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).

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.

In this study, application of differential braking strategy to remove the oscillatory instability or snaking behavior of an articulated steer vehicle is presented. First, a linearized model of the vehicle is described that is used to represent the equations of motion in the state-space form. Then, this model is utilized for designing a sliding mode controller to adjust the differential braking on the rear axle to stabilize the vehicle during the snaking. The performance of the resulting active control system is evaluated in different driving conditions by using the linearized model. Finally, the control system is incorporated into a virtual prototype of the vehicle in ADAMS, and its operation is examined. The results from the linear model analysis and simulations in ADAMS are reasonably consistent.

Due to the high power and energy density and also relative safety, lithium ion batteries are receiving increasing acceptability in industrial applications especially in transportation systems with electric traction such as electric vehicles and hybrid electric vehicles. In this regard, to ensure performance reliability, accurate modeling of calendar life of such batteries is a necessity. In fact, potential failure of Li-ion battery packs remains a barrier to commercialization. Battery pack life is a critical feature to warranty and maintenance planning for hybrid vehicles, and will require adaptive control systems to account for the loss in vehicle range, and loss in battery charge and discharge efficiency. Failure not only results in large replacement costs, but also potential safety concerns such as overheating or short circuiting which may lead to fires.

Machine learning (ML) plays an ever-increasing role in advanced automotive functionality for driver assistance and autonomous operation; however, its adequacy from the perspective of safety certification remains controversial. In this paper, we analyze the impacts that the use of ML within software has on the ISO 26262 safety lifecycle and ask what could be done to address them. We then provide a set of recommendations on how to adapt the standard to better accommodate ML.

This paper seeks to identify the refrigeration load of a hybrid electric truck in order to find the demand power required by the energy management system. To meet this objective, in addition to the power consumption of the refrigerator, the vehicle mass needs to be estimated. The Recursive Least Squares (RLS) method with forgetting factors is applied for this estimation. As an example of the application of this parameter identification, the estimated parameters are fed to the energy control strategy of a parallel hybrid truck. The control system calculates the demand power at each instant based on estimated parameters. Then, it decides how much power should be provided by available energy sources to minimize the total energy consumption. The simulation results show that the parameter identification can estimate the vehicle mass and refrigeration load very well which is led to have fairly accurate power demand prediction.

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.

Decision-making of lane-change for autonomous vehicles faces challenges due to the behavioral differences among human drivers in dynamic traffic environments. To enhance the performances of autonomous vehicles, this paper proposes a game theoretic decision-making method that considers the diverse Social Value Orientations (SVO) of drivers. To begin with, trajectory features are extracted from the NGSIM dataset, followed by the application of Inverse Reinforcement Learning (IRL) to determine the reward preferences exhibited by drivers with distinct Social Value Orientation (SVO) during their decision-making process. Subsequently, a reward function is formulated, considering the factors of safety, efficiency, and comfort. To tackle the challenges associated with interaction, a Stackelberg game model is employed.

Safety assurance is a central concern for the development and societal acceptance of automated driving (AD) systems. Perception is a key aspect of AD that relies heavily on Machine Learning (ML). Despite the known challenges with the safety assurance of ML-based components, proposals have recently emerged for unit-level safety cases addressing these components. Unfortunately, AD safety cases express safety requirements at the system level and these efforts are missing the critical linking argument needed to integrate safety requirements at the system level with component performance requirements at the unit level. In this paper, we propose the Integration Safety Case for Perception (ISCaP), a generic template for such a linking safety argument specifically tailored for perception components. The template takes a deductive and formal approach to define strong traceability between levels.

An electric vehicle model has been developed with four direct-drive in-wheel motors. A high-level vehicle stability controller is proposed, which uses the principles of fuzzy logic to determine the corrective yaw moment required to minimize the vehicle sideslip and yaw rate errors. A genetic algorithm has been used to optimize the parameters of the fuzzy controller. The performance of the controller is evaluated as the vehicle is driven through a double-lane-change maneuver. Preliminary results indicate that the proposed control system has the ability to improve the performance of the vehicle considerably.

Driving Automation Systems (DAS) are subject to complex road environments and vehicle behaviors and increasingly rely on sophisticated sensors and Artificial Intelligence (AI). These properties give rise to unique safety faults stemming from specification insufficiencies and technological performance limitations, where sensors and AI introduce errors that vary in magnitude and temporal patterns, posing potential safety risks. The Safety of the Intended Functionality (SOTIF) standard emerges as a promising framework for addressing these concerns, focusing on scenario-based analysis to identify hazardous behaviors and their causes. Although the current standard provides a basic cause-and-effect model and high-level process guidance, it lacks concepts required to identify and evaluate hazardous errors, especially within the context of AI. This paper introduces two key contributions to bridge this gap.