Teaching Autonomous Systems at 1/10th-scale

Loading...
Thumbnail Image
Penn collection
Real-Time and Embedded Systems Lab (mLAB)
Degree type
Discipline
Subject
CPS Auto
autonomous vehicles
autonomous racing
safety critical systems
robotic autonomy
robotic planning
Automotive Engineering
Computer Engineering
Curriculum and Instruction
Educational Methods
Electrical and Computer Engineering
Funder
Grant number
License
Copyright date
Distributor
Related resources
Contributor
Abstract

Teaching autonomous systems is challenging because it is a rapidly advancing cross-disciplinary field that requires theory to be continually validated on physical platforms. For an autonomous vehicle (AV) to operate correctly, it needs to satisfy safety and performance properties that depend on the operational context and interaction with environmental agents, which can be difficult to anticipate and capture. This paper describes a senior undergraduate level course on the design, programming and racing of 1/10th-scale autonomous race cars. We explore AV safety and performance concepts at the limits of perception, planning, and control, in a highly interactive and competitive environment. The course includes an ethics-centered design philosophy, which seeks to engage the students in an analysis of ethical and socio-economic implications of autonomous systems. Our hypothesis is that 1/10th-scale autonomous vehicles sufficiently capture the scaled dynamics, sensing modalities, decision making and risks of real autonomous vehicles, but are a safe and accessible platform to teach the foundations of autonomous systems. We describe the design, deployment and feedback from two offerings of this class for college seniors and graduate students, open-source community development across 36 universities, international racing competitions, student skill enhancement and employability, and recommendations for tailoring it to various settings.

Advisor
Date of presentation
2020-01-01
Conference name
Real-Time and Embedded Systems Lab (mLAB)
Conference dates
2023-05-17T23:14:13.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
@inproceedings{f110sigse2020, title={Teaching Autonomous Systems at 1/10th-scale: A project-based course and community}, author={A. Agnihotri and M. O'Kelly and H. Abbas and R. Mangharam}, booktitle={ACM Special Interest Group on Computer Science Education (SIGCSE)}, year={2020}, organization={ACM} }
Collection