Related papers: Bridging Dimensions: Confident Reachability for Hi…
A control system consists of a plant component and a controller which periodically computes a control input for the plant. We consider systems where the controller is implemented by a feedforward neural network with ReLU activations. The…
Deep neural networks are increasingly being used as controllers for safety-critical systems. Because neural networks are opaque, certifying their correctness is a significant challenge. To address this issue, several neural network…
The arising application of neural networks (NN) in robotic systems has driven the development of safety verification methods for neural network dynamical systems (NNDS). Recursive techniques for reachability analysis of dynamical systems in…
While tactile sensor technology has made great strides over the past decades, applications in robotic manipulation are limited by aspects such as blind spots, difficult integration into hands, and low spatial resolution. We present a method…
Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space are finite,…
This paper deals with the problem of point-to-point reachability in multi-linear systems. These systems consist of a partition of the Euclidean space into a finite number of regions and a constant derivative assigned to each region in the…
We present a two-stage framework that integrates a learning-based estimator and a controller, designed to address contact-intensive tasks. The estimator leverages a Bayesian particle filter with a mixture density network (MDN) structure,…
Robotic in-hand manipulation has been a long-standing challenge due to the complexity of modelling hand and object in contact and of coordinating finger motion for complex manipulation sequences. To address these challenges, the majority of…
The use of separable approximations is proposed to mitigate the curse of dimensionality related to the approximation of high-dimensional value functions in optimal control. The separable approximation exploits intrinsic decaying sensitivity…
We want to build robots that are useful in unstructured real world applications, such as doing work in the household. Grasping in particular is an important skill in this domain, yet it remains a challenge. One of the key hurdles is…
Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, with the resulting neural approximations enabling verification and control of such systems. However, in safety-critical contexts, the use of…
Hyperdimensional (HD) computing is built upon its unique data type referred to as hypervectors. The dimension of these hypervectors is typically in the range of tens of thousands. Proposed to solve cognitive tasks, HD computing aims at…
The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…
The intrinsic complexity of deep neural networks (DNNs) makes it challenging to verify not only the networks themselves but also the hosting DNN-controlled systems. Reachability analysis of these systems faces the same challenge. Existing…
In recent years, both reinforcement learning and learning-based control -- as well as the study of their safety, which is crucial for deployment in real-world robots -- have gained significant traction. However, to adequately gauge the…
There have been attempts in reinforcement learning to exploit a priori knowledge about the structure of the system. This paper proposes a hybrid reinforcement learning controller which dynamically interpolates a model-based linear…
The rapid advancement of Large Language Models (LLMs) has created a critical gap in consumer protection due to the lack of standardized certification processes for LLM-powered Artificial Intelligence (AI) systems. This paper argues that…
In this work, we analyze an efficient sampling-based algorithm for general-purpose reachability analysis, which remains a notoriously challenging problem with applications ranging from neural network verification to safety analysis of…
We propose a new reachability learning framework for high-dimensional nonlinear systems, focusing on reach-avoid problems. These problems require computing the reach-avoid set, which ensures that all its elements can safely reach a target…
Learning-based methods for synthesizing controllers have gained popularity due to their high expressiveness and strong empirical performance. However, in safety-critical scenarios such as autonomous driving, robotics, and power systems,…