Synthetic Data Generation for Minimum-Exposure Navigation in a Time-Varying Environment using Generative AI Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915189462401024 |
|---|---|
| author | Bapat, Nachiket U. Paffenroth, Randy C. Cowlagi, Raghvendra V. |
| author_facet | Bapat, Nachiket U. Paffenroth, Randy C. Cowlagi, Raghvendra V. |
| contents | We study the problem of synthetic generation of samples of environmental features for autonomous vehicle navigation. These features are described by a spatiotemporally varying scalar field that we refer to as a threat field. The threat field is known to have some underlying dynamics subject to process noise. Some "real-world" data of observations of various threat fields are also available. The assumption is that the volume of ``real-world'' data is relatively small. The objective is to synthesize samples that are statistically similar to the data. The proposed solution is a generative artificial intelligence model that we refer to as a split variational recurrent neural network (S-VRNN). The S-VRNN merges the capabilities of a variational autoencoder, which is a widely used generative model, and a recurrent neural network, which is used to learn temporal dependencies in data. The main innovation in this work is that we split the latent space of the S-VRNN into two subspaces. The latent variables in one subspace are learned using the ``real-world'' data, whereas those in the other subspace are learned using the data as well as the known underlying system dynamics. Through numerical experiments we demonstrate that the proposed S-VRNN can synthesize data that are statistically similar to the training data even in the case of very small volume of ``real-world'' training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06619 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Synthetic Data Generation for Minimum-Exposure Navigation in a Time-Varying Environment using Generative AI Models Bapat, Nachiket U. Paffenroth, Randy C. Cowlagi, Raghvendra V. Machine Learning Systems and Control We study the problem of synthetic generation of samples of environmental features for autonomous vehicle navigation. These features are described by a spatiotemporally varying scalar field that we refer to as a threat field. The threat field is known to have some underlying dynamics subject to process noise. Some "real-world" data of observations of various threat fields are also available. The assumption is that the volume of ``real-world'' data is relatively small. The objective is to synthesize samples that are statistically similar to the data. The proposed solution is a generative artificial intelligence model that we refer to as a split variational recurrent neural network (S-VRNN). The S-VRNN merges the capabilities of a variational autoencoder, which is a widely used generative model, and a recurrent neural network, which is used to learn temporal dependencies in data. The main innovation in this work is that we split the latent space of the S-VRNN into two subspaces. The latent variables in one subspace are learned using the ``real-world'' data, whereas those in the other subspace are learned using the data as well as the known underlying system dynamics. Through numerical experiments we demonstrate that the proposed S-VRNN can synthesize data that are statistically similar to the training data even in the case of very small volume of ``real-world'' training data. |
| title | Synthetic Data Generation for Minimum-Exposure Navigation in a Time-Varying Environment using Generative AI Models |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2503.06619 |