20 FPS on an NVIDIA A100 GPU. |
| title | Data-Driven Traffic Simulation for an Intersection in a Metropolis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.00943 |