Search Results

Forecasting the motion of the leading vehicle is a critical task for connected autonomous vehicles as it provides an efficient way to model the leading-following vehicle behavior and analyze the interactions. In this study, a personalized time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The method enables a precise, personalized trajectory prediction for leading vehicles with limited inter-vehicle communication signals, such as vehicle speed, acceleration, space headway, and time headway of the front vehicles. Based on the learning nature of human beings that a human always tries to solve problems based on grouping and similar experience, three different driving styles are first recognized based on an unsupervised clustering with a Gaussian Mixture Model (GMM).

Vehicles designed for the Baja SAE competition operate on challenging off-road terrain and may be required to withstand accidental impacts with other vehicles and obstacles. Although significant injuries are not commonly observed in this competition, it is important to understand the performance of these vehicles in crash scenarios to optimize frame design and vehicle performance. A finite element model comprising the vehicle chassis and associated subsystem weights, a Hybrid III occupant, and safety systems was developed to evaluate vehicle impact performance in frontal crash. Impacts velocities up to 36 kph were considered, and no significant risk of head, neck or thoracic injury was predicted. Neck injury (as predicted by Nij) and chest acceleration were found to be the most critical, reaching 66% and 75% of their threshold values, respectively, in the most severe crashes considered.

Robust lane marking detection remains a challenge, particularly in temperate climates where markings degrade rapidly due to winter conditions and snow removal efforts. In previous work, dynamic Bayesian networks with heuristic features were used with the feature distributions trained using semi-supervised expectation maximization, which greatly reduced sensitivity to initialization. This work has been extended in three important respects. First, the tracking formulation used in previous work has been corrected to prevent false positives in situations where only poor RANSAC hypotheses were generated. Second, the null hypothesis is reformulated to guarantee that detected hypotheses satisfy a minimum likelihood. Third, the computational requirements have been greatly reduced by computing an upper bound on the marginal likelihood of all part hypotheses upon generation and rejecting parts with an upper bound less likely than the null hypothesis.

Recently, the development of braking assistance system has largely benefit the safety of both driver and pedestrians. A robust prediction and detection of driver braking intention will enable driving assistance system response to traffic situation correctly and improve the driving experience of intelligent vehicles. In this paper, two types unsupervised clustering methods are used to build a driver braking intention predictor. Unsupervised machine learning algorithms has been widely used in clustering and pattern mining in previous researches. The proposed unsupervised learning algorithms can accurately recognize the braking maneuver based on vehicle data captured with CAN bus. The braking maneuver along with other driving maneuvers such as normal driving will be clustered and the results from different algorithms which are K-means and Gaussian mixture model (GMM) will be compared.

The automobile industry has been undergoing a transition from fossil fuels to a low emission platform due to stricter environmental policies and energy security considerations. Electric vehicles, powered by lithium-ion batteries, have started to attain a noticeable market share recently due to their stable performance and maturity as a technology. However, electric vehicles continue to suffer from two disadvantages that have limited widespread adoption: charging time and energy density. To mitigate these challenges, vehicle Original Equipment Manufacturers (OEMs) have developed different vehicle architectures to extend the vehicle range. This work seeks to compare various powertrains, including: combined power battery electric vehicles (BEV) (zinc-air and lithium-ion battery), zero emission fuel cell vehicles (FCV)), conventional gasoline powered vehicles (baseline internal combustion vehicle), and ICE engine extended range hybrid electric vehicle.

A three dimensional IR-TRACC (Infrared Telescope Rod for Assessment of Chest Compression) was designed for the Test Device for Human Occupant Restraint (THOR) in recent years to measure chest deflections. Due to the design intricateness, the deflection calculation from the measurements is sophisticated. An algorithm was developed in this paper to calculate the three dimensional deflections of the chest. The algorithm calculates the compression and also converts the results to the local spine coordinate system so that it can correlate with the Post Mortem Human Subject (PMHS) measurements for injury calculation. The method was also verified by a finite element calculation for accuracy, comparing the calculation from the corresponding model output and the direct point to point measurements. In addition, the IR-TRACC calibration methods are discussed in this paper.

Dynamic modelling of the contact between the tires of automobiles and the road surface is crucial for accurate and effective vehicle dynamic simulation and the development of various driving controllers. Furthermore, an accurate prediction of the rolling resistance is needed for powertrain controllers and controllers designed to reduce fuel consumption and engine emissions. Existing models of tires include physics-based analytical models, finite element based models, black box models, and data driven empirical models. The main issue with these approaches is that none of these models offer the balance between accuracy of simulation and computational cost that is required for the model-based development cycle. To address this issue, we present a volumetric approach to model the forces/moments between the tire and the road for vehicle dynamic simulations.

The development of a comprehensive battery simulator is essential for future improvements in the durability, performance and service life of lithium-ion batteries. Although simulations can never replace actual experimental data, they can still be used to provide valuable insights into the performance of the battery, especially under different operating conditions. In addition, a single-cell model can be easily extended to the pack level and can be used in the optimization of a battery pack. The first step in building a simulator is to create a model that can effectively capture both the voltage response and thermal behavior of the battery. Since these effects are coupled together, creating a robust simulator requires modeling both components. This paper will develop a battery simulator, where the entire battery model will be composed of four smaller submodels: a heat generation model, a thermal model, a battery parameter model and a voltage response model.

A compact sized vehicle that has a narrow track could solve problems caused by vehicle congestion and limited parking spaces in a mega city. Having a smaller footprint reduces the vehicle's total weight which would decrease overall vehicle power consumption. Also a smaller and narrower vehicle could travel easily through tight and congested roads that would speed up the traffic flow and hence decrease the overall traffic volume in urban areas. As an additional benefit of having a narrow track length, a driver can experience similar motorcycle riding experience without worrying about bad weather conditions since a driver sits in a weather protected cabin. However, reducing the vehicle's track causes instability in vehicle dynamics, which leads to higher possibility of rollovers if the vehicle is not controlled properly. A three wheel personal vehicle with an active tilting system is designed in MapleSim.

This paper proposes a vehicle performance/safety method using combined active steering and differential braking to achieve yaw stability and rollover avoidance. The advantages and disadvantages of active steering and differential braking control methods are identified under a variety of input signals, such as J-turn, sinusoidal, and fishhook inputs by using the implemented linear 4 DOF model. Also, the nonlinear model of the vehicle is evaluated and verified through individual and integrated controller. Each controller gives the correction steering angle and correction moment to the simplified steering and braking actuators. The integrated active steering and differential braking control are shown to be most efficient in achieving yaw stability and rollover avoidance, while active steering and differential braking control has been shown to improve the vehicle performance and safety only in yaw stability and rollover avoidance, respectively.

Today, commercially available drones have limited use-cases in the rapidly evolving community. However, with advances in drone and software technology, it is possible to utilize these aerial machines to solve problems in a variety of industries such as mining, medical, construction, and law enforcement. For example, in order to reduce time of investigation, Indiana State Police are currently utilizing ad-hoc commercial drones to reconstruct crash scenes for insurance and legal purposes. In this paper, we illustrate how to effectively integrate drones for in-vehicle services and real-time prediction for automotive applications. In order to accomplish this, we first integrate simpler controls such as voice-commands to control the drone from the vehicle. Next, we build smart prediction software that monitors vehicle behavior and reacts in real-time to collisions.

With the widespread development of automated driving systems (ADS), it is imperative that standardized testing methodologies be developed to assure safety and functionality. Scenario testing evaluates the behavior of an ADS-equipped subject vehicle (SV) in predefined driving scenarios. This paper compares four modes of performing such tests: closed-course testing with real actors, closed-course testing with surrogate actors, simulation testing, and closed-course testing with mixed reality. In a collaboration between the Waterloo Intelligent Systems Engineering (WISE) Lab and AAA, six automated driving scenario tests were executed on a closed course, in simulation, and in mixed reality. These tests involved the University of Waterloo’s automated vehicle, dubbed the “UW Moose”, as the SV, as well as pedestrians, other vehicles, and road debris.