Advanced capabilities planned for the next generation of autonomous unmanned vehicles will be based on non-traditional software components containing complex machine learning algorithms.

AdvoCATE (Assurance Case Automation Toolset) supports the development and management of safety/assurance cases, providing novel capabilities in automating their creation and, more broadly, organizing project assurance activities.

The Assurance-based Learning-enabled Cyber-Physical Systems (ALC) toolchain is an integrated set of tools and corresponding workflows specifically tailored for the model-based

AlphaZero.jl is a generic implementation of DeepMind's algorithm written in Julia. It is consistently 20x to 100x faster than existing Python implementations while being equally simple and flexible.

CoPilot is a domain-specific, embedded-stream language for generating hard real-time C code for monitors. Copilot is a runtime verification framework written in Haskell.

Control Systems Analysis Framework (CSAF) is a framework to minimize the effort required to evaluate, implement, and verify controller design (classical and learning enabled) with respect to the system dynamics.

We investigate the problem of data-driven, on-the-fly control of systems with unknown nonlinear dynamics wheredata from only a single finite-horizon trajectory and possibly side information on the dynamics are available.

We propose an efficient new method for training neural networks in reinforcement learning tasks.

Real world navigation requires robots to operate in unfamiliar, dynamic environments, sharing spaces with humans.

Self-driving cars, autonomous robots, modern airplanes, or robotic surgery: we increasingly entrust our lives to computers and should therefore strive for highest safety standards - mathematical correctness proof.