Erik Frisk

Theodor Westny, Joel Oskarsson, Björn Olofsson et al.

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. Multimodal probabilistic predictions are obtained 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.

Theodor Westny, Joel Oskarsson, Björn Olofsson et al.

Given their flexibility and encouraging performance, deep-learning models are becoming standard for motion prediction in autonomous driving. However, with great flexibility comes a lack of interpretability and possible violations of physical constraints. Accompanying these data-driven methods with differentially-constrained motion models to provide physically feasible trajectories is a promising future direction. The foundation for this work is a previously introduced graph-neural-network-based model, MTP-GO. The neural network learns to compute the inputs to an underlying motion model to provide physically feasible trajectories. This research investigates the performance of various motion models in combination with numerical solvers for the prediction task. The study shows that simpler models, such as low-order integrator models, are preferred over more complex, e.g., kinematic models, to achieve accurate predictions. Further, the numerical solver can have a substantial impact on performance, advising against commonly used first-order methods like Euler forward. Instead, a second-order method like Heun's can greatly improve predictions.

Luigi Romano, Ole Morten Aamo, Jan Åslund et al.

In [1], a new modeling paradigm for developing rate-and-state-dependent, control-oriented friction models was introduced. The framework, termed Friction with Bristle Dynamics (FrBD), combines nonlinear analytical expressions for the friction coefficient with constitutive equations for bristle-like elements. Within the FrBD framework, this letter introduces two novel formulations based on the two most general linear viscoelastic models for solids: the Generalized Maxwell (GM) and Generalized Kelvin-Voigt (GKV) elements. Both are analyzed in terms of boundedness and passivity, revealing that these properties are satisfied for any physically meaningful parametrization. An application of passivity for control design is also illustrated, considering an example from robotics. The findings of this letter systematically integrate rate-and-state dynamic friction models with linear viscoelasticity.

Ipek Kuvvetli, Christofer Sundström, Sogol Kharrazi et al.

This paper presents a comparative optimization framework for smart charging of electrified vehicle fleets. Using heuristic sequential dynamic programming (SeqDP), the framework minimizes electricity costs while adhering to constraints related to the power grid, charging infrastructure, vehicle availability, and simple considerations of battery aging. Based on real-world operational data, the model incorporates discrete energy states, time-varying tariffs, and state-of-charge (SoC) targets to deliver a scalable and cost-effective solution. Classical DP approach suffers from exponential computational complexity as the problem size increases. This becomes particularly problematic when conducting monthly-scale analyses aimed at minimizing peak power demand across all vehicles. The extended time horizon, coupled with multi-state decision-making, renders exact optimization impractical at larger scales. To address this, a heuristic method is employed to enable systematic aggregation and tractable computation for the Non-Linear Programming (NLP) problem. Rather than seeking a globally optimal solution, this study focuses on a time-efficient smart charging strategy that aims to minimize energy cost while flattening the overall power profile. In this context, a sequential heuristic DP approach is proposed. Its performance is evaluated against a full-fleet solver using Gurobi, a widely used commercial solver in both academia and industry. The proposed algorithm achieves a reduction of the overall cost and peak power by more than 90% compared to uncontrolled schedules. Its relative cost remains within 9\% of the optimal values obtained from the full-fleet solver, and its relative peak-power deviation stays below 15% for larger fleets.

Theodor Westny, Arman Mohammadi, Daniel Jung et al.

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.

Theodor Westny, Björn Olofsson, Erik Frisk

The availability of high-quality datasets is crucial for the development of behavior prediction algorithms in autonomous vehicles. This paper highlights the need to standardize the use of certain datasets for motion forecasting research to simplify comparative analysis and proposes a set of tools and practices to achieve this. Drawing on extensive experience and a comprehensive review of current literature, we summarize our proposals for preprocessing, visualization, and evaluation in the form of an open-sourced toolbox designed for researchers working on trajectory prediction problems. The clear specification of necessary preprocessing steps and evaluation metrics is intended to alleviate development efforts and facilitate the comparison of results across different studies. The toolbox is available at: https://github.com/westny/dronalize.

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. 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.

Luigi Romano, Ole Morten Aamo, Jan Åslund et al.

Accurate estimation of the vehicle's sideslip angle and tire forces is essential for enhancing safety and handling performances in unknown driving scenarios. To this end, the present paper proposes an innovative observer that combines a linear single-track model with a distributed representation of the tires and information collected from standard sensors. In particular, by adopting a comprehensive representation of the tires in terms of hyperbolic partial differential equations (PDEs), the proposed estimation strategy exploits dynamical inversion to reconstruct the lumped and distributed vehicle states solely from yaw rate and lateral acceleration measurements. Simulation results demonstrate the effectiveness of the observer in estimating the sideslip angle and tire forces even in the presence of noise and model uncertainties.

Arman Mohammadi, Mattias Krysander, Daniel Jung et al.

Deep neural networks has been increasingly applied in fault diagnostics, where it uses historical data to capture systems behavior, bypassing the need for high-fidelity physical models. However, despite their competence in prediction tasks, these models often struggle with the evaluation of their confidence. This matter is particularly important in consistency-based diagnosis where decision logic is highly sensitive to false alarms. To address this challenge, this work presents a diagnostic framework that uses ensemble probabilistic machine learning to improve diagnostic characteristics of data driven consistency based diagnosis by quantifying and automating the prediction uncertainty. The proposed method is evaluated across several case studies using both ablation and comparative analyses, showing consistent improvements across a range of diagnostic metrics.

Olov Holmer, Mattias Krysander, Erik Frisk

Accurate predictions of when a component will fail are crucial when planning maintenance, and by modeling the distribution of these failure times, survival models have shown to be particularly useful in this context. The presented methodology is based on conventional neural network-based survival models that are trained using data that is continuously gathered and stored at specific times, called snapshots. An important property of this type of training data is that it can contain more than one snapshot from a specific individual which results in that standard maximum likelihood training can not be directly applied since the data is not independent. However, the papers show that if the data is in a specific format where all snapshot times are the same for all individuals, called homogeneously sampled, maximum likelihood training can be applied and produce desirable results. In many cases, the data is not homogeneously sampled and in this case, it is proposed to resample the data to make it homogeneously sampled. How densely the dataset is sampled turns out to be an important parameter; it should be chosen large enough to produce good results, but this also increases the size of the dataset which makes training slow. To reduce the number of samples needed during training, the paper also proposes a technique to, instead of resampling the dataset once before the training starts, randomly resample the dataset at the start of each epoch during the training. The proposed methodology is evaluated on both a simulated dataset and an experimental dataset of starter battery failures. The results show that if the data is homogeneously sampled the methodology works as intended and produces accurate survival models. The results also show that randomly resampling the dataset on each epoch is an effective way to reduce the size of the training data.

Olov Holmer, Erik Frisk, Mattias Krysander

In this paper, a family of neural network-based survival models is presented. The models are specified based on piecewise definitions of the hazard function and the density function on a partitioning of the time; both constant and linear piecewise definitions are presented, resulting in a family of four models. The models can be seen as an extension of the commonly used discrete-time and piecewise exponential models and thereby add flexibility to this set of standard models. Using a simulated dataset the models are shown to perform well compared to the highly expressive, state-of-the-art energy-based model, while only requiring a fraction of the computation time.

Theodor Westny, Erik Frisk, Björn Olofsson

The use of learning-based methods for vehicle behavior prediction is a promising research topic. However, many publicly available data sets suffer from class distribution skews which limits learning performance if not addressed. This paper proposes an interaction-aware prediction model consisting of an LSTM autoencoder and SVM classifier. Additionally, an imbalanced learning technique, the multiclass balancing ensemble is proposed. Evaluations show that the method enhances model performance, resulting in improved classification accuracy. Good generalization properties of learned models are important and therefore a generalization study is done where models are evaluated on unseen traffic data with dissimilar traffic behavior stemming from different road configurations. This is realized by using two distinct highway traffic recordings, the publicly available NGSIM US-101 and I80 data sets. Moreover, methods for encoding structural and static features into the learning process for improved generalization are evaluated. The resulting methods show substantial improvements in classification as well as generalization performance.