Search Results for author:
Found 81 papers, 39 papers with code
Event-triggered Robust Model Predictive Control under Hard Computation Resource Constraints
Yet, this central computer typically serves multiple systems simultaneously, leading to significant hardware demands due to the need to solve numerous optimization problems concurrently.
On Rollouts in Model-Based Reinforcement Learning
Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it.
Safety in safe Bayesian optimization and its ramifications for control
A recurring and important task in control engineering is parameter tuning under constraints, which conceptually amounts to optimization of a blackbox function accessible only through noisy evaluations.
Lipschitz Safe Bayesian Optimization for Automotive Control
To obtain safety guarantees, many existing safe Bayesian optimization methods rely on assumptions that are hard to verify in practice.
Early Stopping Bayesian Optimization for Controller Tuning
Standard BO practice is to evaluate the closed-loop performance of parameters proposed during optimization on an episode with a fixed length.
CHEQ-ing the Box: Safe Variable Impedance Learning for Robotic Polishing
These results highlight the potential of adaptive hybrid RL for real-world, contact-rich tasks trained directly on hardware.
Bayesian Optimization via Continual Variational Last Layer Training
While Bayesian neural networks (BNNs) are a promising direction for higher capacity surrogate models, they have so far seen limited use due to poor performance on some problem types.
On Foundation Models for Dynamical Systems from Purely Synthetic Data
Our results demonstrate the feasibility of foundation models for dynamical systems that outperform specialist models in terms of generalization, data efficiency, and robustness.
Local Bayesian Optimization for Controller Tuning with Crash Constraints
Controller tuning is crucial for closed-loop performance but often involves manual adjustments.
Simulation-Aided Policy Tuning for Black-Box Robot Learning
At the core of the algorithm, a probabilistic model learns the dependence of the policy parameters and the robot learning objective not only by performing experiments on the robot, but also by leveraging data from a simulator.
Feedforward Controllers from Learned Dynamic Local Model Networks with Application to Excavator Assistance Functions
Instead, in a data-driven approach, recorded trajectories from the real system can be used to train local model networks (LMNs), for which feedforward controllers are derived via feedback linearization.
Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors
Combining Reinforcement Learning (RL) with a prior controller can yield the best out of two worlds: RL can solve complex nonlinear problems, while the control prior ensures safer exploration and speeds up training.
Combining Automated Optimisation of Hyperparameters and Reward Shape
We then propose a methodology for the combined optimisation of hyperparameters and the reward function.
On the Consistency of Kernel Methods with Dependent Observations
We propose the new notion of empirical weak convergence (EWC) as a general assumption explaining such phenomena for kernel methods.
Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption
This combination raises a critical question: 'When to trust your model?
Distributed Event-Based Learning via ADMM
We consider a distributed learning problem, where agents minimize a global objective function by exchanging information over a network.
Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining
By incorporating local sensitivities of nonlinear programs, the proposed method not only mimics optimal MPC inputs but also adjusts to known changes in physical parameters of the model using linear predictions while still guaranteeing stability.
On Safety in Safe Bayesian Optimization
To overcome this challenge, we introduce the Lipschitz-only Safe Bayesian Optimization (LoSBO) algorithm, which guarantees safety without an assumption on the RKHS bound, and empirically show that this algorithm is not only safe, but also exhibits superior performance compared to the state-of-the-art on several function classes.
Automatic nonlinear MPC approximation with closed-loop guarantees
We address this problem by presenting a novel algorithm that automatically computes an explicit approximation to nonlinear MPC schemes while retaining closed-loop guarantees.
Event-Triggered Safe Bayesian Optimization on Quadcopters
Utilizing standard safe BO strategies that do not address time-variations can result in failure as previous safe decisions may become unsafe over time, which we demonstrate herein.
Mean field limits for discrete-time dynamical systems via kernel mean embeddings
Mean field limits are an important tool in the context of large-scale dynamical systems, in particular, when studying multiagent and interacting particle systems.
Tracking Object Positions in Reinforcement Learning: A Metric for Keypoint Detection (extended version)
However, whether an SAE is actually able to track objects in the scene and thus yields a spatial state representation well suited for RL tasks has rarely been examined due to a lack of established metrics.
Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control
We find that in the case of trajectory control, the standard model-based RL formulation used in approaches like PETS-MPPI and MBPO is not suitable.
On kernel-based statistical learning in the mean field limit
In many applications of machine learning, a large number of variables are considered.
Learning Hybrid Dynamics Models With Simulator-Informed Latent States
In this paper, we propose a new approach to hybrid modeling, where we inform the latent states of a learned model via a black-box simulator.
Exact Inference for Continuous-Time Gaussian Process Dynamics
This is crucial to sample consistent predictions from the dynamics model.
Scale-Preserving Automatic Concept Extraction (SPACE)
Convolutional Neural Networks (CNN) have become a common choice for industrial quality control, as well as other critical applications in the Industry 4. 0.
Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations
Accurately predicting deformable linear object (DLO) dynamics is challenging, especially when the task requires a model that is both human-interpretable and computationally efficient.
Scalable Concept Extraction in Industry 4.0
Subsequently, we demonstrate the potential of CE methods, by applying them in three industrial use cases.
Toward Multi-Agent Reinforcement Learning for Distributed Event-Triggered Control
Model-free learning of communication and control policies provides an alternative.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Approximate non-linear model predictive control with safety-augmented neural networks
Our method requires a single evaluation of the NN and forward integration of the input sequence online, which is fast to compute on resource-constrained systems.
Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Test
Machine learning and deep learning have been used extensively to classify physical surfaces through images and time-series contact data.
Reproducing kernel Hilbert spaces in the mean field limit
Kernel methods, being supported by a well-developed theory and coming with efficient algorithms, are among the most popular and successful machine learning techniques.
Combining Slow and Fast: Complementary Filtering for Dynamics Learning
This filtering technique combines two signals by applying a high-pass filter to one signal, and low-pass filtering the other.
Data-Driven Observability Analysis for Nonlinear Stochastic Systems
Establishing these properties is challenging, especially when no analytical model is available and they are to be inferred directly from measurement data.
Towards remote fault detection by analyzing communication priorities
We propose a fault detection method that uses these priorities to detect errors in other agents.
Event-Triggered Time-Varying Bayesian Optimization
To cope with stale data arising from time variations, current approaches to TVBO require prior knowledge of a constant rate of change.
Improving the Performance of Robust Control through Event-Triggered Learning
However, in practice, many systems also exhibit uncertainty in the form of changes over time, e. g., due to weight shifts or wear and tear, leading to decreased performance or instability of the learning-based controller.
On Controller Tuning with Time-Varying Bayesian Optimization
Current TVBO methods do not explicitly account for these properties, resulting in poor tuning performance and many unstable controllers through over-exploration of the parameter space.
Event-triggered and distributed model predictive control for guaranteed collision avoidance in UAV swarms
Distributed model predictive control (DMPC) is often used to tackle path planning for unmanned aerial vehicle (UAV) swarms.
ECLAD: Extracting Concepts with Local Aggregated Descriptors
Further, we introduce a process for the validation of concept-extraction techniques based on synthetic datasets with pixel-wise annotations of their main components, reducing the need for human intervention.
Recognition Models to Learn Dynamics from Partial Observations with Neural ODEs
Identifying dynamical systems from experimental data is a notably difficult task.
Parameter Filter-based Event-triggered Learning
However, they usually come with a critical assumption - access to an accurate model of the system.
Learning by Doing: Controlling a Dynamical System using Causality, Control, and Reinforcement Learning
Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i. i. d.
Model-based Reinforcement Learning
reinforcement-learning
+1
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems
Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage.
Local policy search with Bayesian optimization
We develop an algorithm utilizing a probabilistic model of the objective function and its gradient.
GoSafe: Globally Optimal Safe Robot Learning
When learning policies for robotic systems from data, safety is a major concern, as violation of safety constraints may cause hardware damage.
Safe Value Functions
Although it is often not possible to compute the minimum required penalty, we reveal clear structure of how the penalty, rewards, discount factor, and dynamics interact.
On exploration requirements for learning safety constraints
In particular, we discuss the family of constraints that enforce safety in the context of a nominal control policy, and expose that these constraints do not need to be accurate everywhere.
Probabilistic Robust Linear Quadratic Regulators with Gaussian Processes
Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design.
Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
The combination of machine learning with control offers many opportunities, in particular for robust control.
Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression
However, these estimates are of a Bayesian nature, whereas for some important applications, like learning-based control with safety guarantees, frequentist uncertainty bounds are required.
Scaling Beyond Bandwidth Limitations: Wireless Control With Stability Guarantees Under Overload
An important class of cyber-physical systems relies on multiple agents that jointly perform a task by coordinating their actions over a wireless network.
Structure-preserving Gaussian Process Dynamics
On the other hand, classical numerical integrators are specifically designed to preserve these crucial properties through time.
Structured learning of rigid-body dynamics: A survey and unified view from a robotics perspective
Accurate models of mechanical system dynamics are often critical for model-based control and reinforcement learning.
Robot Learning with Crash Constraints
We consider failing behaviors as those that violate a constraint and address the problem of learning with crash constraints, where no data is obtained upon constraint violation.
Learning Event-triggered Control from Data through Joint Optimization
We present a framework for model-free learning of event-triggered control strategies.
Learning Constrained Dynamics with Gauss' Principle adhering Gaussian Processes
The identification of the constrained dynamics of mechanical systems is often challenging.
Identifying Causal Structure in Dynamical Systems
In this paper, we propose a method that identifies the causal structure of control systems.
Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures
When learning to ride a bike, a child falls down a number of times before achieving the first success.
Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes
The identification of the constrained dynamics of mechanical systems is often challenging.
A Kernel Two-sample Test for Dynamical Systems
Evaluating whether data streams are drawn from the same distribution is at the heart of various machine learning problems.
Safe and Fast Tracking on a Robot Manipulator: Robust MPC and Neural Network Control
Fast feedback control and safety guarantees are essential in modern robotics.
Actively Learning Gaussian Process Dynamics
Despite the availability of ever more data enabled through modern sensor and computer technology, it still remains an open problem to learn dynamical systems in a sample-efficient way.
Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
In reinforcement learning (RL), an autonomous agent learns to perform complex tasks by maximizing an exogenous reward signal while interacting with its environment.
A Learnable Safety Measure
While safety can only be guaranteed after learning the safety measure, we show that failures can already be greatly reduced by using the estimated measure during learning.
Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
Learning robot controllers by minimizing a black-box objective cost using Bayesian optimization (BO) can be time-consuming and challenging.
Trajectory-Based Off-Policy Deep Reinforcement Learning
Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks.
Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study
Bayesian optimization is proposed for automatic learning of optimal controller parameters from experimental data.
Deep Reinforcement Learning for Event-Triggered Control
Event-triggered control (ETC) methods can achieve high-performance control with a significantly lower number of samples compared to usual, time-triggered methods.
Gait learning for soft microrobots controlled by light fields
Soft microrobots based on photoresponsive materials and controlled by light fields can generate a variety of different gaits.
Learning an Approximate Model Predictive Controller with Guarantees
A supervised learning framework is proposed to approximate a model predictive controller (MPC) with reduced computational complexity and guarantees on stability and constraint satisfaction.
A Local Information Criterion for Dynamical Systems
Apart from its application for encoding a sequence of observations, we propose to use the compression achieved by this encoding as a criterion for model selection.
Event-triggered Learning for Resource-efficient Networked Control
Common event-triggered state estimation (ETSE) algorithms save communication in networked control systems by predicting agents' behavior, and transmitting updates only when the predictions deviate significantly.
Probabilistic Recurrent State-Space Models
State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification.
On the Design of LQR Kernels for Efficient Controller Learning
Finding optimal feedback controllers for nonlinear dynamic systems from data is hard.
Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
PID control architectures are widely used in industrial applications.
Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
In practice, the parameters of control policies are often tuned manually.
Automatic LQR Tuning Based on Gaussian Process Global Optimization
With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data.
Depth-Based Object Tracking Using a Robust Gaussian Filter
To address this issue, we show how a recently published robustification method for Gaussian filters can be applied to the problem at hand.
Robust Gaussian Filtering using a Pseudo Measurement
The contribution of this paper is to show that any Gaussian filter can be made compatible with fat-tailed sensor models by applying one simple change: Instead of filtering with the physical measurement, we propose to filter with a pseudo measurement obtained by applying a feature function to the physical measurement.
