$\texttt{immrax}$: A Parallelizable and Differentiable Toolbox for Interval Analysis and Mixed Monotone Reachability in JAX
This provides a practical tool for researchers and engineers working on verification and control problems in AI and robotics, though it is incremental as it builds on existing interval analysis methods by integrating them with JAX.
The authors developed a parallelizable and differentiable toolbox for interval analysis and mixed monotone reachability in JAX, enabling efficient computation with GPU acceleration and automatic differentiation, and demonstrated its performance on case studies like a neural network-controlled vehicle model and a swinging pendulum control problem.
We present an implementation of interval analysis and mixed monotone interval reachability analysis as function transforms in Python, fully composable with the computational framework JAX. The resulting toolbox inherits several key features from JAX, including computational efficiency through Just-In-Time Compilation, GPU acceleration for quick parallelized computations, and Automatic Differentiability. We demonstrate the toolbox's performance on several case studies, including a reachability problem on a vehicle model controlled by a neural network, and a robust closed-loop optimal control problem for a swinging pendulum.