2 code implementations • 1 May 2024 • Theodor Westny, Björn Olofsson, Erik Frisk
The availability of high-quality datasets is crucial for the development of behavior prediction algorithms in autonomous vehicles.
no code implementations • 27 Mar 2024 • Olov Holmer, Erik Frisk, Mattias Krysander
In this paper, a family of neural network-based survival models is presented.
no code implementations • 27 Mar 2024 • Olov Holmer, Mattias Krysander, Erik Frisk
The results also show that randomly resampling the dataset on each epoch is an effective way to reduce the size of the training data.
no code implementations • 20 Mar 2024 • Ying Shuai Quan, Jian Zhou, Erik Frisk, Chung Choo Chung
This paper proposes a safety-critical controller for dynamic and uncertain environments, leveraging a robust environment control barrier function (ECBF) to enhance the robustness against the measurement and prediction uncertainties associated with moving obstacles.
1 code implementation • 18 Mar 2024 • Theodor Westny, Björn Olofsson, Erik Frisk
The ability to predict the future trajectories of traffic participants is crucial for the safe and efficient operation of autonomous vehicles.
no code implementations • 27 Dec 2023 • Fatemeh Hashemniya, Arvind Balachandran, Erik Frisk, Mattias Krysander
The findings indicate that the default sensor setup is insufficient for achieving complete fault isolability.
1 code implementation • 27 Nov 2023 • Theodor Westny, Arman Mohammadi, Daniel Jung, Erik Frisk
This paper addresses the training of Neural Ordinary Differential Equations (neural ODEs), and in particular explores the interplay between numerical integration techniques, stability regions, step size, and initialization techniques.
no code implementations • 24 Nov 2023 • Theodor Westny, Björn Olofsson, Erik Frisk
To study the effects of uncertainty in autonomous motion planning and control, an 8-DOF model of a tractor-semitrailer is implemented and analyzed.
2 code implementations • 11 Apr 2023 • Theodor Westny, Joel Oskarsson, Björn Olofsson, Erik Frisk
This research investigates the performance of various motion models in combination with numerical solvers for the prediction task.
no code implementations • 1 Feb 2023 • Olov Holmer, Erik Frisk, Mattias Krysander
Due to the complex behavior of system degradation, data-driven methods are often preferred, and neural network-based methods have been shown to perform particularly very well.
2 code implementations • 1 Feb 2023 • Theodor Westny, Joel Oskarsson, Björn Olofsson, Erik Frisk
Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior.
1 code implementation • 22 Dec 2022 • Jian Zhou, Björn Olofsson, Erik Frisk
This paper proposes an interaction and safety-aware motion-planning method for an autonomous vehicle in uncertain multi-vehicle traffic environments.
no code implementations • 30 Mar 2022 • Erik Jakobsson, Erik Frisk, Mattias Krysander, Robert Pettersson
In this work Time Series Classification techniques are investigated, and especially their applicability in applications where there are significant differences between the individuals where data is collected, and the individuals where the classification is evaluated.
no code implementations • 17 Dec 2021 • Victor Fors, Björn Olofsson, Erik Frisk
Simulation results from highway driving scenarios show that the proposed method in real-time negotiates traffic situations out of scope for a nominal MPC approach and performs favorably to state-of-the-art reinforcement-learning approaches without requiring prior training.
1 code implementation • 22 Sep 2021 • Theodor Westny, Erik Frisk, Björn Olofsson
The use of learning-based methods for vehicle behavior prediction is a promising research topic.