Theodor Westny

Ph.D.

AI, ML, Motion Planning

Autonomous Driving

Theodor Westny, Ph.D., is a researcher at the Division of Vehicular Systems, Department of Electrical Engineering, Linköping University, Sweden. His research is on AI and deep learning for applications in autonomous systems, generative modeling, learning continuous-time dynamics, autonomous motion planning and control as well as vehicle dynamics modeling. He received his doctoral degree in January 2025 after he successfully defended his thesis titled “Context-Aware Behavior Prediction for Autonomous Driving”.

He joined the Division of Vehicular Systems in August 2020 after obtaining his MSc. Degree in Electrical Engineering with the thesis “Modeling and Lateral Control of Tractor-Trailer Vehicles during Aggressive Maneuvers”. During his engineering studies, he did an exchange semester at UNSW, Sydney, Australia and completed several software developer internships, including a visit in 2020 to the motion planning and controls team at Embark Trucks, San Francisco, USA. Since 2018, he has been an active member of the global talent network, Nova.

Research Interests

Spatio-Temporal Data Analysis
- Multi-agent Trajectory Prediction
- Learning on graphs, (Temporal) GNNs
- Learning continuous-time dynamics, Neural ODEs, PINN
Probabilistic and Generative Modeling
- Diffusion models
- Mixture density networks
- Variational Autoencoders
Autonomous Vehicles
- Vehicle dynamics modeling
- Predictive control
- Advanced driver assistance systems
- End-to-end motion planning

Selected Ph.D. Coursework

Neural Networks and Deep Learning (6 ECTS)
Reinforcement Learning (6 ECTS)
Machine Learning for Computer Vision (6 ECTS)
Graph Learning (6 ECTS)
Probabilistic Artificial Intelligence (Summer school, 7.5 ECTS)
Advanced Machine Learning (6 ECTS)
Generalization of Overparameterized Models and Double Descent (3 ECTS)
Statistical Inference and Applications (6 ECTS)
Simulation of ODEs and DAEs (9 ECTS)
Advanced Motion Planning and Control (9 ECTS)
Optimal Vehicle Maneuvers (6 ECTS)
Observer Theory and Non-linear Design Techniques (6 ECTS)

News

Jan 10, 2025	I am happy to share that I successfully defended my Ph.D. thesis. Many thanks to everyone involved!
May 02, 2024	Our paper, Stability-Informed Initialization of Neural Ordinary Differential Equations has been accepted to ICML 2024! Looking forward to sharing our findings in Vienna this July.
Mar 15, 2024	We are up and running! Welcome to my page

Selected Publications

Diffusion-Based Environment-Aware Trajectory Prediction

Theodor Westny, Björn Oskarsson , and Erik Frisk

arXiv preprint arXiv:2403.11643, 2024

Abs Bib PDF

The ability to predict the future trajectories of traffic participants is crucial for the safe and efficient operation of autonomous vehicles. In this paper, a diffusion-based generative model for multi-agent trajectory prediction is proposed. The model is capable of capturing the complex interactions between traffic participants and the environment, accurately learning the multimodal nature of the data. The effectiveness of the approach is assessed on large-scale datasets of real-world traffic scenarios, showing that our model outperforms several well-established methods in terms of prediction accuracy. By the incorporation of differential motion constraints on the model output, we illustrate that our model is capable of generating a diverse set of realistic future trajectories. Through the use of an interaction-aware guidance signal, we further demonstrate that the model can be adapted to predict the behavior of less cooperative agents, emphasizing its practical applicability under uncertain traffic conditions.
@article{westny2024diffusion, title = {Diffusion-Based Environment-Aware Trajectory Prediction}, author = {Westny, Theodor and Oskarsson, Bj{\"o}rn and Frisk, Erik}, journal = {arXiv preprint arXiv:2403.11643}, year = {2024}, }
MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs

Theodor Westny, Joel Oskarsson , Björn Olofsson , and Erik Frisk

IEEE Transactions on Intelligent Vehicles, 2023

Abs Bib PDF Code

Enabling resilient autonomous motion planning requires robust predictions of surrounding road users’ future behavior. In response to this need and the associated challenges, we introduce our model, titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multi-modal probabilistic predictions are provided by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of metrics.
@article{westny2023graph, journal = {IEEE Transactions on Intelligent Vehicles}, title = {{MTP-GO}: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural {ODEs}}, year = {2023}, volume = {8}, number = {9}, pages = {4223-4236}, author = {Westny, Theodor and Oskarsson, Joel and Olofsson, Bj{\"o}rn and Frisk, Erik}, doi = {10.1109/TIV.2023.3282308}, }
Stability-Informed Initialization of Neural Ordinary Differential Equations

Theodor Westny, Arman Mohammadi , Daniel Jung , and Erik Frisk

In Proceedings of the 41st International Conference on Machine Learning , 2024

Abs Bib PDF Code

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. It is shown how the choice of integration technique implicitly regularizes the learned model, and how the solver’s corresponding stability region affects training and prediction performance. From this analysis, a stability-informed parameter initialization technique is introduced. The effectiveness of the initialization method is displayed across several learning benchmarks and industrial applications.
@inproceedings{westny2023stability, title = {Stability-Informed Initialization of Neural Ordinary Differential Equations}, author = {Westny, Theodor and Mohammadi, Arman and Jung, Daniel and Frisk, Erik}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {52903--52914}, year = {2024}, }