Safe, real-time active model discrimination and fault diagnosis for nonlinear systems via differentiable reachability
X. Ni, M. Ornik, G. Chou, S. Coogan
IEEE Robotics and Automation Letters, 2026
Abstract
We present a safe, real-time algorithm for active fault diagnosis and model discrimination for uncertain continuous-time nonlinear systems with process and measurement disturbances. Given a finite set of candidate models representing nominal and faulty modes, including actuator and sensor faults, we formulate an output-feedback, time-varying policy optimization problem that (i) handles state-input safety constraints over a finite horizon and (ii) drives the system to produce sampled measurements consistent with at most one model, enabling sound diagnosis. To solve this problem in real time, we develop a tractable approximation using interval overapproximations of reachable state and output sets, and encode diagnosability via a differentiable objective that penalizes overlap between the reachable output sets of possible models. The resulting optimization is solved efficiently online with gradient-based methods using JAX and differentiable reachability primitives. We evaluate our method on sensor and actuator fault diagnosis (up to 11 candidate models) in several nonlinear robotic systems, including a simulated aircraft, a hardware differential-drive robot, quadrupedal navigation, and a simulated quadrotor. Across these case studies, our approach identifies a model discriminating input sequence in under 50 ms, outperforming baselines in discrimination success rate and speed while providing formal soundness guarantees.