ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910876127199232 |
|---|---|
| author | Ferlez, James Elnaggar, Mahmoud Shoukry, Yasser Fleming, Cody |
| author_facet | Ferlez, James Elnaggar, Mahmoud Shoukry, Yasser Fleming, Cody |
| contents | In this paper, we develop a novel closed-form Control Barrier Function (CBF) and associated controller shield for the Kinematic Bicycle Model (KBM) with respect to obstacle avoidance. The proposed CBF and shield -- designed by an algorithm we call ShieldNN -- provide two crucial advantages over existing methodologies. First, ShieldNN considers steering and velocity constraints directly with the non-affine KBM dynamics; this is in contrast to more general methods, which typically consider only affine dynamics and do not guarantee invariance properties under control constraints. Second, ShieldNN provides a closed-form set of safe controls for each state unlike more general methods, which typically rely on optimization algorithms to generate a single instantaneous for each state. Together, these advantages make ShieldNN uniquely suited as an efficient Multi-Obstacle Safe Actions (i.e. multiple-barrier-function shielding) during training time of a Reinforcement Learning (RL) enabled Neural Network controller. We show via experiments that ShieldNN dramatically increases the completion rate of RL training episodes in the presence of multiple obstacles, thus establishing the value of ShieldNN in training RL-based controllers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2006_09564 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers Ferlez, James Elnaggar, Mahmoud Shoukry, Yasser Fleming, Cody Robotics Machine Learning Systems and Control Optimization and Control In this paper, we develop a novel closed-form Control Barrier Function (CBF) and associated controller shield for the Kinematic Bicycle Model (KBM) with respect to obstacle avoidance. The proposed CBF and shield -- designed by an algorithm we call ShieldNN -- provide two crucial advantages over existing methodologies. First, ShieldNN considers steering and velocity constraints directly with the non-affine KBM dynamics; this is in contrast to more general methods, which typically consider only affine dynamics and do not guarantee invariance properties under control constraints. Second, ShieldNN provides a closed-form set of safe controls for each state unlike more general methods, which typically rely on optimization algorithms to generate a single instantaneous for each state. Together, these advantages make ShieldNN uniquely suited as an efficient Multi-Obstacle Safe Actions (i.e. multiple-barrier-function shielding) during training time of a Reinforcement Learning (RL) enabled Neural Network controller. We show via experiments that ShieldNN dramatically increases the completion rate of RL training episodes in the presence of multiple obstacles, thus establishing the value of ShieldNN in training RL-based controllers. |
| title | ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers |
| topic | Robotics Machine Learning Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2006.09564 |