Search Results

Electrification is the well-accepted solution to address carbon emissions and modernize vehicle controls. Batteries play a critical in the journey of electrification and modernization with battery voltage prediction as the foundation for safe and efficient operation. Due to its strong dependency on prior information, battery voltage was estimated with recurrent neural network methods in the recent literatures exploring a variety of deep learning techniques to estimate battery behaviors. In these studies, standard recurrent neural networks, gated recurrent units, and long-short term memory are popular neural network architectures under review. However, in most cases, each neural network architecture is individually assessed and therefore the knowledge about comparative study among three neural network architecture is limited. In addition, many literatures only studied either the dynamic voltage response or the voltage relaxation.

UGV (Unmanned Ground Vehicle) is gaining increasing amounts of attention from both industry and academic communities in recent years. Local trajectory planning is one of the most important parts of designing a UGV. However, there has been little research into local trajectory planning and tracking, and current research has not considered the dynamic of the surrounding environment. Therefore, we propose a dynamic local trajectory planning and tracking method for UGV driving on the highway in this paper. The method proposed in this paper can make the UGV travel from the navigation starting point to the navigation end point without collision on both straight and curve road. The key technology for this method is trajectory planning, trajectory tracking and trajectory update signal generation. Trajectory planning algorithm calculates a reference trajectory satisfying the demands of safety, comfort and traffic efficiency.

The dynamic trajectory planning problem for automatic vehicles in complex traffic scenarios is investigated in this paper. A hierarchical motion planning framework is developed to complete the complex planning task. An improved dangerous potential field in the curvilinear coordinate system is constructed to describe the collision risk of automatic vehicles accurately instead of the discrete Gaussian convolution algorithm. At the same time, the driving comfort is also considered in order to generate an optimal, smooth, collision-free and feasible path in dynamics. The optimal path can be mapped into the Cartesian coordinate system simply and conveniently. Furthermore, a velocity profile considering practical vehicle dynamics is also presented to improve the safety and the comfort in driving. The effectiveness of the proposed dynamic trajectory planning is verified by numerical simulation for several typical traffic scenarios.

Vehicle weight reduction has become one of the essential research areas in the automotive industry. It is important to perform design optimization of Body-in-White (BIW) at the concept design phase so that to reduce the development cost and shorten the time-to-market in later stages. Finite Element (FE) models are commonly used for vehicle design. However, even with increasing speed of computers, the simulation of FE models is still too time-consuming due to the increased complexity of models. This calls for the development of a systematic and efficient approach that can effectively perform vehicle weight reduction, while satisfying the stringent safety regulations and constraints of development time and cost. In this paper, an efficient BIW weight reduction approach is proposed with consideration of complex safety and stiffness performances. A parametric BIW FE model is first constructed, followed by the building of surrogate models for the responses of interest.

We present research in progress to develop and implement a transportable instrumentation package (TIP) to collect driver data in a vehicle. The overall objective of the project is to investigate the symbiotic relationship between humans and their vehicles. We first describe the state-of-art technologies to build the components of TIP that meet the criteria of ease of installation, minimal interference with driving, and sufficient signals to monitor driver state and condition. This method is a viable alternative to current practice which is to first develop a fully instrumented test vehicle, often at great expense, and use it to collect data from each participant as he/she drives a prescribed route. Another practice, as for example currently being used in the SHRP-2 naturalistic driving study, is to install the appropriate instrumentation for data collection in each individual's vehicle, often requiring several hours.

Automated driving is considered a key technology for reducing traffic accidents, improving road utilization, and enhancing transportation economy and thus has received extensive attention from academia and industry in recent years. Although recent improvements in artificial intelligence are beginning to be integrated into vehicles, current AD technology is still far from matching or exceeding the level of human driving ability. The key technologies that need to be developed include achieving a deep understanding and cognition of traffic scenarios and highly intelligent decision-making. Automated Vehicles, the Driving Brain, and Artificial Intelligenceaddresses brain-inspired driving and learning from the human brain's cognitive, thinking, reasoning, and memory abilities. This report presents a few unaddressed issues related to brain-inspired driving, including the cognitive mechanism, architecture implementation, scenario cognition, policy learning, testing, and validation.

This paper presents results of a three-phase research project aimed at understanding how future automotive interior materials should be selected or designed to satisfy the needs of the customers. The first project phase involved development of 22 five-point semantic differential scales to measure visual, visual-tactile, and evaluative characteristics of the materials. Some examples of the adjective pairs used to create the semantic differential scales to measure the perceptual characteristics of the material are: a) Visual: Light vs. Dark, Flat vs. Shiny, etc., b) Visual-Tactile: Smooth vs. Rough, Slippery vs. Sticky, Compressive vs. Non-Compressive, Textured vs. Non-Textured, etc., c) Evaluative (overall perception): Dislike vs. Like, Fake vs. Genuine, Cheap vs. Expensive, etc. In the second phase, 12 younger and 12 older drivers were asked to evaluate a number of different automotive interior materials by using the 22 semantic differential scales.

This paper presents results of a research project conducted to develop a methodology and to refine the specifications of a small, low mass, low cost vehicle being developed at the University of Michigan-Dearborn. The challenge was to assure that the design would meet the needs and expectations of customers in three different countries, namely, China, India and the United States. U.S, Chinese and Indian students studying on the university campus represented customers from their respective countries for our surveys and provided us with the necessary data on: 1) Importance of various vehicle level attributes to the entry level small car customer, 2) Preferences to various features, and 3) Direction magnitude estimation on parameters to size the vehicle for each of the three markets.

This paper describes a research project currently in-progress to develop a parametric model of a vehicle for use in early design stages of a new vehicle program. The model requires key input parameters to define the kind of new vehicle to be designed — in terms of details such as its intended driver/user population, vehicle type (e.g. 2-box, 3-box designs), and some key exterior and interior dimensions related to its size and proportions. The model computes and graphically displays interior package, ergonomics zones for driver controls and displays, and field of views through window openings. It also allows importing or inputting and superimposing and manipulating exterior surfaces created by a designer to assess compatibility between the interior occupant package and the vehicle exterior.

As vehicle fuel economy continues to grow in importance, the ability to accurately measure the level of efficiency on all driveline components is required. A standardized test procedure enables manufacturers and suppliers to measure component losses consistently and provides data to make comparisons. In addition, the procedure offers a reliable process to assess enablers for efficiency improvements. Previous published studies have outlined the development of a comprehensive test procedure to measure transfer case speed-dependent parasitic losses at key speed, load, and environmental conditions. This paper will take the same basic approach for the Power Transfer Units (PTUs) used on Front Wheel Drive (FWD) based All Wheel Drive (AWD) vehicles. Factors included in the assessment include single and multi-stage PTUs, fluid levels, break-in process, and temperature effects.

The automotive industry is expected to accelerate the transition to revolutionary products, rapid changes in technology and increasing technological sophistication. This will require engineers to advance their knowledge, connect and integrate different areas of knowledge and be skilled in synthesis. In addition, they must learn to work in cross-disciplinary teams and adopt a systems approach. The College of Engineering and Computer Science (CECS) at the University of Michigan-Dearborn (UM-Dearborn) responded by creating interdisciplinary MS and Ph.D. programs in automotive systems engineering (ASE) and augmenting them with hands-on research. Students at the undergraduate level can also engage in numerous ASE activities. UM-Dearborn's ASE programs offer interesting and possibly unique advantages. The first is that it offers a spectrum of ASE degree and credit programs, from the MS to the Ph.D. to continuing education.

The research on coasting resistance is vital to electric vehicles, since the smaller the coasting resistance, the longer the coast-down distance. Vehicle coast resistance consists of rolling resistance, vehicle inner resistance and the aerodynamic drag. The vehicle inner resistance is mainly caused by driveline’s friction loss and oil splash loss. The rolling resistance is decided by tire resistance coefficient, which is influenced by tires and road conditions. And the aerodynamic drag is affected by vehicle’s shape and air. In this paper, four factors including tire pressure, road surface condition, atmosphere temperature, and recirculation on or off are examined. Experimental tests have been conducted on three different vehicles: one subcompact sedan, one compact sedan and one subcompact SUV. Then experimental results have been imported to simulation model to investigate the corresponding influence on NEDC range.

Computer programs and models are playing an increasing role in simulating vehicle crashworthiness, dynamic, and fuel efficiency. To maximize the effectiveness of these models, the validity and predictive capabilities of these models need to be assessed quantitatively. For a successful implementation of Computer Aided Engineering (CAE) models as an integrated part of the current vehicle development process, it is necessary to develop objective validation metric that has the desirable metric properties to quantify the discrepancy between multiple tests and simulation results. However, most of the outputs of dynamic systems are multiple functional responses, such as time history series. This calls for the development of an objective metric that can evaluate the differences of the multiple time histories as well as the key features under uncertainty.

Seat comfort is a highly subjective attribute and depends on a wide range of factors, but the successful prediction of seat comfort from a group of relevant variables can hold the promise of eliminating the need for time-consuming subjective evaluations during the early stages of seat cushion selection and development. This research presents the subjective seat comfort data of a group of 30 participants using a controlled range of seat foam samples, and attempts to correlate this attribute with a) the anthropometric and demographic characteristics of the participants, b) the objective pressure distribution at the body-seat interface and c) properties of the various foam samples that were used for the test.

The automotive interior suppliers are challenged to develop materials, that not only perform functionally, but also provide the right combination sensory experience (e.g. visual appeal, tactile feeling) and brand differentiation at very competitive costs. Therefore, the objective of this research presented in this paper is to develop a methodology that can be used to measure customer perception of interior materials and to come up with a unique system for assessing value of different interior materials. The overall methodology involves the application of a number of psychophysical measurement methods (e.g. Semantic Differential Scaling) and statistical methods to assess: 1) overall customer perceived quality of materials, 2) elements (or attributes) of perception, and 3) value of materials from OEM's viewpoint in terms of the measurement of perception of quality divided by a measure of cost.

The engine operating point (EOP), which is determined by the engine speed and torque, is an important part of a vehicle's powertrain performance and it impacts FC, available propulsion power, and emissions. Predicting instantaneous EOP in real-time subject to dynamic driver behaviour and environmental conditions is a challenging problem, and in existing literature, engine performance is predicted based on internal powertrain parameters. However, a driver cannot directly influence these internal parameters in real-time and can only accommodate changes in driving behaviour and cabin temperature. It would be beneficial to develop a direct relationship between the vehicle-level parameters that a driver could influence in real-time, and the instantaneous EOP. Such a relationship can be exploited to dynamically optimize engine performance.