Search Results

In the next 20 years fully autonomous vehicles are expected to be in the market. The advance on their development is creating paradigm shifts on different automotive related research areas. Vehicle interiors design and human vehicle interaction are evolving to enable interaction flexibility inside the cars. However, most of today’s vehicle manufacturers’ autonomous car concepts maintain the steering wheel as a control element. While this approach allows the driver to take over the vehicle route if needed, it causes a constraint in the previously mentioned interaction flexibility. Other approaches, such as the one proposed by Google, enable interaction flexibility by removing the steering wheel and accelerator and brake pedals. However, this prevents the users to take control over the vehicle route if needed, not allowing them to make on-route spontaneous decisions, such as stopping at a specific point of interest.

Image segmentation has historically been a technique for analyzing terrain for military autonomous vehicles. One of the weaknesses of image segmentation from camera data is that it lacks depth information, and it can be affected by environment lighting. Light detection and ranging (LiDAR) is an emerging technology in image segmentation that is able to estimate distances to the objects it detects. One advantage of LiDAR is the ability to gather accurate distances regardless of day, night, shadows, or glare. This study examines LiDAR and camera image segmentation fusion to improve an advanced driver-assistance systems (ADAS) algorithm for off-road autonomous military vehicles. The volume of points generated by LiDAR provides the vehicle with distance and spatial data surrounding the vehicle.

The application of virtual engineering methods can streamline the product design process through improved collaboration opportunities among the technical staff and facilitate additive manufacturing processes. A product digital twin can be created using the available computer-aided design and analytical mathematical models to numerically explore the current and future system performance based on operating cycles. The strategic decision to implement a digital twin is of interest to companies, whether the required financial and workforce resources will be worthwhile. In this paper, two metrics are introduced to assist management teams in evaluating the technology potential. The usefulness and time savings metrics will be presented with accompanying definitions. A case study highlights the usefulness metric for the “Deep Orange” prototype vehicle, an innovative off-road hybrid vehicle designed and fabricated at Clemson University.

Automotive drive-by-wire systems have enabled greater mobility options for individuals with physical disabilities. To further expand the driving paradigm, a need exists to consider an alternative vehicle steering mechanism to meet specific needs and constraints. In this study, a cellphone steering controller was investigated using a fixed-base driving simulator. The cellphone incorporated the direction control of the vehicle through roll motion, as well as the brake and throttle functionality through pitch motion, a design that can assist disabled drivers by excluding extensive arm and leg movements. Human test subjects evaluated the cellphone with conventional vehicle control strategy through a series of roadway maneuvers. Specifically, two distinctive driving situations were studied: a) obstacle avoidance test, and b) city road traveling test. A conventional steering wheel with self-centering force feedback tuning was used for all the driving events for comparison.

Unmanned ground vehicles (UGVs) may encounter difficulties accommodating environmental uncertainties and system degradations during harsh conditions. However, human experience and onboard intelligence can may help mitigate such cases. Unfortunately, human operators have cognition limits when directly supervising multiple UGVs. Ideally, an automated decision aid can be designed that empowers the human operator to supervise the UGVs. In this paper, we consider a connected UGV platoon under cyber attacks that may disrupt safety and degrade performance. An observer-based resilient control strategy is designed to mitigate the effects of vehicle-to-vehicle (V2V) cyber attacks. In addition, each UGV generates both internal and external evaluations based on the platoons performance metrics. A cloud-based trust-based information management system collects these evaluations to detect abnormal UGV platoon behaviors.

The ability to independently transfer into and out of a vehicle is essential for many wheelchair users to achieve driving independence. The purpose of the current study is to build upon the previous exploratory study that investigated the transfer strategies of wheelchair users by observing YouTube videos. This observational study videotaped five wheelchair users transferring from their wheelchairs into two research vehicles, a small and mid-size sedan that were equipped with a 50mm grid. The goal of this study was to use these videos and vehicle grids to precisely identify ingress and egress motions as well as “touch points” in a controlled setting with a small sample of five male wheelchair users. Using the videos from multiple different camera perspectives, the participants’ ingress and egress transfers were coded, documenting the touch points and step-by-step action sequences.

Vehicle dynamics simulation is one of the newest and most valuable technologies being applied in the racing world today. Professional designers and race teams are investing heavily to test and improve the dynamics of their suspension systems through this new technology. This paper discusses the testing of one of Clemson University's most recent Formula SAE racecars on a seven-poster vehicle dynamics simulator; commonly known as a “shaker rig.” Testing of the current dampers using a shock dynamometer was conducted prior to testing and results are included for further support of conclusions. The body of the paper is a discussion of the setup and testing procedures involved with the dynamic simulator. The results obtained from the dynamic simulator tests are then analyzed in conjunction with the shock dynamometer results. Conclusions are formed from test results and methods for future improvements to be applied in Formula SAE racing are suggested.

In the U.S., the teenage driving population is at the highest risk of being involved in a crash. Teens often demonstrate poor vehicle control skills and poor ability to identify hazards, thus proper understanding of automotive indicators and warnings may be even more critical for this population. This research evaluates teen drivers’, between 15 to 17 years of age, understanding of symbols from vehicles featuring advanced driving assistant systems and multiple powertrain configurations. Teen drivers’ (N=72) understanding of automotive symbols was compared to three other groups with specialized driving experience and technical knowledge: automotive engineering graduate students (N=48), driver rehabilitation specialists (N=16), and performance driving instructors (N=15). Participants matched 42 symbols to their descriptions and then selected the five symbols they considered most important.

Autonomous driving technologies can provide better safety, comfort and efficiency for future transportation systems. Most research in this area has mainly been focused on developing sensing and control approaches to achieve various autonomous driving functions. Very little of this research, however, has studied how to efficiently handle sensing exceptions. A simple exception measured by any of the sensors may lead to failures in autonomous driving functions. The autonomous vehicles are then supposed to be sent back to manufacturers for repair, which takes both time and money. This paper introduces an efficient approach to make human drivers able to online teach autonomous vehicles to drive under sensing exceptions. A human-vehicle teaching-and-learning framework for autonomous driving is proposed and the human teaching and vehicle learning processes for handling sensing exceptions in autonomous vehicles are designed in detail.

Energy management of hybrid vehicle has been a widely researched area. Strategies like dynamic programming (DP), equivalent consumption minimization strategy (ECMS), Pontryagin’s minimum principle (PMP) are well analyzed in literatures. However, the adaptive optimization work is still lacking, especially for reinforcement learning (RL). In this paper, Q-learning, as one of the model-free reinforcement learning method, is implemented in a mid-size 48V mild parallel hybrid electric vehicle (HEV) framework to optimize the fuel economy. Different from other RL work in HEV, this paper only considers vehicle speed and vehicle torque demand as the Q-learning states. SOC is not included for the reduction of state dimension. This paper focuses on showing that the EMS with non-SOC state vectors are capable of controlling the vehicle and outputting satisfactory results. Electric motor torque demand is chosen as action.

It’s important to predict human actions in the industry assembly process. Foreseeing future actions before they happened is an essential part for flexible human-robot collaboration and crucial to safety issues. Vision-based human action prediction from videos provides intuitive and adequate knowledge for many complex applications. This problem can be interpreted as deducing the next action of people from a short video clip. The history information needs to be considered to learn these relations among time steps for predicting the future steps. However, it is difficult to extract the history information and use it to infer the future situation with traditional methods. In this scenario, a model is needed to handle the spatial and temporal details stored in the past human motions and construct the future action based on limited accessible human demonstrations.

Fully autonomous vehicles have the potential to fundamentally transform the future transportation system. While previous research has examined individuals’ perceptions towards fully autonomous vehicles, a complete understanding of attitudes and opinions across the lifespan is unknown. Therefore, individuals’ awareness, acceptance, and preferences towards autonomous vehicles were obtained from 75 participants through interviews with three diverse groups of participants: 20 automotive engineering graduate students who were building an autonomous concept vehicle, 21 non-technical adults, and 34 senior citizens. The results showed that regardless of age, an individual’s readiness to ride in a fully autonomous vehicle and the vehicle’s requirements were influenced by the users’ understanding of autonomous vehicles.

In this paper, we present a framework for the robot to learn how to place objects to a workpiece by learning from humans in smart manufacturing. In the proposed framework, the rational scene dictionary (RSD) corresponding to the keyframes of task (KFT) are used to identify the general object-action-location relationships. The Generalized Voronoi Diagrams (GVD) based contour is used to determine the relative position and orientation between the object and the corresponding workpiece at the final state. In the learning phase, we keep tracking the image segments in the human demonstration. For the moment when a spatial relation of some segments are changed in a discontinuous way, the state changes are recorded by the RSD. KFT is abstracted after traversing and searching in RSD, while the relative position and orientation of the object and the corresponding mount are presented by GVD-based contours for the keyframes.

Digital twin technology has become impactful in Industry 4.0 as it enables engineers to design, simulate, and analyze complex systems and products. As a result of the synergy between physical and virtual realms, innovation in the “real twin” or actual product is more effectively fostered. The availability of verified computer models that describe the target system is important for realistic simulations that provide operating behaviors that can be leveraged for future design studies or predictive maintenance algorithms. In this paper, a digital twin is created for an offroad tracked vehicle that can operate in either autonomous or remote-control modes. Mathematical models are presented and implemented to describe the twin track and vehicle chassis governing dynamics. These components are interfaced through the nonlinear suspension elements and distributed bogies.

Current military operations in Iraq and Afghanistan are unique because the battlefield can be described as a non-linear, asymmetrical environment. Units operate in zones that are susceptible to enemy contact from any direction at any time. The response to these issues has been the addition of add-on armor to HMMWV's and other tactical vehicles. The retro-fitting of armor to these vehicles has resulted in many accidents due to rollover and instability. The goal of this paper is to determine possible causes of the instability and rollover of up-armored tactical vehicles and to develop simulation tools that can analyze the steady-state and transient dynamics of the vehicles. Models and simulations include a steady-state rollover scenario, analysis of understeer gradient, and a transient handling analysis that uses models of both a human driver and a vehicle to analyze vehicle response to an obstacle avoidance maneuver.

Learning only from a small set of examples remains a huge challenge in machine learning. Despite recent breakthroughs in the applications of neural networks, the applicability of these techniques has been limited by the requirement for large amounts of training data. What’s more, the standard supervised machine learning method does not provide a satisfactory solution for learning new concepts from little data. However, the ability to learn enough information from few samples has been demonstrated in humans. This suggests that humans may make use of prior knowledge of a previously learned model when learning new ones on a small amount of training examples. In the area of autonomous driving, the model learns to drive the vehicle with training data from humans, and most machine learning based control algorithms require training on very large datasets. Collecting and constructing training data set takes a huge amount of time and needs specific knowledge to gather relevant information.

Despite the growing acceptance of driver education programs, there remains a class of unpredictable and dangerous vehicle situations for which very little training or education is offered. Included in this list is a condition called run-off-the-road (ROR) which occurs when the wheels of the vehicle leave the paved surface of the road and begin to travel on the lower friction surfaces of the shoulder or side of the road. Unsuccessful recovery from ROR contributes to an overwhelming percentage of motorized vehicle crash fatalities and injuries. Most present solutions involve roadway infrastructure management and driver assistance systems. While these solutions have contributed varying amounts of success to the ROR problem, they remain limited as they do not directly address the critical cause of ROR crashes which is driver performance errors.

Improper fit in a vehicle will affect a driver’s ability to reach the steering wheel and pedals, view the roadway and instrument gauges, and allow vehicle safety features to protect the driver during a crash. CarFit® is a community outreach program to educate older drivers on proper “fit” within their personal vehicle. A subset of measurements from CarFit® were used to quantify the “fit” of 97 older drivers over 60 and 20 younger drivers, ages 30-39, in their personal vehicles. Binary, logistic regression was used to assess the likelihood of drivers meeting the CarFit® measurement criteria prior to and after CarFit® education. The results showed older drivers were five times more likely than younger drivers to meet the CarFit® criteria for line of sight above the steering wheel, suggesting that younger drivers would also benefit from CarFit® education.

Since 1989, ISO has published procedures for developing and testing public information symbols (ISO 9186), while the SAE standard for in-vehicle icon comprehension testing (SAE J2830) was first published in 2008. Neither testing method was designed to evaluate the comprehension of symbols in modern vehicles that offer digital instrument cluster interfaces that afford new levels of flexibility to further improve drivers’ understanding of symbols. Using a driving simulator equipped with an eye tracker, this study investigated drivers’ understanding of six automotive symbols presented on in-vehicle displays. Participants included 24 teens, 24 adults, and 24 senior drivers. Symbols were presented in a symbol-only, symbol + short text descriptions, and symbol + long text description conditions. Participants’ symbol comprehension, driving performance, reaction times, and eye glance times were measured.

With the dramatic increase in vehicle technology, the availability of a wide range of powertrains, and the development of advanced driver assistant systems (ADAS), instrument cluster interfaces have become more complex, increasing the demand on drivers. Understanding the needs and preferences of a diverse group of drivers is essential for the development of digital instrument cluster interfaces that improve driver’s understanding of critical information about the vehicle. This study investigated drivers’ understanding and preferences related to powertrain and ADAS symbols presented on instrument clusters. Participants answered questions that evaluated nine symbol’s comprehension, familiarity, and helpfulness. Then, participants were presented with information from the owner’s manual for each symbol and responded if the information changed their understanding of the symbol.