Search Results

Technological advancement in the automotive industry necessities a closer focus on the functional safety for higher automated driving levels. The automotive industry is transforming from conventional driving technology, where the driver or the human is a part of the control loop, to fully autonomous development and self-driving mode. The Society of Automotive Engineers (SAE) defines the level 4 of autonomy: “Automated driving feature will not require the driver to take over driving control.” Thus, more and more safety related electronic control units (ECUs) are deployed in the control module to support the vehicle. As a result, more complexity of system architecture, software, and hardware are interacting and interfacing in the control system, which increases the risk of both systematic and random hardware failures.

The development of a robust feedback slip controller for a torque converter clutch (TCC) is presented in this paper. The dynamic behavior of the TCC is modeled utilizing the principles of input-output system identification. An H∞ loop shaping controller design technique is applied in order to ensure robust stability against unmodeled system dynamics and large variations in system parameters. Road driving tests indicate that the control system achieves high levels of reliability and stability.

Multicore microcontrollers are rapidly making their way into the automotive industry. We have adopted the Cilk approach (MIT 1994) to develop a pure ANSI C Fork-Join dynamic scheduling runtime middle-layer with a work-stealing scheduler targeted for automotive multicore embedded systems. This middle-layer could be running on top of any AUTOSAR compliant multicore RTOS. We recently have successfully integrated our runtime layer into parts of legacy Ford powertrain software at Ford Motor Company. We have used the 3-core AURIX multicore chip from Infineon and the multicore RTA-OS. For testing purposes, we have forked some parallelizable functions inside two periodic tasks in Ford legacy powertrain software to be dynamically scheduled and executed on the available cores. Our preliminary evaluation showed 1.3–1.4x speedups for these two forked tasks.

Off-road vehicle operation requires constant decision-making under great uncertainty. Such decisions are multi-faceted and range from acquisition decisions to operational decisions. A major input to these decisions is terrain information in the form of soil properties. This information needs to be propagated to path planning algorithms that augment them with other inputs such as visual terrain assessment and other sensors. In this sequence of steps, many resources are needed, and it is not often clear how best to utilize them. We present an integrated approach where a mission’s overall performance is measured using a multiattribute utility function. This framework allows us to evaluate the value of acquiring terrain information and then its use in path planning. The computational effort of optimizing the vehicle path is also considered and optimized. We present our approach using the data acquired from the Keweenaw Research Center terrains and present some results.

Controller Area Network (CAN), the de facto standard for in-vehicle networks, has insufficient security features and thus is inherently vulnerable to various attacks. To protect CAN bus from attacks, intrusion detection systems (IDSs) based on advanced deep learning methods, such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), have been proposed to detect intrusions. However, those models generally introduce high latency, require considerable memory space, and often result in high energy consumption. To accelerate intrusion detection and also reduce memory requests, we exploit the use of Binarized Neural Network (BNN) and hardware-based acceleration for intrusion detection in in-vehicle networks. As BNN uses binary values for activations and weights rather than full precision values, it usually results in faster computation, smaller memory cost, and lower energy consumption than full precision models.

Machine learning methods, such as decision trees and deep neural networks, are becoming increasingly important and useful for data analysis in various scientific fields including dynamics and control, signal processing, pattern recognition, fluid mechanics, and chemical synthesis, etc. For future engine design and performance optimization, there is an urgent need for a robust predictive model which could capture the major combustion properties such as autoignition and flame propagation of multicomponent fuels under a wide range of engine operating conditions, without massive experimental measurement or computational efforts. It will be shown that these long-held limitations and challenges related to complex fuel combustion and engine research could be readily solved by implementing machine learning methods.

Today, commercially available drones have limited use-cases in the rapidly evolving community. However, with advances in drone and software technology, it is possible to utilize these aerial machines to solve problems in a variety of industries such as mining, medical, construction, and law enforcement. For example, in order to reduce time of investigation, Indiana State Police are currently utilizing ad-hoc commercial drones to reconstruct crash scenes for insurance and legal purposes. In this paper, we illustrate how to effectively integrate drones for in-vehicle services and real-time prediction for automotive applications. In order to accomplish this, we first integrate simpler controls such as voice-commands to control the drone from the vehicle. Next, we build smart prediction software that monitors vehicle behavior and reacts in real-time to collisions.

The development of efficient algorithms has been the focus of automobile engineers since self-driving cars become popular. This is due to the potential benefits we can get from self-driving cars and how they can improve safety on our roads. Despite the good promises that come with self-driving cars development, it is way behind being a perfect system because of the complexity of our environment. A self-driving car must understand its environment before it makes decisions on how to navigate, and this might be difficult because the changes in our environment is non-deterministic. With the development of computer vision, some key problems in intelligent driving have been active research areas. The advances made in the field of artificial intelligence made it possible for researchers to try solving these problems with artificial intelligence. Lane detection and tracking is one of the critical problems that need to be effectively implemented.

Traditional Heat Ventilation and Air Conditioning (HVAC) control systems are reactive by design and largely dependent on the on-board sensory data available on a Controller Area Network (CAN) bus. The increasingly common Internet connectivity offered in today's vehicles, through infotainment and telematic systems, makes data available that may be used to improve current HVAC systems. This includes real-time outside relative humidity, ambient temperature, precipitation (i.e., rain, snow, etc.), and weather forecasts. This data, combined with position and route information of the vehicle, may be used to provide a more comfortable experience to vehicle occupants in addition to improving driver visibility through more intelligent humidity, and defrost control. While the possibility of improving HVAC control utilizing internet connectivity seems obvious, it is still currently unclear as to what extent.

In the automotive industry, a Malfunction Indicator Light (MIL) is commonly employed to signify a failure or error in a vehicle system. To identify the root cause that has triggered a particular fault, a technician or engineer will typically run diagnostic tests and analyses. This type of analysis can take a significant amount of time and resources at the cost of customer satisfaction and perceived quality. Predicting an impending error allows for preventative measures or actions which might mitigate the effects of the error. Modern vehicles generate data in the form of sensor readings accessible through the vehicle’s Controller Area Network (CAN). Such data is generally too extensive to aid in analysis and decision making unless machine learning-based methods are used. This paper proposes a method utilizing a recurrent neural network (RNN) to predict an impending fault before it occurs through the use of CAN data.

Engineering design-decisions often involve many attributes which can differ in the levels of their importance to the decision maker (DM), while also exhibiting complex statistical relationships. Learning a decision-making policy which accurately represents the DM’s actions has long been the goal of decision analysts. To circumvent elicitation and modeling issues, this process is often oversimplified in how many factors are considered and how complicated the relationships considered between them are. Without these simplifications, the classical lottery-based preference elicitation is overly expensive, and the responses degrade rapidly in quality as the number of attributes increase. In this paper, we investigate the ability of deep preference machine learning to model high-dimensional decision-making policies utilizing rankings elicited from decision makers.

This paper presents a nonlinear model predictive controller (NMPC) coupled with a pre-trained reinforcement learning (RL) model that can be applied to lateral control tasks for autonomous vehicles. The past few years have seen opulent breakthroughs in applying reinforcement learning to quadruped, biped, and robot arm motion control; while these research extend the frontiers of artificial intelligence and robotics, control policy governed by reinforcement learning along can hardly guarantee the safety and robustness imperative to the technologies in our daily life because the amount of experience needed to train a RL model oftentimes makes training in simulation the only candidate, which leads to the long-standing sim-to-real gap problem–This forbids the autonomous vehicles to harness RL’s ability to optimize a driving policy by searching in a high-dimensional state space.