Engineering Commons^™

Evaluation Of Lidar Uncertainty And Applications Towards Slam In Off-Road Environments, Zachary D. Jeffries

Dissertations, Master's Theses and Master's Reports

Safe and robust operation of autonomous ground vehicles in all types of conditions and environment necessitates complex perception systems and unique, innovative solutions. This work addresses automotive lidar and maximizing the performance of a simultaneous localization and mapping stack. An exploratory experiment and an open benchmarking experiment are both presented. Additionally, a popular SLAM application is extended to use the type of information gained from lidar characterization, demonstrating the performance gains and necessity to tightly couple perception software and sensor hardware. The first exploratory experiment collects data from child-sized, low-reflectance targets over a range from 15 m to 35 m. …

Through-Ice Acoustic Source Tracking Using Vision Transformers With Ordinal Classification, Steven Whitaker, Andrew Barnard, George D. Anderson, Timothy C. Havens

Michigan Tech Publications

Ice environments pose challenges for conventional underwater acoustic localization techniques due to theirmultipath and non-linear nature. In this paper, we compare different deep learning networks, such as Transformers, Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Vision Transformers (ViTs), for passive localization and tracking of single moving, on-ice acoustic sources using two underwater acoustic vector sensors. We incorporate ordinal classification as a localization approach and compare the results with other standard methods. We conduct experiments passively recording the acoustic signature of an anthropogenic source on the ice and analyze these data. The results demonstrate that Vision Transformers are …

Community Detection In Complex Networks And Application To Dense Wireless Sensor Networks Localization, Sakineh Yazdanparast

Dissertations, Master's Theses and Master's Reports

Complex network analysis is applied in numerous researches. Features and characteristics of complex networks provide information associated with a network feature called community structure. Naturally, nodes with similar attributes will be more likely to form a community. Community detection is described as the process by which complex network data are analyzed to uncover organizational properties, and structure; and ultimately to enable extraction of useful information. Analysis of Wireless Sensor Networks (WSN) is considered as one of the most important categories of network analysis due to their enormous and emerging applications. Most WSN applications are location-aware, which entails precise localization of …

Effect Of Sensor Errors On Autonomous Steering Control And Application Of Sensor Fusion For Robust Navigation, Shuvodeep Bhattacharjya

Dissertations, Master's Theses and Master's Reports

Autonomous steering control is one the most important features in autonomous vehicle navigation. The nature and tuning of the controller decides how well the vehicle follows a defined trajectory. A poorly tuned controller can cause the vehicle to oversteer or understeer at turns leading to deviation from a defined path. However, controller performance also depends on the state–feedback system. If the states used for controller input are noisy or has bias / systematic error, the navigation performance of the vehicle is affected irrespective of the control law and controller tuning. In this report, autonomous steering controller analysis is done for …

Target Localization And Tracking By Fusing Doppler Differentials From Cellular Emanations With A Multi-Spectral Video Tracker, Casey D. Demars, Michael Roggemann, Adam Webb, Timothy C. Havens

Michigan Tech Publications

We present an algorithm for fusing data from a constellation of RF sensors detecting cellular emanations with the output of a multi-spectral video tracker to localize and track a target with a specific cell phone. The RF sensors measure the Doppler shift caused by the moving cellular emanation and then Doppler differentials between all sensor pairs are calculated. The multi-spectral video tracker uses a Gaussian mixture model to detect foreground targets and SIFT features to track targets through the video sequence. The data is fused by associating the Doppler differential from the RF sensors with the theoretical Doppler differential computed …

Heterogeneous Multi-Sensor Fusion For 2d And 3d Pose Estimation, Hanieh Deilamsalehy

Dissertations, Master's Theses and Master's Reports

Sensor fusion is a process in which data from different sensors is combined to acquire an output that cannot be obtained from individual sensors. This dissertation first considers a 2D image level real world problem from rail industry and proposes a novel solution using sensor fusion, then proceeds further to the more complicated 3D problem of multi sensor fusion for UAV pose estimation.

One of the most important safety-related tasks in the rail industry is an early detection of defective rolling stock components. Railway wheels and wheel bearings are two components prone to damage due to their interactions with the …

A Novel Low Latency, High Resolution And Low Cost Time Synchronization, Ali Aghdaei

Dissertations, Master's Theses and Master's Reports

This report presents a new low latency, high resolution and low cost timing synchro- nization technique for digital receivers. Traditional timing synchronization employs Matched filter to perform cross-correlation operation and estimate Time-of-Arrival (TOA) of the signal. Decreasing the latency of the traditional method through over- sampling leads to a higher complexity and it is not viable. Furthermore, to obtain a high-resolution TOA, an extensive bandwidth is required, which results in high system complexity. The proposed method uses single bit quantization to employ XNOR blocks instead of multiplier and accumulator (MAC) blocks in the traditional method. This substantially decreases complexity incorporating …