Empowering Graduate Engineering Students With Proficiency in Autonomy

Author(s):  
Adhiti T. Raman ◽  
Venkat N. Krovi ◽  
Matthias J. A. Schmid

A new class of distributed, autonomous systems is emerging, capable of exploiting multimodal distributed and networked spatial and temporal data (at significantly larger scales). A renaissance autonomy engineer requires proficiency in both traditional engineering concepts as well as a systems engineering skillset for implementing the ensuing complex systems. In this paper, we describe goals, development and first offering of a scaffolded course: “AuE 893 Autonomy: Science and Systems” to begin addressing this goal. Geared towards graduate engineering students, with limited prior exposure, the course complements the concepts from traditional courses (on mobile-robotics) with experiential hands-on system-integration efforts (building on the F1tenth.org kits). The staged course structure initially builds upon open-source Robotics Operating System (ROS) tutorials on simulated systems (Gazebo/RViz) with networked communication; Hardware-in-the-loop realization (with a Turtlebot platform) then aids the exploration (and reinforcement) of autonomy concepts. The course culminates in a final-project comprising performance testing with student-team integrated scaled Autonomous Remote Control cars (based on the F1tenth.org parts-list). All three student teams were successful in navigating around a closed racecourse at speeds of 10–15 miles per hour, using Simultaneous Localization and Mapping (SLAM) for situational awareness and obstacle-avoidance. We conclude with discussion of lessons-learnt and opportunities for future improvement.

2018 ◽  
Author(s):  
Adhiti Raman

In recent years, an aggressive expansion of research as well as commercialization efforts in autonomous vehicles can be witnessed. At the same time, many existing companies have expanded their portfolio to autonomous technologies as well (e.g. NVIDIA). This has created an already large need for autonomous-vehicle engineers who are not only proficient in single traditional engineering fields (e.g. mechanical) and old-school automotive studies, but who also have acquired the significantly different, interdisciplinary skillset for mobile robotics. Unlike students of computer science, mechanical engineering graduate students are hardly exposed to coding and robotic system integration in current traditional curricula. The new demands of the automotive industry require an automotive engineer who understands the science of autonomy as well as its impact on the design and implementation of autonomous vehicles, and is equipped with hands-on experience with the latest technology in the field.We describe a unique education program that draws content from traditional courses on mobile-robotics as well as incorporates experiential learning by hands-on training in software, specifically addressing the skill gap in traditional automotive engineering education. Geared towards engineering students with no previous training in robotic system integration, and with only basic undergraduate understanding of programming languages, the teaching experiment employed an active learning approach to introduce numerous concepts as a host of hands-on exercises on multiple robotic platforms. Beginning with simple tutorials on networked communication to demonstrate the power of ROS, the course built up to complete control system design on a student-built RC car that can avoid obstacles and navigate a racecourse by performing SLAM.A brief evaluation of the course exhibited good student performance in general with unique and creative approaches to the programming tasks in particular. Although employing different approaches, each student team was able to demonstrate comparable, efficient performance.


Author(s):  
Jeremiah Vanderlaan ◽  
Josh Richert ◽  
James Morrison ◽  
Thomas Doyle

We are a group of engineering students, in our first year of undergraduate study. We have been selected from one thousand first year students and have competed and won the PACE competition. All engineers share a common general first year, but we have been accepted into Civil and Mechanical engineering. This project was assigned as the final project in the Design and Graphics course. The project we are tasked with, called the Cornerstone Design Project, is to first dissect a product, discover how it works, dimension each part and create a fully assembled model using CAD software (Solid Edge V20 in our case). As part of discovering how it works we must benchmark it so the device can be compared with competing products. The goal of the project is to develop a full understanding of part modeling and assembly in Solid Edge, learn proper measurement techniques, and learn the process of reverse engineering and product dissection. All of these tasks were stepping stones to help us fully understand how the device, and all its components, work.


Author(s):  
Rod D. Roscoe ◽  
Samuel T. Arnold ◽  
Ashley T. Clark

Instruction and coursework that link engineering and psychology may enable future engineers to better understand the people they are engineering for (e.g., users and clients) and themselves as engineers (e.g., teammates). In addition, human-centered engineering education may empower engineering students to better solve problems at the intersection of technology and people. In this study, we surveyed students’ conceptions and attitudes toward human systems engineering. We aggregate responses across three survey iterations to discuss students’ knowledge and beliefs, and to consider instructional opportunities for introductory courses.


Automation ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 48-61
Author(s):  
Bhavyansh Mishra ◽  
Robert Griffin ◽  
Hakki Erhan Sevil

Visual simultaneous localization and mapping (VSLAM) is an essential technique used in areas such as robotics and augmented reality for pose estimation and 3D mapping. Research on VSLAM using both monocular and stereo cameras has grown significantly over the last two decades. There is, therefore, a need for emphasis on a comprehensive review of the evolving architecture of such algorithms in the literature. Although VSLAM algorithm pipelines share similar mathematical backbones, their implementations are individualized and the ad hoc nature of the interfacing between different modules of VSLAM pipelines complicates code reuseability and maintenance. This paper presents a software model for core components of VSLAM implementations and interfaces that govern data flow between them while also attempting to preserve the elements that offer performance improvements over the evolution of VSLAM architectures. The framework presented in this paper employs principles from model-driven engineering (MDE), which are used extensively in the development of large and complicated software systems. The presented VSLAM framework will assist researchers in improving the performance of individual modules of VSLAM while not having to spend time on system integration of those modules into VSLAM pipelines.


2015 ◽  
Vol 2 (2) ◽  
pp. 22-28 ◽  
Author(s):  
Ales Jelinek

The aim of this paper is to provide a brief overview of vector map techniques used in mobile robotics and to present current state of the research in this field at the Brno University of Technology. Vector maps are described as a part of the simultaneous localization and mapping (SLAM) problem in the environment without artificial landmarks or global navigation system. The paper describes algorithms from data acquisition to map building but particular emphasis is put on segmentation, line extraction and scan matching algorithms. All significant algorithms are illustrated with experimental results.


2017 ◽  
Vol 10 (9) ◽  
pp. 95
Author(s):  
Lizeth Ramos ◽  
Arturo Valderruten

The purpose of this article is to present the results of a research that was developed with eight groups of students of undergraduate programs of the Language Institute at Santiago de Cali University. The research was developed with four groups of students who used a mobile application developed jointly by foreign language professors, a software development professor and systems engineering students, as a support tool for individual practice of English level 1 (Test groups) and an equal number of groups of students who did not use the application (Control groups). No mobile applications already available in the market were used because none of them fit the sequence of topics that the course develops along the semester, thus, it was necessary to design an application tailored to the different themes, grammar and vocabulary requirements that were developed by the students. In both cases, a written test was performed at the beginning and end of the course in order to establish the benefit that the application could offer to the students in the test groups. The results indicate that the frequent use of the mobile application might have a positive impact on the development of both listening and linguistic competencies of English.


10.29007/6434 ◽  
2018 ◽  
Author(s):  
Alicia Noceti

Writing is extremely challenging for engineering students. Navarro (2012) asserts that academic literacy in the mother tongue is similar to learning a foreign language as it involves immersion in a new culture. Food Engineering undergraduates (School of Food Science, University of Entre Ríos) face this difficulty when they have to write their Final Project. As a consequence, interdisciplinary actions were implemented by engineers and linguists (both in English and Spanish) in order to raise students´ awareness of this genre characteristics, to facilitate its production and to write relevant titles and abstracts. The importance of both title and abstract is paramount once the Final Projects are uploaded to the university website in order to attract readers. The objective of this study was to explore whether interdisciplinary actions could optimize undergraduates´ written production. All titles produced since the first Food Engineer graduated were collected. This corpus analysis revealed that titles were extremely short and provided very little information. Consequently, pedagogical activities were designed and implemented as from 2012. An exploration of antecedent or prior genre knowledge (Artemeva, N. & Fox., J., 2010) was carried out in different workshops. Generic structure, audience awareness, rhetorical functions and linguistic features studied in the English courses were activated. Writing seminars in Spanish were implemented in 5º year. In addition, undergraduates attended tutorials with the engineers and then and then interviews with the linguists. In several meetings students discussed titles and abstracts (in Spanish and English), designed their slides for the oral defense and rehearsed their oral presentations. The analysis of the corpus including all projects´ titles defended within the time window that included our actions indicated that students had activated their previous generic knowledge. Feedback from students, after graduation, demonstrated that interdisciplinary activities included language as an across the curriculum content and contributed to the adequate production of academic genres. Results may affect curricular design and decisions at the macro level since implementation of writing seminars along undergraduates´ trajectories has been positioned as a top priority.


Sign in / Sign up

Export Citation Format

Share Document