Coordinating the motion profiles of fully automated vehicles in confined sites presents a challenge, particularly in avoiding conflicts in MUTually EXclusive (MUTEX) zones like intersections, merge-splits, and narrow roads. Prior methods have utilized optimization-based formulations, where the scheduling (order) of vehicles in MUTEX zones is found using a heuristic, followed by solving a nonlinear program (NLP) to determine the optimal state and control trajectories of each vehicle given the schedule. This paper presents a method that reduces the computational demand in the second step by decomposing the NLP into multiple smaller, parallelly solvable, NLPs. The method uses the confined area’s road network geometry and the vehicle positions to identify non-significant MUTEX relations and leverage results from graph theory to use this information to identify independent subproblems. We demonstrate that the solution obtained using this approach is equivalent to that obtained by solving the original NLP. Furthermore, by utilizing the dual variables connected to the MUTEX enforcing constraints, the method is capable of a further, sub-optimality-inducing, subdivision of the problem, enabling a trade-off between optimality and computation. We show how the method can be utilized, both when the plan needs to be initially computed and when there is a need for updating an existing motion plan. Simulation examples demonstrate the computational improvement with respect to the non-decomposed problem.

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.

In this paper, we present a high-level optimization-based control strategy for the coordination of electric automated vehicles (AVs) in confined sites. A centralized controller optimizes the state and input trajectories of all vehicles in the site such that collisions are avoided in cross-intersections, narrow roads, merge crossings, and charging stations, while also considering the charging process. Specifically, the controller consists of two optimization-based components. The first component is tasked with solving the combinatorial part of the problem, which corresponds to the order in which the vehicles pass the crossings, by solving a Mixed Integer Quadratic Problem (MIQP). The found combinatorial solution is then utilized for calculating the optimal state and input trajectories that are obtained by solving a Nonlinear Program (NLP). The control algorithm is compared with respect to alternative optimization-based approaches in simulation scenarios. For the presented scenario, our method achieves improved energy efficiency by up to 7.6% while slightly improving the average mission end time, and furthermore, it is capable of avoiding deadlocks.

A lane keeping assist system uses sensor and environmental information to automatically steer the vehicle, whenever necessary, to keep it within the lanes. As the system overrides the driver, it is important that automatic interventions are only used when the driver is unaware of the traffic situation, i.e., in cases of unintentional lane departures. Hence, one of the major challenges for such systems is to distinguish between intentional and unintentional driving behaviors. In this work, we implement an intention-aware lane keeping assist system based on machine learning, where the goal is to activate interventions only when the lane departure is unintentional. The system performance is evaluated using a real-world data set, partly consisting of unintentional lane departure events, normal driving, and intentional lane departure events. The results show that driver state information, obtained from a camera-based gaze-tracking system, improves the lane keeping assist system’s performance, especially for intentional lane departure events. They also show that it is hard to predict the driver intention for prediction horizons longer than 1.5 s.

Advanced driver assistance systems have been an active research topic for decades, for which many approaches have been developed not only to reduce the number of traffic accidents but also to increase the driver’s comfort. Among the many different solutions proposed, learning-based prediction approaches have gained considerable attention in recent years. Within this scope, this work focuses on the implementation aspects of a linear learning-based regression model for detecting unintended lane-departures, where the goal is to achieve a prediction model with good predictive performance while keeping the computational complexity as low as possible. Aspects under consideration include input signal selection and down-sampling. The linear prediction model is analyzed using a real world data set, and benchmarked against a kinematic constant velocity model and a non-linear regression model. The results show that the linear regression model has a significantly higher prediction performance when compared to a kinematic model. It is also shown that the predictive performance remains comparable to the more complex nonlinear regression model, even though the computational complexity of the linear model is significantly lower.

This paper presents a computationally efficient algorithm for eco-driving along horizons of over 100 km. The eco-driving problem is formulated as a bi-level program, where the bottom level is solved offline, pre-optimising gear as a function of longitudinal velocity (kinetic energy) and acceleration. The top level is solved online, optimising a nonlinear dynamic program with travel time, kinetic energy and acceleration as state variables. To further reduce computational effort, the travel time is adjoined to the objective by applying necessary Pontryagin’s Maximum Principle conditions, and the nonlinear program is solved using real-time iteration sequential quadratic programming scheme in a model predictive control framework. Compared to average driver’s driving cycle, the energy savings of using the proposed algorithm is up to 11.60%.

This paper presents a probabilistic framework for collision probability estimation. The framework uses information about objects' velocity and acceleration gathered from a larger real traffic data set in order to create a discrete Markov Chain model. This model is then used to predict other traffic participants motion in a given scenario and through this calculate the probability of a future collision. The framework is then analyzed with respect to potential errors that are created in the discretization process. Especially the errors related to the discrete velocity regions are investigated in more detail. The analysis is performed on a selection of critical scenarios from a larger data set in order to set scenario-based requirements of the state discretization resolution. In the end, there is a discussion about the implications for the collision probability estimate, as well as, suggested next steps in order to get a complete view of the precision of the estimate.

By considering a lane change maneuver as primarily a longitudinal motion planning problem, this paper presents a lane change maneuver algorithm with a pragmatic approach to determine an inter-vehicle traffic gap and time instance to perform the maneuver. The proposed approach selects an appropriate inter-vehicle traffic gap and time instance to perform the lane change maneuver by simply estimating whether there might exist a longitudinal trajectory that allows the automated vehicle to safely perform the maneuver. The lane change maneuver algorithm then proceeds to solve two loosely coupled convex quadratic programs to obtain the longitudinal trajectory to position the automated vehicle in the selected inter-vehicle traffic gap at the desired time instance and the corresponding lateral trajectory. Simulation results demonstrate the capability of the proposed approach to select an appropriate inter-vehicle traffic gap and time instance to initialize the lateral motion of a lane change maneuver in various traffic scenarios. The real-time ability of the lane change maneuver algorithm to generate safe and smooth trajectories is shown by experimental results of a Volvo V60 performing automated lane change maneuvers on a test track.

Automated driving is predicted to enhance traffic safety, transport efficiency, and driver comfort. To extend the capability of current advanced driver assistance systems, and eventually realize fully automated driving, the intelligent vehicle system must have the ability to plan different maneuvers while adapting to the surrounding traffic environment. This paper presents an algorithm for longitudinal and lateral trajectory planning for automated driving maneuvers where the vehicle does not have right of way, i.e., yielding maneuvers. Such maneuvers include, e.g., lane change, roundabout entry, and intersection crossing. In the proposed approach, the traffic environment which the vehicle must traverse is incorporated as constraints on its longitudinal and lateral positions. The trajectory planning problem can thereby be formulated as two loosely coupled low-complexity model predictive control problems for longitudinal and lateral motion. Simulation results demonstrate the ability of the proposed trajectory planning algorithm to generate smooth collision-free maneuvers which are appropriate for various traffic situations.

Detecting pedestrians is a challenging and widely explored problem in computer vision. Many approaches rely on large quantities of manually labelled training data to learn a pedestrian classifier. To reduce the need for collecting and manually labelling real image training data, this paper investigates the possibility to use augmented images to train a pedestrian classifier. Augmented images are generated by rendering virtual pedestrians onto real image backgrounds. Classifiers learned from real or augmented training data are evaluated on real image test data from the widely used Daimler Mono Pedestrian benchmark data set. Results show that augmented training data generated from a single 200 frame image sequence reach 70 % average detection rate at one False Positives Per Image (FPPI), compared to 81 % for a classifier trained by a large-scale real data set. Results also show that complementing real training data with augmented data improves detection performance, compared to using real training data only.

This paper examines the problem of estimating vehicle position and direction, i.e., pose, from a single vehicle-mounted camera. A drawback of pose estimation using vision only is that it fails when image information is poor. Consequently, other information sources, e.g., motion models and sensors, may be used to complement vision to improve the estimates. We propose to combine standard in-vehicle sensor data and vehicle motion models with the accuracy of local visual bundle adjustment. This means that pose estimates are optimized with regard not only to observed image features but also to a single-track vehicle model and standard in-vehicle sensors. The described method has been experimentally tested on challenging data sets at both low and high vehicle speeds as well as a data set with moving objects. The vehicle motion model in combination with in-vehicle sensors exhibit good accuracy in estimating planar vehicle motion. Results show that this property is preserved, when combining these information sources with vision. Furthermore, the accuracy obtained from vision-only in direction estimation is improved, primarily in situations in which there are few matched visual features.

This paper describes a method for estimating the 6-DoF viewing parameters of a calibrated vehicle-mounted camera. Visual features are combined with standard in-vehicle sensors and a single-track vehicle motion model in a bundle adjustment framework to produce a jointly optimal viewing parameter estimate. Results show that the vehicle motion model in combination with in-vehicle sensors exhibit good accuracy in estimating planar vehicle motion. This property is preserved, when combining these information sources with vision. Furthermore, the accuracy obtained from vision-only in direction estimation is not only maintained, but in fact further improved, primarily in situations where the matched visual features are few.

This paper describes a framework which uses augmented reality for evaluating the performance of mobile computer vision systems. Computer vision systems use primarily image data to interpret the surrounding world, e.g to detect, classify and track objects. The performance of mobile computer vision systems acting in unknown environments is inherently difficult to evaluate since, often, obtaining ground truth data is problematic. The proposed novel framework exploits the possibility to add virtual agents into a real data sequence collected in an unknown environment, thus making it possible to efficiently create augmented data sequences, including ground truth, to be used for performance evaluation. Varying the content in the data sequence by adding different virtual agents is straightforward, making the proposed framework very flexible. The method has been implemented and tested on a pedestrian detection system used for automotive collision avoidance. Preliminary results show that the method has potential to replace and complement physical testing, for instance by creating collision scenarios, which are difficult to test in reality.

NMR spectroscopy is a powerful technique used in protein research for comprehensive functional characterizations, e.g. structure determination at atomic resolution. Due to the molecular size (typically≫1000 atoms), protein NMR spectra contain a large number of signal frequencies. Resolving these requires high-dimensional spectroscopy. However, when the number of frequency exceeds three, conventional approaches start to demand unrealistic long experiment time, and the data analysis becomes challenging. In this paper we explore a combination of novel methods: Data from 5D NMR experiments are recorded as a series of 2D projections, which are then subjected to 2D subband filters and 2D LS-ESPRIT for estimation of signal parameters. Based on the relations established between 5D NMR signals and their 2D counterparts, projection spectroscopy allows to extract highly similar information as what would be found in conventional 5D NMR experiments; however, while the latter would require months of experiment time, the recording of all necessary projections can be accomplished within 1–2 days. Preliminary results show the efficiency of the method with respect to accuracy and resolution of the parameter estimates as compared with conventional methods.

UNLABELLED: PRODECOMP (projection decomposition) is an implementation of a multi-way decomposition algorithm for the analysis of two-dimensional projections of high-dimensional nuclear magnetic resonance spectra. The newest version, PRODECOMPv3, features a dramatic speedup, more reliable decompositions, a substantial reduction in memory demands, a new graphical user interface and integration into third-party software. These improvements extend the applicability of decompositions to novel types of NMR data on proteins, yielding backbone and side-chain assignments as well as structural information, and therewith enabling complete characterizations of proteins. AVAILABILITY: Program, short manual and an example calculation are freely available at www2.chem.gu.se/bcbp/nmr/prodecomp.html.

Augmented Chemistry (AC) is an application that utilizes a tangible user interface (TUI) for organic chemistry education. The empirical evaluation described in this paper compares learning effectiveness and user acceptance of AC versus the more traditional ball-and-stick model (BSM). Learning effectiveness results were almost the same for both learning environments. User preference and rankings, using NASA-TLX and SUMI, showed more differences and it was therefore decided to focus mainly on improving these aspects in a re-design of the AC system. For enhanced interaction, keyboard-free system configuration, and internal/external database (DB) access, a graphical user interface (GUI) has been incorporated into the TUI. Three-dimensional (3D) rendering has also been improved using shadows and related effects, thereby enhancing depth perception. The re-designed AC system was then compared to the old system by means of a small qualitative user study. This user study showed an improvement in subjective opinions a out the system's ease of use and ease of learning.