paper-with-me

홈 › Papers

Certifiable Reachability Learning Using a New Lipschitz Continuous Value Function

2024-08-15 · Jingqi Li, Donggun Lee, Jaewon Lee, Kris Shengjun Dong, Somayeh Sojoudi, Claire Tomlin

We propose a new reachability learning framework for high-dimensional nonlinear systems, focusing on reach-avoid problems. These problems require computing the reach-avoid set, which ensures that all its elements can safely reach a target set despite disturbances within pre-specified bounds. Our framework has two main parts: offline learning of a newly designed reachavoid value function, and post-learning certification. Compared to prior work, our new value function is Lipschitz continuous and its associated Bellman operator is a contraction mapping, both of which improve the learning performance. To ensure deterministic guarantees of our learned reach-avoid set, we introduce two efficient post-learning certification methods. Both methods can be used online for real-time local certification or offline for comprehensive certification. We validate our framework in a 12-dimensional crazyflie drone racing hardware experiment and a simulated 10-dimensional highway take-over example.

📄 PDF Abstract BibTeX arXiv:2408.07866

Code (1)

jamesjingqili/Lipschitz_Continuous_Reachability_Learning 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Reachability Analysis of Deep Neural Networks with Provable Guarantees

2018-05-06 · Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska

Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over …

How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints

2025-11-23 · Kensuke Nakamura, Arun L. Bishop, Steven Man, Aaron M. Johnson 외 arxiv

Latent safety filters extend Hamilton-Jacobi (HJ) reachability to operate on latent state representations and dynamics learned directly from high-dimensional observations, enabling safe visuomotor control under hard-to-m…

Reinforcement Learning

ReachNN: Reachability Analysis of Neural-Network Controlled Systems

2019-06-25 · Chao Huang, Jiameng Fan, Wenchao Li, Xin Chen 외

Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neural-network controllers in the loop. Pre…

Lipschitz-Certifiable Training with a Tight Outer Bound

2020-12-01 · NeurIPS 2020 12 · Sungyoon Lee, Jaewook Lee, Saerom Park

Verifiable training is a promising research direction for training a robust network. However, most verifiable training methods are slow or lack scalability. In this study, we propose a fast and scalable certifiable train…

1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness

2023-11-28 · Bernd Prach, Fabio Brau, Giorgio Buttazzo, Christoph H. Lampert

The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems. Recently, the scientific community h…