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.

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.

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.

A Task and Message Schedule for a FlexCAN-based Hybrid-Electric vehicle (HEV) functional unit is described. The resulting schedule is a component of an incremental message and task scheduling approach based on a time-driven message schedule and priority-driven task schedule. The HEV functional unit involves the combined control and monitoring functions of an internal combustion engine working in parallel with a permanent magnet synchronous motor. The control algorithm for the synchronous motor has been simulated using VHDL-AMS. The global message system is supported by FlexCAN and the task scheduler system is supported by a priority based OS (e.g., OSEK or AUTOSAR).

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.

The safety of ground vehicles is a matter of critical importance. Vehicle safety is enhanced with the use of control systems that mitigate the effect of unachievable demands from the driver, especially demands for tire forces that cannot be developed. This paper presents the results of a smart tire prototyping and validation study, which is an investigation of a smart tire system that can be used as part of these mitigation efforts. The smart tire can monitor itself using in-tire sensors and provide information regarding its own tire forces and moments, which can be transmitted to a vehicle control system for improved safety. The smart tire is designed to estimate the three orthogonal tire forces and the tire aligning moment at least once per wheel revolution during all modes of vehicle operation, with high accuracy. The prototype includes two in-tire piezoelectric deformation sensors and a rotary encoder.

To improve the safety of automated driving, the paramount target of this intelligent system is to detect and segment the obstacle such as car and pedestrian, precisely. Object detection in self-driving vehicle has chiefly accomplished by making decision and detecting objects through each frame of video. However, there are diverse group of methods in both machine learning and machine vision to improve the performance of system. It is significant to factor in the function of the time in the detection phase. In other word, considering the inputs of system, which have been emitted from eclectic type of sensors such as camera, radar, and LIDAR, as time-varying signals, can be helpful to engross ‘time’ as a fundamental feature in modeling for forecasting the object, while car is moving on the way. In this paper, we focus on eliciting a model through the time to increase the accuracy of object detection in self-driving vehicles.

Most of the present EV on-board chargers utilize a three-stage design, e.g., AC/DC rectifier, DC to high-frequency AC inverter, and AC to DC rectifier, which limits the wall-to-battery efficiency to ∼94%. To further increase the efficiency and power density, a matrix converter is an excellent candidate directly converting grid AC to high-frequency AC thereby saves one stage. However, its control complexity and the high cost of building the back-to-back switches are barriers its acceptance. Instead, this paper adopts the 650V E-mode GaN HEMTs to build a level-2 on-board charger using the indirect matrix topology. The input voltage is 80∼260VAC, the battery voltage is 200∼500VDC and the rated power is 7.2kW. Variable switching frequency is combined with phase-shift control to realize the zero-voltage switching. To further increase the system efficiency, four GaN HEMTs are paralleled to form one switching module with a novel gate-drive technology.

Objection detection using a camera sensor is essential for developing Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD) vehicles. Due to the recent advancement in deep Convolution Neural Networks (CNNs), object detection based on CNNs has achieved state-of-the-art performance during daytime. However, using an RGB camera alone in object detection under poor lighting conditions, such as sun flare, snow, and foggy nights, causes the system's performance to drop and increases the likelihood of a crash. In addition, the object detection system based on an RGB camera performs poorly during nighttime because the camera sensors are susceptible to lighting conditions. This paper explores different pedestrian detection systems at low-lighting conditions and proposes a sensor-fused pedestrian detection system under low-lighting conditions, including nighttime. The proposed system fuses RGB and infrared (IR) thermal camera information.

Since the popularization of the Electric Vehicle (EV) there has been a large movement of consumers, governments, and the automotive industry due to its environmentally friendly characteristics. Unlike an IC engine, the batteries use multitudes of rare earth minerals and complex manufacturing processes which in some cases have been shown to produce as many emissions as an ICE vehicle over its entire lifespan. Another unnoticed important environmental concern has been the final recycling and disposal of the power train after its use. Unlike an ICE engine, which can be melted down or re-used, recycling batteries are much more difficult. In most cases the recycling process and the byproducts produced can be very harmful to the environment. This paper aims to be a complete cradle-to-grave analysis of all emissions produced in the life of an EV battery.