Search Results

Environmental perception is considered an essential module for autonomous driving and Advanced Driver Assistance System (ADAS). Recently, deep Convolutional Neural Networks (CNNs) have become the State-of-the-Art with many different architectures in various object detection problems. However, performances of existing CNNs have been dropping when detecting small objects at a large distance. To deploy any environmental perception system in real world applications, it is important that the system achieves high accuracy regardless of the size of the object, distance, and weather conditions. In this paper, a robust sensor fused object detection system is proposed by utilizing the advantages of both vision and automotive radar sensors. The proposed system consists of three major components: 1) the Coordinate Conversion module, 2) Multi level-Sensor Fusion Detection (MSFD) system, and 3) Temporal Correlation filtering module.

Forward collision warning is one of the most challenging concerns in the safety of autonomous vehicles. A cooperation between many sensors such as LIDAR, Radar and camera helps to enhance the safety. Apart from the importance of having a reliable object detector, the safety system should have requisite capabilities to make reasonable decisions in the moment. In this work, we concentrate on detecting front vehicles of autonomous cars using a monocular camera, beyond only a detection method. In fact, we devise a solution based on a cooperation between a deep object detector and a reinforcement learning method to provide forward collision warning signals. The proposed method models the relation between acceleration, distance and collision point using the area of the bounding box related to the front vehicle. An agent of learning automata as a reinforcement learning method interacts with the environment to learn how to behave in eclectic hazardous situations.

As advanced vehicle controls and autonomy become mainstream in the automotive industry, the need to employ traditional mathematical models and control strategies arises for the purpose of simulating autonomous vehicle handling maneuvers. This study focuses on lane change maneuvers for autonomous vehicles driving at low speeds. The lane change methodology uses PID (Proportional-Integral-Derivative) controller to command the steering wheel angle, based on the yaw motion and lateral displacement of the vehicle. The controller was developed and tested on a bicycle model of an electric vehicle (a Chevrolet Bolt 2017), with the implementation done in MATLAB/Simulink. This simple mathematical model was chosen in order to limit computational demands, while still being capable of simulating a smooth lane change maneuver under the direction of the car’s mission planning module at modest levels of lateral acceleration.

Rapid changes in the automotive industry, including the growth of advanced vehicle controls and autonomy, are driving the need for more dedicated proving ground spaces where these systems can be developed safely. To address this need, Kettering University has created the GM Mobility Research Center, a 21-acre proving ground located in Flint, Michigan at the former “Chevy in the Hole” factory location. Construction of a proving ground on this site represents a beneficial redevelopment of an industrial brownfield, as well as a significant expansion of the test facilities available at the campus of Kettering University. Test facilities on the site include a road course and a test pad, along with a building that has garage space, a conference room, and an indoor observation platform. All of these facilities are available to the students and faculty of Kettering University, along with their industrial partners, for the purpose of engaging in advanced transportation research and education.

The fatal automobile accidents can be attributed to fatigued and distracted driving by drivers. Driver Monitoring Systems alert the distracted drivers by raising alarms. Most of the image based driver drowsiness detection systems face the challenge of failure proof performance in real time applications. Failure in face detection and other important part (eyes, nose and mouth) detections in real time cause the system to skip detections of blinking and yawning in few frames. In this paper, a real time robust and failure proof driver drowsiness detection system is proposed. The proposed system deploys a set of detection systems to detect face, blinking and yawning sequentially. A robust Multi-Task Convolutional Neural Network (MTCNN) with the capability of face alignment is used for face detection. This system attained 97% recall in the real time driving dataset collected. The detected face is passed on to ensemble of regression trees to detect the 68 facial landmarks.

Lean applications in product development usually start with manufacturing due to the relative experience of measuring improvements and identifying wastes in physical settings. The full potential of lean implementation in any product development, however, can only be realized when applied throughout the process, starting with early process. Considering that the first and most essential principle in lean implementation is the characterization of value from the customer's perspective, it is imperative that the proper definition of value is realized at the beginning of the process. In addition, streaming and flowing of this customer's specified value should be realized throughout the process from start to finish. This paper discusses the application of lean principles to integrated design and manufacturing phases of the Product Development Process.

Typically, when someone needs to perform occasional towing tasks, such as towing a boat on a trailer, they have two choices. They can either purchase a larger, more powerful vehicle than they require for their regular usage, or they can rent a larger vehicle when they need to tow something. In this project, we propose a third alternative: a trailer with an on-board power supply, which can be towed by a small vehicle. This system requires a means of sensing how much power the trailer's power supply should provide, and an appropriate control system to provide this power. In this project, we design and model the trailer, a standard small car, and the control system, and evaluate the concept's feasibility. We have selected a suitable power source for the trailer, a DC motor, coupled directly to the trailer's single drive wheel, which allow us to dispense with the need for a differential.

The objective of this project is to analyze potential design changes that can improve the performance of helical spring in an independent suspension. The performance of the helical spring was based upon the result measure of maximum value of stress acting on it and the amount displacement caused when the spring undergoes loading. The design changes in the spring were limited to coil cross section, spring diameter (constant & variable), pitch and length of the spring. The project was divided into Stage I & Stage II. For Stage I, using all the possible combinations of these design parameters, linear stress analysis was performed on different spring designs and their Stress and displacement results were evaluated. Based on the results, the spring designs were classified as over designed or under designed springs.

The torsional natural frequencies of axles equipped with limited slip differential clutches depend on whether or not the tires and clutches are slipping since the effective inertia at each end of the axle is different for slipping and non-slipping conditions. Limited slip axle vibrations are typically analyzed for one tire slipping and the other not since that is the case for which the limited slip clutches are used. Vibrations often arise, however, during normal turning when both drive tires have good traction.

Modeling and simulation of dynamic systems is not always a simple task. In this paper, the mathematical model of a 4 Degree Of Freedom (DOF) ride model is presented using a bond-graph technique with state energy variables. We believe that for the physical model as described in this research, the use of a bond-graph approach is the only feasible solution. Any attempt to use classical methods such as Lagrange equations or Newton's second law, will create tremendous difficulties in the transformation of a set of second order linear differential equations to a set of first order differential equations without violating the existence and the uniqueness of the solution of the differential equations, the only approach is the elimination of the damping of the tires, which makes the model unrealistic. The bond-graph model is transformed to a mathematical model. Matlab is used for writing a computer script that solves the engineering problem.

The kinematics and kinetics of a seven degree of freedom vehicle ride model with independent front and rear suspension are developed. Lagrange's equation is used to obtain the mathematical model of the vehicle. The equations of motion are transformed to state space equations in Linear Time Invariant (LTI) form. The effect of Chassis Design Factors (CDF) such as stabilizer bars, stiffness', Dynamic Index in Pitch (DIP) and mass ratio on the vehicle ride quality are investigated. The ride quality of the 3 dimensional vehicle that includes bounce, pitch, roll and unsprung masses motion is demonstrated in time domain response. The vehicle is considered as a Multi-Input-Multi-Output System (MIMO) subjected to deterministic ground inputs. Outputs of interest for the ride quality investigation are vertical and angular displacement and vertical accelerations. Numerical computer simulation analysis is performed using MATLAB® software.

Vehicle Dynamics play an important role in responsiveness of a vehicle. The performance of a vehicle depends on its ride and handling characteristics [1]. Handling is a measure of the directional response of a vehicle and one of the important characteristics from the vehicle dynamics point of view. The directional response of a vehicle depends on the dynamics of the steering system. A good steering control provides an accurate feedback about how the vehicle reacts to the road. In this paper, the powerful techniques of Bond graphs and state equations [2] are used to design and analyze the dynamics of a manual rack and pinion steering system. The author obtains the transfer function between the Angle of rotation of front tire and the Angle of rotation of steering wheel. The overall steering ratio of the bond graph modeled steering system is compared with the overall ratio of a similar vehicle to validate the model.

Bond graph modeling is a powerful technique to study the complex interactions occurring between various components in a system. A few investigations were carried out to study vehicle dynamics using Bondgraphs, but are limited to 2 degree of freedom systems [1,2&3]. In this work, a 4-DOF-vehicle model was developed using bond graphs. A frequency response analysis was also carried out to study the natural frequencies. This model was later validated using Lagrangian principles. The results correlated well for a typical passenger car using the manufacturer supplied information available in the public domain.

While many current vehicle network systems for body bus applications use event triggered analysis processes, the deterministic point of view raises concerns about system timing due to message latency. This paper studies the latency performance characteristics of a typical body bus vehicle network using event triggered analysis over the CAN bus.

This paper documents the electrical infrastructure design of a Hybrid Go Kart competition vehicle which includes a dual Fuel Cell power system, Ultra Capacitors for energy storage, and a dual AC induction motor capable of independent drive. The Kart was built primarily to compete in the 2009 Formula Zero international event. This paper emphasized the vehicle model and control strategy as a result of three (3) graduate student research projects. The vehicle was fabricated and tested but did not participate in the race competition since the race organization folded. The vehicle model was developed in Simulink to determine whether the fuel cell and ultra-capacitor combination will be sufficient for peak transient power requirement of 14 kW. The vehicle’s functional description and performance specifications are documented including the integration of the fuel cell power modules, energy storage system, power converters, and AC motor and motor controllers.

Numerous studies have documented the implantation of a 6-axis load cell in series with the tibial shaft and a limited number of studies have instrumented the femur for uniaxial load transduction. We are unaware of a single study seeking to instrument both anatomical segments. In addition, while the instrumentation processes have been described in textural and graphical detail, the dimensions and material choices for preparation jigs, potting cups, etc. are typically not given. In the current study, we have reviewed the available literature and have developed a modified preparation and implantation methodology. We also include complete designs appropriate for a reproduction of our process or modification of the methodology by the reader. The robustness of our technique was verified in a companion study in which whole, unembalmed cadavers were subjected to a HYGE frontal sled test without compromise of the instrumentation.

Object avoidance for autonomous driving is a vital factor in safe driving. When a vehicle travels from any random start places to any target positions in the milieu, an appropriate route must prevent static and moving obstacles. Having the accurate depth of each barrier in the scene can contribute to obstacle prevention. In recent years, precise depth estimation systems can be attributed to notable advances in Deep Neural Networks and hardware facilities/equipment. Several depth estimation methods for autonomous vehicles usually utilize lasers, structured light, and other reflections on the object surface to capture depth point clouds, complete surface modeling, and estimate scene depth maps. However, estimating precise depth maps is still challenging due to the computational complexity and time-consuming process issues. On the contrary, image-based depth estimation approaches have recently come to attention and can be applied for a broad range of applications.

As automated driving becomes more common, simulation of vehicle dynamics and control scenarios are increasingly important for investigating motion control approaches. In this work, a study of the differences between the Pure Pursuit and Stanley autonomous vehicle controllers, based on vehicle dynamics responses, is presented. Both are geometric controllers that use only immediate vehicle states, along with waypoint data, to control a vehicle’s future direction as it proceeds from point to point, and both are among the most popular lateral controllers in use today. The MATLAB Automated Driving Toolbox is employed to implement and virtually test the Pure Pursuit and Stanley lateral controllers in different driving scenarios. These include low intensity scenarios such as city driving, and emergency maneuvers such as the moose test.

Safety is considered one of the most important parameters when designing a ground vehicle. The adverse effect of weather on a vehicle can lead to a surge in safety issues and accidents. Several safety assistance systems are available in modern vehicles, which are designed to lessen the negative effects of weather hazards. Although these safety systems can intervene during crucial conditions to avoid accidents, driving a vehicle on snowy or icy terrain can still be a challenging task. Road conditions with the least tire-road friction often results in poor vehicle handling, and without any kind of safety system it can lead to mishaps. With the use of Adams Car software and vehicle dynamics modeling, a realistic relationship between the vehicle and road surface may be established. The simulation can be used to have a better understanding of vehicle handling in snowy and icy conditions, tire-ice interaction, and tire modeling.

Lane marks are an important aspect for autonomous driving. Autonomous vehicles rely on lane mark information to determine a safe and legal path to drive. In this paper an approach to estimate lane lines on straight or slightly curved roads using a LiDAR unit for autonomous vehicles is presented. By comparing the difference in elevation of LiDAR channels, a drivable region is defined. The presented approach used in this paper differs from previous LiDAR lane line detection methods by reducing the drivable region from three to two dimensions exploring only the x-y trace. In addition, potential lane markings are extracted by filtering a range of intensity values as opposed to the traditional approach of comparing neighboring intensity values. Further, by calculating the standard deviation of the potential lane markings in the y-axis, the data can be further refined to specific points of interest.