Instructor Information

Tamim Sookoor

Work Phone: 240-592-0663

Course Information

Course Description

Autonomic systems leverage the growing advances in control, computer vision, and machine learning coupled with technological advances in sensing, computation, and communication. While this emerging highly connected, autonomous world is full of promise, it also introduces safety and security risks that are not present in legacy systems. This course focuses on the complexities inherent in autonomous systems and the multifaceted and multilayered approaches necessary to assure their secure and safe operation. As these systems become more pervasive, guaranteeing their safe operation even during unforeseen and unpredictable events becomes imperative. There are currently no real solutions to provide these runtime guarantees necessitating cutting edge research to provide state awareness, intelligence, control, safety, security, effective human-machine interaction, robust communication, and reliable computation and operation to these systems. This course follows a seminar-style format where students are expected to lead class discussions and write a publication-quality paper as part of a course project.

Course Goal

The goals for this course are to: (1) introduce autonomous systems, (2) introduce the vulnerabilities in the hardware, software, and learning algorithms of autonomous systems, (3) and most importantly, challenge students to think of approaches to assuring the safety and security of autonomous systems that are becoming pervasive in society.

Course Objectives

  • By the end of the course, students should be able to:
    Understand the basics of autonomous systems and their potential vulnerabilities.
  • Assess potential vulnerabilities in autonomous systems.
  • Appreciate the challenges that machine learning introduces to autonomous systems.
  • Perform novel assured autonomy research, including problem identification, solution proposal, experimentation, data analysis, and technical paper and presentation development.

When This Course is Typically Offered

This course is typically offered in fhe fall term at Kossiakoff Center.

Syllabus

  • Introduction to Assured Autonomy
  • AI Safety, Trust, Security, and Privacy
  • Anomaly and Fault Detection
  • Data Set Shift
  • Formal Verification and Validation
  • Test, Evaluation, and Certification
  • Interpretable Machine Learning
  • Human-Autonomy Integration
  • Policy and Governance
  • Adversarial AI
  • Runtime Monitoring and Assurance
  • Software, Sensor, and Actuator Assurance

Student Assessment Criteria

Class Preparation and Participation 20%
Paper Presentations 20%
Peer Reviews 10%
Course Project Proposal 10%
Course Project Report 25%
Course Project Presentation 15%

Assignments are due according to the dates posted in your Blackboard course site. You may check these due dates in the Course Calendar or the Assignments in the corresponding modules. Expect grades to be posted one week after the due date of each assignment.

We generally do not directly grade spelling and grammar. However, egregious violations of the rules of the English language may be noted without comment. Consistently poor performance in either spelling or grammar is taken as an indication of poor written communication ability that may detract from your grade.

Timely feedback on students’ performance is an established learning tool, so we will endeavor to provide feedback, as quickly as possible, on all material that you submit.

A grade of A indicates achievement of consistent excellence and distinction throughout the course—that is, conspicuous excellence in all aspects of assignments and discussion in every week.

A grade of B indicates work that meets all course requirements on a level appropriate for graduate academic work. These criteria apply to both undergraduates and graduate students taking the course.

Final grades will be determined using the following scale:

100-90 = A
89-80 = B
79-70 = C
<70 = F

Computer and Technical Requirements

This course is suitable for graduate students with little prior experience in the area.

Participation Expectations

Students are expected to read the assigned papers each week (approximately 3-4 hours per week). Students will be required to present one or more papers to the class (approximately 2-3 hours per week) and lead a discussion of that material. The course project will include both a presentation and a paper (approximately 2-3 hours per week) that provides technical details of the work.

Textbooks

Textbook information for this course is available online through the MBS Direct Virtual Bookstore.

Course Notes

There are no notes for this course.

Final Words from the Instructor

The instructor is open to any comments or suggestions to improve the course and will seek to quickly integrate any improvements. The instructor is best reached via email and will usually respond within 48 hours.

(Last Modified: 08/08/2019 02:00:08 PM)