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.

This paper describes a front road wheel steer-by-wire system with two actuator motors on the rack and pinion assembly to move the road wheels. Dual actuators are used to provide actuator redundancy and to enhance the fault tolerance capability. When one actuator faults or fails, the other actuator is designed to work independently and maintain full system performance. The paper emphasizes control method to implement the motion control for the front road wheel steer-by-wire system with two actuators on the common load. The proposed dual servo synchronization motion control implements the angle tracking for the road wheel reference input by controlling two actuators synchronously and cooperatively. It includes two servo feedback control loops to track the common reference input. The angular position error between two feedback loops is compensated using a synchronized compensator.

Internal combustion engines are designed to maximize power subject to meeting exhaust emission requirements and minimizing fuel consumption. Maximizing engine power and fuel economy is limited by engine knock for a given air-to-fuel charge. Therefore, the ability to detect engine knock and run the engine at its knock limit is a key for the best power and fuel economy. This paper shows inaudible knock detection ability using in-cylinder ionization signals over the entire engine speed and load map. This is especially important at high engine speed and high EGR rates. The knock detection ability is compared between three sensors: production knock (accelerometer) sensor, in-cylinder pressure and ionization sensors. The test data shows that the ionization signals can be used to detect inaudible engine knock while the conventional knock sensor cannot under some engine operational conditions.

This paper introduces the Driver Stability System (DSS) at Visteon. DSS is a new active comfort / safety system for automobiles which controls the seat bolsters independently in real time to enhance the lateral support of the occupants. Under turning maneuvers, DSS reacts to the vehicle dynamics to provide an increased contact area between the occupants and their seats, allowing optimal occupant location with respect to such variables as steering wheel angle, lateral acceleration, yaw rate, and vehicle velocity. The lateral force compensation is directly coupled to the dynamic movement of vehicle chassis and the change of road profile. The system consists of the seat bolster assembly including DC motors, wheel speed sensors, steering wheel sensor, lateral accelerometer, yaw rate sensor, and electronic control unit (ECU). This paper also discusses the control concept of DSS and its realistic controller structure.

Steer-by-wire systems (SBW) offer the potential to enhance steering functionality by enabling features such as automatic lane keeping, park assist, variable steer ratio, and advanced vehicle dynamics control. The lack of a steering intermediate shaft significantly enhances vehicle architectural flexibility. These potential benefits led GM to include steer-by-wire technology in its next generation fuel cell demonstration vehicle, called “Sequel.” The Sequel's steer-by-wire system consists of front and rear electromechanical actuators, a torque feedback emulator for the steering wheel, and a distributed electronic control system. Redundancy of sensors, actuators, controllers, and power allows the system to be fault-tolerant. Control is provided by multiple ECU's that are linked by a fault-tolerant communication system called FlexRay. In this paper, we describe the objectives for fault tolerance and performance that were established for the Sequel.

Commonly, a significant event is detected when a normally stable engine parameter (ex. sensor voltage, sensor current, air flow, pedal position, fuel level, tire pressure, engine acceleration, etc.) transiently exceeds a calibrated detection threshold. Many implementations of detection thresholds rely on multi-input lookup tables or functions and are complex and difficult to calibrate. An approach is presented to minimize threshold calibration effort and complexity, while improving detection performance, by dynamically computing thresholds on-line based on current real-time data. Determining engine synchronization without a camshaft position sensor is presented as an illustrative application.

Cylinder air/fuel ratio distribution is an important factor affecting the economy, power, vibration, and emissions of an internal combustion engine. Currently, production automobiles utilize an exhaust gas sensor located in the main exhaust stream in order to regulate air/fuel mixtures. By measuring the oxygen content of the exhaust gas for each cylinder independently, the degree of air/fuel variation between cylinders can be determined. This information can be used to determine the mixture quality of specific cylinders. Knowing these variances can lead to design changes in the intake and exhaust manifolds as well as better control of fuel metering which will improve the output of the engine. This study was carried out using a 1991 3.8L Buick V-6 engine with customized exhaust manifolds utilizing exhaust gas oxygen sensors for each cylinder in addition to the sensor located in the main combined exhaust gas stream. Production level, ZrO2 sensors were used for this experimental study.

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.

To obtain the maximum output power and fuel economy from an internal combustion engine, it is often necessary to detect engine knock and operate the engine at its knock limit. This paper presents the ability to detect knock using in-cylinder ionization signals on a large displacement, air-cooled, “V” twin motorcycle engine over the engine operational map. The knock detection ability of three different sensors is compared: production knock (accelerometer) sensor, in-cylinder pressure sensor, and ionization sensor. The test data shows that the ionization sensor is able to detect knock better than the production knock sensor when there is high mechanical noise present in the engine.

Automakers looking to remake their traditional vehicle line-up into autonomous vehicles, Noise, Vibration, and Harshness (NVH) considerations for autonomous vehicles are soon to follow. While traditional NVH considerations still must be applied to carry-over systems, additional components are required for an autonomous vehicle to operate. These additional components needed for autonomy also require NVH analysis and optimization. Autonomous vehicles rely on a suite of sensors, including Light Detection and Ranging (LiDAR) and cameras placed at optimal points on the vehicle for maximum coverage and utilization. In this study, the NVH considerations of autonomous vehicles are examined, focusing on the additional perception equipment installed in autonomous vehicles.

A hardware and software architecture suitable for a safety-critical steer-by-wire systems is presented. The architecture supports three major failure modes and features several safety protocols and mechanisms. Failures due to component failures, software errors, and human errors are handled by the architecture and safety protocols. A test implementation using replicated communication channels, controllers, sensors, and actuators has been performed. The test implementation uses the CAN protocol, Motorola S12 microcontrollers, and Microchip MCP250XX components with a steering wheel and road wheel simulator. The focus of the paper is on the application level, using system engineering principles which incorporate a holistic approach to achieve safety at various levels.

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.