System-level Safety Guard: Safe Tracking Control through Uncertain Neural Network Dynamics Models
This work addresses safety-critical deployment challenges for neural networks in robotics and control, though it appears incremental as it builds on existing MILP methods for safety verification.
The paper tackles the problem of ensuring safety in control systems using uncertain neural network dynamics models by formulating a constrained trajectory tracking problem and solving it with Mixed-integer Linear Programming, demonstrating its effectiveness in robot navigation and obstacle avoidance simulations.
The Neural Network (NN), as a black-box function approximator, has been considered in many control and robotics applications. However, difficulties in verifying the overall system safety in the presence of uncertainties hinder the deployment of NN modules in safety-critical systems. In this paper, we leverage the NNs as predictive models for trajectory tracking of unknown dynamical systems. We consider controller design in the presence of both intrinsic uncertainty and uncertainties from other system modules. In this setting, we formulate the constrained trajectory tracking problem and show that it can be solved using Mixed-integer Linear Programming (MILP). The proposed MILP-based approach is empirically demonstrated in robot navigation and obstacle avoidance through simulations. The demonstration videos are available at https://xiaolisean.github.io/publication/2023-11-01-L4DC2024.