How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914839533715456 |
|---|---|
| author | Mao, Zhenjiang Sobolewski, Carson Ruchkin, Ivan |
| author_facet | Mao, Zhenjiang Sobolewski, Carson Ruchkin, Ivan |
| contents | End-to-end learning has emerged as a major paradigm for developing autonomous systems. Unfortunately, with its performance and convenience comes an even greater challenge of safety assurance. A key factor of this challenge is the absence of the notion of a low-dimensional and interpretable dynamical state, around which traditional assurance methods revolve. Focusing on the online safety prediction problem, this paper proposes a configurable family of learning pipelines based on generative world models, which do not require low-dimensional states. To implement these pipelines, we overcome the challenges of learning safety-informed latent representations and missing safety labels under prediction-induced distribution shift. These pipelines come with statistical calibration guarantees on their safety chance predictions based on conformal prediction. We perform an extensive evaluation of the proposed learning pipelines on two case studies of image-controlled systems: a racing car and a cartpole. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_12252 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy Mao, Zhenjiang Sobolewski, Carson Ruchkin, Ivan Machine Learning End-to-end learning has emerged as a major paradigm for developing autonomous systems. Unfortunately, with its performance and convenience comes an even greater challenge of safety assurance. A key factor of this challenge is the absence of the notion of a low-dimensional and interpretable dynamical state, around which traditional assurance methods revolve. Focusing on the online safety prediction problem, this paper proposes a configurable family of learning pipelines based on generative world models, which do not require low-dimensional states. To implement these pipelines, we overcome the challenges of learning safety-informed latent representations and missing safety labels under prediction-induced distribution shift. These pipelines come with statistical calibration guarantees on their safety chance predictions based on conformal prediction. We perform an extensive evaluation of the proposed learning pipelines on two case studies of image-controlled systems: a racing car and a cartpole. |
| title | How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2308.12252 |