Related papers: Safe Reach Set Computation via Neural Barrier Cert…
Achieving safe autonomous navigation systems is critical for deploying robots in dynamic and uncertain real-world environments. In this paper, we propose a hierarchical control framework leveraging neural network verification techniques to…
Learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics, but this performance comes at the cost of reduced transparency and lack of guarantees on the safety or…
In this work, we propose a data-driven scheme within a compositional framework with noisy data to design robust safety controllers in a fully decentralized fashion for large-scale interconnected networks with unknown mathematical dynamics.…
Complex dynamical systems rely on the correct deployment and operation of numerous components, with state-of-the-art methods relying on learning-enabled components in various stages of modeling, sensing, and control at both offline and…
Ensuring the functional safety of motion planning modules in autonomous vehicles remains a critical challenge, especially when dealing with complex or learning-based software. Online verification has emerged as a promising approach to…
A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic…
Cyber-physical systems can be subject to sensor attacks, e.g., sensor spoofing, leading to unsafe behaviors. This paper addresses this problem in the context of linear systems when an omniscient attacker can spoof several system sensors at…
Existing machine learning-based surrogate modeling methods for transient stability constrained-optimal power flow (TSC-OPF) lack certifications in the presence of unseen disturbances or uncertainties. This may lead to divergence of TSC-OPF…
Challenges related to automated driving are no longer focused on just the construction of such automated vehicles (AVs), but in assuring the safety of their operation. Recent advances in Level 3 and Level 4 autonomous driving have motivated…
In this paper, we investigate the problem of verifying the finite-time safety of continuous-time perturbed deterministic systems represented by ordinary differential equations in the presence of measurable disturbances. Given a finite-time…
As the use of autonomous robots expands in tasks that are complex and challenging to model, the demand for robust data-driven control methods that can certify safety and stability in uncertain conditions is increasing. However, the…
Safety in terms of collision avoidance for multi-robot systems is a difficult challenge under uncertainty, non-determinism and lack of complete information. This paper aims to propose a collision avoidance method that accounts for both…
The control of complex systems faces a trade-off between high performance and safety guarantees, which in particular restricts the application of learning-based methods to safety-critical systems. A recently proposed framework to address…
Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits - minimal subnetworks responsible for specific…
This paper addresses the challenge of integrating explicit hard constraints into the control barrier function (CBF) framework for ensuring safety in autonomous systems, including robots. We propose a novel data-driven method to derive CBFs…
A biometric recognition system can operate in two distinct modes: identification or verification. In the first mode, the system recognizes an individual by searching the enrolled templates of all the users for a match. In the second mode,…
Safe motion planning algorithms are necessary for deploying autonomous robots in unstructured environments. Motion plans must be safe to ensure that the robot does not harm humans or damage any nearby objects. Generating these motion plans…
Motivated by the fragility of neural network (NN) controllers in safety-critical applications, we present a data-driven framework for verifying the risk of stochastic dynamical systems with NN controllers. Given a stochastic control system,…
This paper presents four theoretical contributions that improve the usability of risk certificates for neural networks based on PAC-Bayes bounds. First, two bounds on the KL divergence between Bernoulli distributions enable the derivation…
In this paper, we propose a novel framework for approximating the explicit MPC law for linear parameter-varying systems using supervised learning. In contrast to most existing approaches, we not only learn the control policy, but also a…