Search Results for author: Moritz Diehl

Found 22 papers, 11 papers with code

AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control

no code implementations6 Jun 2024 Rudolf Reiter, Andrea Ghezzi, Katrin Baumgärtner, Jasper Hoffmann, Robert D. McAllister, Moritz Diehl

The \ac{RL} critic is used as an approximation of the optimal value function, and an actor roll-out provides an initial guess for primal variables of the \ac{MPC}.

Model Predictive Control reinforcement-learning

Progressive Smoothing for Motion Planning in Real-Time NMPC

no code implementations4 Mar 2024 Rudolf Reiter, Katrin Baumgärtner, Rien Quirynen, Moritz Diehl

Nonlinear model predictive control (NMPC) is a popular strategy for solving motion planning problems, including obstacle avoidance constraints, in autonomous driving applications.

Autonomous Driving Model Predictive Control +1

Collision-free Motion Planning for Mobile Robots by Zero-order Robust Optimization-based MPC

no code implementations30 Jun 2023 Yunfan Gao, Florian Messerer, Jonathan Frey, Niels van Duijkeren, Moritz Diehl

This paper presents an implementation of robust model predictive control (MPC) for collision-free reference trajectory tracking for mobile robots.

Model Predictive Control Motion Planning

Frenet-Cartesian Model Representations for Automotive Obstacle Avoidance within Nonlinear MPC

no code implementations22 Dec 2022 Rudolf Reiter, Armin Nurkanović, Jonathan Frey, Moritz Diehl

We specify costs and collision avoidance constraints in the more advantageous coordinate frame, derive appropriate formulations and compare different obstacle constraints.

Collision Avoidance Model Predictive Control

Vertical Airborne Wind Energy Farms with High Power Density per Ground Area based on Multi-Aircraft Systems

no code implementations28 Nov 2022 Jochem De Schutter, Jakob Harzer, Moritz Diehl

This paper proposes and simulates vertical airborne wind energy (AWE) farms based on multi-aircraft systems with high power density (PD) per ground area.

Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control

no code implementations23 Oct 2022 Alessandro Saviolo, Jonathan Frey, Abhishek Rathod, Moritz Diehl, Giuseppe Loianno

Model-based control requires an accurate model of the system dynamics for precisely and safely controlling the robot in complex and dynamic environments.

Active Learning Model Predictive Control +1

An Inverse Optimal Control Approach for Trajectory Prediction of Autonomous Race Cars

no code implementations4 Apr 2022 Rudolf Reiter, Florian Messerer, Markus Schratter, Daniel Watzenig, Moritz Diehl

The algorithm therefore learns to predict the observed vehicle trajectory in a least-squares relation to measurement data and to the presumed structure of the predicting NLP.

Trajectory Prediction

Convergence Analysis of Homotopy-SGD for non-convex optimization

no code implementations20 Nov 2020 Matilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh, Moritz Diehl, Frank Hutter

In this work, we present a first-order stochastic algorithm based on a combination of homotopy methods and SGD, called Homotopy-Stochastic Gradient Descent (H-SGD), which finds interesting connections with some proposed heuristics in the literature, e. g. optimization by Gaussian continuation, training by diffusion, mollifying networks.

An Efficient Real-Time NMPC for Quadrotor Position Control under Communication Time-Delay

1 code implementation21 Oct 2020 Barbara Barros Carlos, Tommaso Sartor, Andrea Zanelli, Gianluca Frison, Wolfram Burgard, Moritz Diehl, Giuseppe Oriolo

The advances in computer processor technology have enabled the application of nonlinear model predictive control (NMPC) to agile systems, such as quadrotors.

Robotics Systems and Control Systems and Control Optimization and Control

Kernel Distributionally Robust Optimization

2 code implementations12 Jun 2020 Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf

We prove a theorem that generalizes the classical duality in the mathematical problem of moments.

Stochastic Optimization

On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs

2 code implementations3 Jun 2020 Matilde Gargiani, Andrea Zanelli, Moritz Diehl, Frank Hutter

This enables researchers to further study and improve this promising optimization technique and hopefully reconsider stochastic second-order methods as competitive optimization techniques for training DNNs; we also hope that the promise of SGN may lead to forward automatic differentiation being added to Tensorflow or Pytorch.

Second-order methods

Transferring Optimality Across Data Distributions via Homotopy Methods

no code implementations ICLR 2020 Matilde Gargiani, Andrea Zanelli, Quoc Tran Dinh, Moritz Diehl, Frank Hutter

Homotopy methods, also known as continuation methods, are a powerful mathematical tool to efficiently solve various problems in numerical analysis, including complex non-convex optimization problems where no or only little prior knowledge regarding the localization of the solutions is available.

Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem

no code implementations31 Mar 2020 Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf

In order to anticipate rare and impactful events, we propose to quantify the worst-case risk under distributional ambiguity using a recent development in kernel methods -- the kernel mean embedding.

HPIPM: a high-performance quadratic programming framework for model predictive control

1 code implementation5 Mar 2020 Gianluca Frison, Moritz Diehl

This paper introduces HPIPM, a high-performance framework for quadratic programming (QP), designed to provide building blocks to efficiently and reliably solve model predictive control problems.

Optimization and Control Systems and Control Systems and Control

acados: a modular open-source framework for fast embedded optimal control

1 code implementation30 Oct 2019 Robin Verschueren, Gianluca Frison, Dimitris Kouzoupis, Niels van Duijkeren, Andrea Zanelli, Branimir Novoselnik, Jonathan Frey, Thivaharan Albin, Rien Quirynen, Moritz Diehl

The acados software package is a collection of solvers for fast embedded optimization, intended for fast embedded applications.

Optimization and Control

The BLAS API of BLASFEO: optimizing performance for small matrices

1 code implementation21 Feb 2019 Gianluca Frison, Tommaso Sartor, Andrea Zanelli, Moritz Diehl

This BLAS API has lower performance than the BLASFEO API, but it nonetheless outperforms optimized BLAS and especially LAPACK libraries for matrices fitting in cache.

Mathematical Software

A Family of Iterative Gauss-Newton Shooting Methods for Nonlinear Optimal Control

2 code implementations29 Nov 2017 Markus Giftthaler, Michael Neunert, Markus Stäuble, Jonas Buchli, Moritz Diehl

This paper introduces a family of iterative algorithms for unconstrained nonlinear optimal control.

Systems and Control Robotics Optimization and Control

BLASFEO: basic linear algebra subroutines for embedded optimization

6 code implementations8 Apr 2017 Gianluca Frison, Dimitris Kouzoupis, Tommaso Sartor, Andrea Zanelli, Moritz Diehl

BLASFEO is a dense linear algebra library providing high-performance implementations of BLAS- and LAPACK-like routines for use in embedded optimization.

Mathematical Software

Cannot find the paper you are looking for? You can Submit a new open access paper.