safety-critical

List of resources about programming practices for writing safety-critical software.

JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

µC/OS-II is a preemptive, highly portable, and scalable real-time kernels. Designed for ease of use on a huge number of CPU architectures.

This repository provides a design methodology and approach to building highly-reliable applications on Microsoft Azure for mission-critical workloads.

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

Constant-complexity, deterministic, very fast memory allocator (heap) for hard real-time high-integrity embedded systems. Allocation takes ≈165 cycles on Cortex M4. There is little activity because the project is finished and does not require further changes.

Matlab Interface for Control Barrier Function (CBF) and Control Lyapunov Function (CLF) based control methods.

Replacements to standard numeric types which throw exceptions on errors

🚀 A fast safe reinforcement learning library in PyTorch

Safety-critical controllers for single/multi robotic navigation: CBF-QP, MPC-CBF, and etc.

A mixed-criticality platform built around Cheshire, with a number of safety/security and predictability features. Ready-to-use FPGA flow on multiple boards is available.

Fast and flexible data logging/tracing toolkit for software testing and debugging. Minimally intrusive C/C++ code instrumentation, host-based decoding application, demo code included.

[ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

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.

The Verifiably Safe Reinforcement Learning Framework

Bourne shell, template engine, scripting language reliable, scalable projects. Based a ISO standard proven effective for large, mission-critical projects, SparForte is designed for fast development while, at the same time, providing easier designing, maintenance and bug removal. About 130.000 lines of code.

A list of papers that studies out-of-distribution (OOD) detection and misclassification detection (MisD)

Repository containing the code for safe reinforcement learning in two custom environments

🚗 A repository for documenting and exploring the world of autonomous driving safety, featuring a curated collection of research papers, reports, and resource.

Implementation of the Online Adaptive CBF for safety-critical navigation for input constrained systems.