Search Results for author:
Found 10 papers, 0 papers with code
Data-informativity conditions for structured linear systems with implications for dynamic networks
When estimating a single module in a linear dynamic network, the data-informativity conditions can generically be formulated as path-based conditions on the graph of the network.
State-action control barrier functions: Imposing safety on learning-based control with low online computational costs
Learning-based control with safety guarantees usually requires real-time safety certification and modifications of possibly unsafe learning-based policies.
Regret Analysis of Learning-Based Linear Quadratic Gaussian Control with Additive Exploration
In this paper, we analyze the regret incurred by a computationally efficient exploration strategy, known as naive exploration, for controlling unknown partially observable systems within the Linear Quadratic Gaussian (LQG) framework.
A Behavioral Perspective on Models of Linear Dynamical Networks with Manifest Variables
This work makes an initial step towards addressing the above issues by taking a behavioral perspective, where input and output channels are not pre-determined.
Approximate Dynamic Programming for Constrained Piecewise Affine Systems with Stability and Safety Guarantees
Infinite-horizon optimal control of constrained piecewise affine (PWA) systems has been approximately addressed by hybrid model predictive control (MPC), which, however, has computational limitations, both in offline design and online implementation.
Suboptimality analysis of receding horizon quadratic control with unknown linear systems and its applications in learning-based control
In this work, we aim to analyze how the trade-off between the modeling error, the terminal value function error, and the prediction horizon affects the performance of a nominal receding-horizon linear quadratic (LQ) controller.
Approximate Dynamic Programming for Constrained Linear Systems: A Piecewise Quadratic Approximation Approach
A novel convex and piecewise quadratic neural network with a local-global architecture is proposed to provide an accurate approximation of the value function, which is used as the cost-to-go function in the online dynamic programming problem.
Finite-sample analysis of identification of switched linear systems with arbitrary or restricted switching
To capture the effect of the parameters of the switching strategies on the LS estimation error, finite-sample error bounds are developed in this work.
Single module identifiability in linear dynamic networks with partial excitation and measurement
Depending on whether the input or the output of the module can be measured, we present four identifiability conditions which cover all possible situations in single module identification.
Generic identifiability of subnetworks in a linear dynamic network: the full measurement case
Conditions for generic identifiability of multiple modules, i. e. a subnetwork, are developed for the situation that all node signals are measured and excitation of the network is provided by both measured excitation signals and unmeasured disturbance inputs.
