Safe Pontryagin Differentiable Programming (Safe PDP) is a new theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks.
-
Updated
Jul 23, 2022 - Python
Safe Pontryagin Differentiable Programming (Safe PDP) is a new theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks.
Safety Critical Control of Autonomous Vehicles by Control Barrier Functions
Implementation of the Heatmap-based Unsupervised Debugging of DNNs (HUDD) toolset
Code for L4DC 2022 paper: Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning.
ICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
On the forward invariance of Neural ODEs: performance guarantees for policy learning
Safe robot learning
Add a description, image, and links to the safety-critical-systems topic page so that developers can more easily learn about it.
To associate your repository with the safety-critical-systems topic, visit your repo's landing page and select "manage topics."