A Universal Framework for Generalized Run Time Assurance with JAX Automatic Differentiation

With the rise of increasingly complex autonomous systems powered by black box AI models, there is a growing need for Run Time Assurance (RTA) systems that provide online safety filtering to untrusted primary controller output. Currently, research in RTA tends to be ad hoc and inflexible, diminishing collaboration and the pace of innovation. The Safe Autonomy Run Time Assurance Framework presented in this paper provides a standardized interface for modular RTA building blocks and a set of universal implementations of constraint-based RTA modules. By leveraging JAX Automatic Differentiation, a technique popularized by deep learning, this framework provides unmatched flexibility in the RTA space by automatically populating advanced optimization based RTA methods from user defined constraints and dynamics. This eliminates tedious manual differentiation and minimizes user effort and error. To validate the feasibility of this framework, a simulation of a multi-agent spacecraft inspection problem is shown with differentiable safety constraints on position and velocity.