Incorporating System-level Safety Requirements in Perception Models via Reinforcement Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915047736868864 |
|---|---|
| author | Fan, Weisi Lane, Jesse Liu, Qisai Sarkar, Soumik Wongpiromsarn, Tichakorn |
| author_facet | Fan, Weisi Lane, Jesse Liu, Qisai Sarkar, Soumik Wongpiromsarn, Tichakorn |
| contents | Perception components in autonomous systems are often developed and optimized independently of downstream decision-making and control components, relying on established performance metrics like accuracy, precision, and recall. Traditional loss functions, such as cross-entropy loss and negative log-likelihood, focus on reducing misclassification errors but fail to consider their impact on system-level safety, overlooking the varying severities of system-level failures caused by these errors. To address this limitation, we propose a novel training paradigm that augments the perception component with an understanding of system-level safety objectives. Central to our approach is the translation of system-level safety requirements, formally specified using the rulebook formalism, into safety scores. These scores are then incorporated into the reward function of a reinforcement learning framework for fine-tuning perception models with system-level safety objectives. Simulation results demonstrate that models trained with this approach outperform baseline perception models in terms of system-level safety. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02951 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Incorporating System-level Safety Requirements in Perception Models via Reinforcement Learning Fan, Weisi Lane, Jesse Liu, Qisai Sarkar, Soumik Wongpiromsarn, Tichakorn Robotics Machine Learning Perception components in autonomous systems are often developed and optimized independently of downstream decision-making and control components, relying on established performance metrics like accuracy, precision, and recall. Traditional loss functions, such as cross-entropy loss and negative log-likelihood, focus on reducing misclassification errors but fail to consider their impact on system-level safety, overlooking the varying severities of system-level failures caused by these errors. To address this limitation, we propose a novel training paradigm that augments the perception component with an understanding of system-level safety objectives. Central to our approach is the translation of system-level safety requirements, formally specified using the rulebook formalism, into safety scores. These scores are then incorporated into the reward function of a reinforcement learning framework for fine-tuning perception models with system-level safety objectives. Simulation results demonstrate that models trained with this approach outperform baseline perception models in terms of system-level safety. |
| title | Incorporating System-level Safety Requirements in Perception Models via Reinforcement Learning |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2412.02951 |