Search Results for author: Matthias Althoff

Found 22 papers, 3 papers with code

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea

no code implementations13 Feb 2024 Hanna Krasowski, Matthias Althoff

We introduce an efficient verification approach that determines the compliance of actions with respect to the COLREGS formalized using temporal logic.

Autonomous Vehicles Reinforcement Learning (RL) +1

End-To-End Set-Based Training for Neural Network Verification

no code implementations26 Jan 2024 Lukas Koller, Tobias Ladner, Matthias Althoff

In many cases, set-based trained neural networks outperform neural networks trained with state-of-the-art adversarial attacks.

Provably-Correct Safety Protocol for Cooperative Platooning

no code implementations13 Dec 2023 Sebastian Mair, Matthias Althoff

Cooperative Adaptive Cruise Control (CACC) is a well-studied technology for forming string-stable vehicle platoons.

Collision Avoidance

Reachability Analysis of ARMAX Models

no code implementations21 Sep 2023 Laura Lützow, Matthias Althoff

The first approach we propose can only be used with dependency-preserving set representations such as symbolic zonotopes, while the second one is valid for arbitrary set representations but relies on a reformulation of the ARMAX model.

valid

Optimizing Modular Robot Composition: A Lexicographic Genetic Algorithm Approach

no code implementations15 Sep 2023 Jonathan Külz, Matthias Althoff

Industrial robots are designed as general-purpose hardware with limited ability to adapt to changing task requirements or environments.

Industrial Robots Navigate

Resilience in Platoons of Cooperative Heterogeneous Vehicles: Self-organization Strategies and Provably-correct Design

no code implementations27 May 2023 Di Liu, Sebastian Mair, Kang Yang, Simone Baldi, Paolo Frasca, Matthias Althoff

We show that self-organization promotes resilience to acceleration limits and communication failures, i. e., homogenizing to a common group behavior makes the platoon recover from these causes of impairments.

Specification-Driven Neural Network Reduction for Scalable Formal Verification

no code implementations3 May 2023 Tobias Ladner, Matthias Althoff

Formal verification of neural networks is essential before their deployment in safety-critical settings.

Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric

no code implementations2 Feb 2023 Eivind Meyer, Maurice Brenner, BoWen Zhang, Max Schickert, Bilal Musani, Matthias Althoff

Heterogeneous graphs offer powerful data representations for traffic, given their ability to model the complex interaction effects among a varying number of traffic participants and the underlying road infrastructure.

Autonomous Driving Trajectory Prediction

Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes

no code implementations19 Oct 2022 Niklas Kochdumper, Hanna Krasowski, Xiao Wang, Stanley Bak, Matthias Althoff

While reinforcement learning produces very promising results for many applications, its main disadvantage is the lack of safety guarantees, which prevents its use in safety-critical systems.

reinforcement-learning Reinforcement Learning (RL) +1

Model Predictive Robustness of Signal Temporal Logic Predicates

no code implementations16 Sep 2022 Yuanfei Lin, Haoxuan Li, Matthias Althoff

We evaluate our approach for the use case of autonomous driving with predicates used in formalized traffic rules on a recorded dataset, which highlights the advantage of our approach compared to traditional approaches in terms of precision.

Autonomous Driving

Open- and Closed-Loop Neural Network Verification using Polynomial Zonotopes

no code implementations6 Jul 2022 Niklas Kochdumper, Christian Schilling, Matthias Althoff, Stanley Bak

We present a novel approach to efficiently compute tight non-convex enclosures of the image through neural networks with ReLU, sigmoid, or hyperbolic tangent activation functions.

Contingency-constrained economic dispatch with safe reinforcement learning

no code implementations12 May 2022 Michael Eichelbeck, Hannah Markgraf, Matthias Althoff

The contingency constraint is computed using set-based backwards reachability analysis and actions of the RL agent are verified through a safety layer.

Computational Efficiency reinforcement-learning +2

Privacy Preserving Set-Based Estimation Using Partially Homomorphic Encryption

1 code implementation19 Oct 2020 Amr Alanwar, Victor Gassmann, Xingkang He, Hazem Said, Henrik Sandberg, Karl Henrik Johansson, Matthias Althoff

The set-based estimation has gained a lot of attention due to its ability to guarantee state enclosures for safety-critical systems.

Cryptography and Security Robotics

Falsification-Based Robust Adversarial Reinforcement Learning

no code implementations1 Jul 2020 Xiao Wang, Saasha Nair, Matthias Althoff

Robust adversarial RL (RARL) was previously proposed to train an adversarial network that applies disturbances to a system, which improves the robustness in test scenarios.

Autonomous Vehicles Decision Making +2

Formal synthesis of closed-form sampled-data controllers for nonlinear continuous-time systems under STL specifications

no code implementations7 Jun 2020 Cees F. Verdier, Niklas Kochdumper, Matthias Althoff, Manuel Mazo Jr

Subsequently, the best candidate is verified using reachability analysis; if the candidate solution does not satisfy the specification, an initial condition violating the specification is extracted as a counterexample.

Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior

no code implementations26 Mar 2020 Fanta Camara, Nicola Bellotto, Serhan Cosar, Florian Weber, Dimitris Nathanael, Matthias Althoff, Jingyuan Wu, Johannes Ruenz, André Dietrich, Gustav Markkula, Anna Schieben, Fabio Tango, Natasha Merat, Charles W. Fox

Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets.

Autonomous Driving Descriptive

Distributed Set-Based Observers Using Diffusion Strategies

2 code implementations23 Mar 2020 Amr Alanwar, Jagat Jyoti Rath, Hazem Said, Karl Henrik Johansson, Matthias Althoff

Both algorithms utilize a set-based diffusion step, which decreases the estimation errors and the size of estimated sets, and can be seen as a lightweight approach to achieve partial consensus between the distributed estimated sets.

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, from Sensing to Tracking

no code implementations26 Feb 2020 Fanta Camara, Nicola Bellotto, Serhan Cosar, Dimitris Nathanael, Matthias Althoff, Jingyuan Wu, Johannes Ruenz, André Dietrich, Charles W. Fox

Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets.

Autonomous Driving

Event-Triggered Diffusion Kalman Filters

1 code implementation1 Nov 2017 Amr Alanwar, Hazem Said, Ankur Mehta, Matthias Althoff

Distributed state estimation strongly depends on collaborative signal processing, which often requires excessive communication and computation to be executed on resource-constrained sensor nodes.

Systems and Control Robotics Signal Processing

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