paper-with-me

Papers

Reachability Analysis for Black-Box Dynamical Systems

2024-10-10 · Vamsi Krishna Chilakamarri, Zeyuan Feng, Somil Bansal

Hamilton-Jacobi (HJ) reachability analysis is a powerful framework for ensuring safety and performance in autonomous systems. However, existing methods typically rely on a white-box dynamics model of the system, limiting their applicability in many practical robotics scenarios where only a black-box model of the system is available. In this work, we propose a novel reachability method to compute reachable sets and safe controllers for black-box dynamical systems. Our approach efficiently approximates the Hamiltonian function using samples from the black-box dynamics. This Hamiltonian is then used to solve the HJ Partial Differential Equation (PDE), providing the reachable set of the system. The proposed method can be applied to general nonlinear systems and can be seamlessly integrated with existing reachability toolboxes for white-box systems to extend their use to black-box systems. Through simulation studies on a black-box slip-wheel car and a quadruped robot, we demonstrate the effectiveness of our approach in accurately obtaining the reachable sets for black?box dynamical systems.

📄 PDF Abstract BibTeX arXiv:2410.07796

Code (1)

sia-lab-git/blackbox_reachability 공식 구현 jax

Methods 이 논문이 사용한 방법론

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

Similar Papers 제목 키워드 기반

Reachability of Black-Box Nonlinear Systems after Koopman Operator Linearization

2021-05-03 · Stanley Bak, Sergiy Bogomolov, Parasara Sridhar Duggirala, Adam R. Gerlach 외

Reachability analysis of nonlinear dynamical systems is a challenging and computationally expensive task. Computing the reachable states for linear systems, in contrast, can often be done efficiently in high dimensions. …

One-Shot Reachability Analysis of Neural Network Dynamical Systems

2022-09-23 · Shaoru Chen, Victor M. Preciado, Mahyar Fazlyab

The arising application of neural networks (NN) in robotic systems has driven the development of safety verification methods for neural network dynamical systems (NNDS). Recursive techniques for reachability analysis of …

Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training

2022-11-21 · Jiaxu Tian, Dapeng Zhi, Si Liu, Peixin Wang 외

The intrinsic complexity of deep neural networks (DNNs) makes it challenging to verify not only the networks themselves but also the hosting DNN-controlled systems. Reachability analysis of these systems faces the same c…

Decision MakingReinforcement Learning (RL)

Deep QP Safety Filter: Model-free Learning for Reachability-based Safety Filter

2026-01-29 · Byeongjun Kim, H. Jin Kim arxiv

We introduce Deep QP Safety Filter, a fully data-driven safety layer for black-box dynamical systems. Our method learns a Quadratic-Program (QP) safety filter without model knowledge by combining Hamilton-Jacobi (HJ) rea…

Data-Driven Reachability Analysis of Stochastic Dynamical Systems with Conformal Inference

2023-09-17 · Navid Hashemi, Xin Qin, Lars Lindemann, Jyotirmoy V. Deshmukh

We consider data-driven reachability analysis of discrete-time stochastic dynamical systems using conformal inference. We assume that we are not provided with a symbolic representation of the stochastic system, but inste…