Accurately estimating articulation angle, coupling force, and lateral velocity in articulated heavy vehicles is critical for accident prevention and energy efficiency. However, despite their importance, these quantities - especially the coupling force - have received limited attention in terms of practical and computationally efficient estimation methods. To bridge this gap, we propose a novel modeling approach that conceptualizes the coupling as a rigid damper. This formulation significantly reduces computational complexity while maintaining high estimation accuracy. Within a Bayesian estimation framework, we employ an unscented Kalman filter (UKF) for real-time inference of the vehicle states. We validate our method on high-fidelity simulation data with realistic scenarios and sensor noise. The results demonstrate the effectiveness of our method, highlighting its potential for enhancing vehicle safety and performance in practical applications.

Articulated Heavy Vehicles (AHVs) play a crucial role in today’s transportation, offering significant commercial and environmental advantages. However, challenges like jackknifing and trailer swing in AHVs highlight the need for focused research. This paper introduces innovative yaw stability algorithms designed to tackle these concerns, employing advanced control allocation techniques, including distributed control allocation. A power loss minimization algorithm with four different methods to maintain yaw stability is tested with real test vehicles. In this framework, the algorithms ensure that control actions stay within predetermined safe limits, contributing significantly to the overall safety and efficiency of AHVs.

This paper presents an end-to-end approach, named FrictionSegNet, for jointly estimating tyre-road friction coefficient and identifying road surfaces in real time from on board camera data. FrictionSegNet combines semantic segmentation and friction estimation by learning a shared latent space that encompasses both semantic segmentation and friction coefficient information. An objective function is designed for this task and minimised using *geco to train the model, providing the ability to control the balance between improved predictions and uncertainty measurement. To the best of our knowledge, this study is the first attempt to jointly estimate tyre-road friction and surface type by learning the joint latent space of semantic segmentation and friction coefficient information. The results suggest that it is possible to identify low-friction surfaces, e.g. snow or ice, and estimate upcoming road friction in real time from a camera only. As it is of interest to develop techniques that require less training data, numerical experiments were performed using transfer learning from a dataset consisting of images of various road surfaces. This led to better performance and faster convergence during training. FrictionSegNet achieved per-pixel accuracies of 97% and 95% when identifying snow and ice respectively, and RMS errors of 0.04–0.09 when estimating$\mu $values achievable by a truck *abs on gravel, dry and wet asphalt, snow, and ice surfaces.

We employ Reinforcement Learning (RL) techniques with improved state and action spaces for tactical decision making in an autonomous truck. Specifically, we implement Adaptive Cruise Control (ACC) and lane change maneuvers for the autonomous truck in a highway scenario. We show the results obtained using three reinforcement learning algorithms: Deep Q-Network (DQN), Advantage Actor-Critic (A2C) and Proximal Policy Optimization (PPO). Our results demonstrate that it is beneficial to separate high-level decision-making processes and low-level control actions between the RL agent and the low-level controllers based on physical models. Furthermore, we design a realistic reward function based on the Total Cost of Operation (TCOP) of the truck to guide the RL agent towards optimal driving strategy.

Reinforcement learning (RL) can be used to create a decision-making agent for autonomous driving. However, previous approaches provide black-box solutions, which do not offer information on how confident the agent is about its decisions. An estimate of both the aleatoric and epistemic uncertainty of the agent’s decisions is fundamental for real-world applications of autonomous driving. Therefore, this paper introduces the Ensemble Quantile Networks (EQN) method, which combines distributional RL with an ensemble approach, to obtain a complete uncertainty estimate. The distribution over returns is estimated by learning its quantile function implicitly, which gives the aleatoric uncertainty, whereas an ensemble of agents is trained on bootstrapped data to provide a Bayesian estimation of the epistemic uncertainty. A criterion for classifying which decisions that have an unacceptable uncertainty is also introduced. The results show that the EQN method can balance risk and time efficiency in different occluded intersection scenarios, by considering the estimated aleatoric uncertainty. Furthermore, it is shown that the trained agent can use the epistemic uncertainty information to identify situations that the agent has not been trained for and thereby avoid making unfounded, potentially dangerous, decisions outside of the training distribution.

Reinforcement learning (RL) can be used to create a tactical decision-making agent for autonomous driving. However, previous approaches only output decisions and do not provide information about the agent's confidence in the recommended actions. This paper investigates how a Bayesian RL technique, based on an ensemble of neural networks with additional randomized prior functions (RPF), can be used to estimate the uncertainty of decisions in autonomous driving. A method for classifying whether or not an action should be considered safe is also introduced. The performance of the ensemble RPF method is evaluated by training an agent on a highway driving scenario. It is shown that the trained agent can estimate the uncertainty of its decisions and indicate an unacceptable level when the agent faces a situation that is far from the training distribution. Furthermore, within the training distribution, the ensemble RPF agent outperforms a standard Deep Q-Network agent. In this study, the estimated uncertainty is used to choose safe actions in unknown situations. However, the uncertainty information could also be used to identify situations that should be added to the training process.

This paper presents a back-to-back performance comparison of lane-change maneuvers using two automated driving approaches and manual driving. The lane changes were conducted in a moving-base truck driving simulator using an A-double long combination vehicle. One of the automated driving approaches was based on driver model control and the other used optimization-based control. The comparison addresses lane change and braking, both initiation and execution, from the perspective of driver behavior and defined characteristic variables. We also discuss combined braking and steering behavior using a moderately safety-critical lane-change scenario. The purpose of this paper is to improve driving automation in early development by comparing and learning from professional truck drivers to enable higher driver acceptance.

Self-driving vehicles for commercial use cases like logistics or overcast mines increase their owners' economic competitiveness. Volvo maintains, evolves, and distributes a vehicle control product line for different brands like Volvo Trucks, Renault, and Mack in more than 190 markets world-wide. From the different application domains of their customers originates the need for a multi-domain reference architecture concerned with transport mission planning, execution, and tracking on top of the vehicle control product line. This industrial case study is the first of its kind reporting about the systematic process to design such a reference architecture involving all relevant external and internal stakeholders, development documents, low level artifacts, and literature. Quantitative and qualitative metrics were applied to evaluate non-functional requirements on the reference architecture level before a concrete variant was evaluated using a Volvo FMX truck in an exemplary construction site setting.

This paper compares the vehicle dynamics performances of two approaches for automated lane change manoeuvres of a long vehicle combination in simulated highway driving. One of the two approaches is a non-linear model predictive controller (NMPC), and the other is based on driver model control (DMC) theory. Both approaches utilize traffic situation predictions that include motion variable constraints and actuation requests for steering, propulsion and braking. The two automated driving approaches are compared in a simulation environment including a high-fidelity vehicle plant model and models of surrounding vehicles. Simulations show that both approaches can generate feasible lane change manoeuvres at the constant speeds of 44 and 78 km/h. In addition, lane changes were successfully conducted in combination with retardation due to leading vehicle braking from 80 to 50 km/h with a varying retardation range of 0.1-0.7 g. In general, the non-linear model predictive control shows a shorter lane change duration and lower values of the used absolute magnitude of the longitudinal and lateral accelerations. However, the specific objective function used in the NMPC leads to an unnecessary variation of longitudinal vehicle speed compared to the driver model control approach.

This paper describes an advance controller designed using the nonlinear inversion technique of a Modelica® based simulation tool, such as Dymola®, for active dolly steering of a high capacity transport vehicle. Actuator dynamics is included in the inverse model controller. Therefore, it can automatically generate required steering angle request for the dolly axles of the vehicle combination. The resultant controller is transfered as a functional mock-up unit (FMU) to Simulink® environment where the actual simulations are conducted. The controller is simulated against a high-fidelity vehicle model of an A-double combination from Virtual Truck Models (VTM) library - developed by Volvo Group Trucks Technology. Effects of variations of the actual actuator dynamics, with respect to the modeled dynamics in the inverse model controller, on overall vehicle performance are investigated.

An experiment was carried out on a low friction test track, where seven truck drivers repeatedly performed collision avoidance and stabilization with a 4×2 tractor. A previous finding from a simulator study was confirmed: In severe yaw instability, drivers engaged in a yaw rate nulling type of steering behavior, in conflict with the assumptions of conventional electronic stability control (ESC), and the experiment provided indications of conventional ESC behaving suboptimally in these situations. Promising results were obtained for modified versions of the ESC, based on the yaw rate nulling model of steering, but further development work is needed.

This paper presents a driving simulator experiment in which manual and automated driving of a prospective long vehicle combination has been studied. Based on post analysis of manual and automated driving trajectories, characteristic measures reflecting the manual drivers behavior have been proposed. It was observed that the drivers had a round shape of the utilized accelerations while negotiating the curves. A similar shape was found when using an objective function which included minimizing the resultant jerk vector.

Front tyre blow-outs lead to several fatal accidents involving heavy vehicles. Common for most heavy vehicles is a positive scrub radius. This can result in a destabilising steering wheel torque at front tyre blow-out. In this study the safety improvement achieved when reducing scrub radius is quantified. By using a heavy truck equipped with a modified electric power steering system it was possible to change the scrub radius virtually. Brakes were configured to emulate front tyre blow-out which appeared as a sudden disturbance on one of the front tyres. In total 20 drivers took part in the study which was run on a test track at 50 km/h. Results show that the produced average lateral deviation from the original direction was 23 cm, when scrub radius was 12 cm, compared to 16 cm, when scrub radius was 0 cm. The main cause of the observed difference was a small, yet significant, initial overshoot in steering wheel angle which can be derived from the destabilising steering wheel torque.