695.715.81 - Assured Autonomy

Expanded Course Description

Students are expected to propose and conduct an experiment that will prove their paper’s hypothesis.  The Course Project will have you drafting and presenting a peer-reviewed academic workshop-level paper. Students are expected to draft and record four voice-over presentations for their research, experiment proposal, and course project final paper. 

Course Structure

Modules: The course is composed of one module topic per week, see the course schedule for details and dates.  Each module will have topic lectures to watch and assigned learning activities. The course materials are divided into modules which can be accessed by clicking Modules on the course menu.

Assignments: The assignments are grouped into "Research Readings Presentations", "Machine Learning Tutorial", and a "Course Project". For the Course Project, students are expected to propose and conduct an experiment that will prove their paper’s hypothesis. Students are expected to draft and record four voice-over presentations for their research, experiment proposal, and course project peer-reviewed academic workshop-level paper.

You should regularly check the Calendar and Announcements for assignment due dates.  You are encouraged to preview all sections of the module before starting.

Course Topics

Introduction to Assured Autonomy

AI Safety, Trust, Security, and Privacy

Anomaly and Fault Detection

Dataset Shift

Formal Verification and Validation

Test, Evaluation, and Certification

Interpretable, Explainable Machine Learning

Human-AI Integration

Ethics, Policy, and Governance

Adversarial Autonomy

Runtime Monitoring and Assurance

Safe Reinforcement Learning

Multi-agent Systems and Cooperative Control

Course Goals

• The course aims to equip students with the ability to design, analyze, and assure the safety and security of real-world autonomous learning-enabled cyber-physical systems (LE-CPS).
• Students will develop the skills to detect and address system anomalies, manage challenges in unpredictable environments, and enhance testing and evaluation processes.
• Additionally, the course emphasizes the importance of ethical considerations and interpretable AI, preparing students to address global legal, policy, and ethical implications in the deployment of autonomous systems. 
• As an additional learning objective, students will demonstrate their knowledge of the course topics through the drafting and presenting a peer-reviewed academic workshop-level paper.

Course Learning Outcomes (CLOs)

• Describe fundamental concepts in the diverse field of designing and implementing autonomous learning-enabled cyber-physical systems (LE-CPS) focusing on the challenges related to assuring their autonomy, safety, and security.
• Explain the complexities of localizing anomalies, faults, dataset shift, covariate shift, and training set shift in complex LE-CPS.
• Evaluate the difficulties in assuring LE-CPS when encountering unpredictable events, including limitations of verification, validation, the impact of adversarial inputs on AI, implementing multi-agent systems & cooperative control.
• Summarize obstacles to the testing and evaluation processes for assuring autonomous systems, including complications in runtime assurance, safe reinforcement learning, and its relationship to supervised and unsupervised learning.
• Conduct scholarly research and presentations with confidence in the course content topics.
• Explain the concept of interpretable AI used in autonomous systems; and the legal, policy, and ethical implications of applying this technology across global domains.

Textbooks

None. A variety of current papers pertaining to assured autonomy will be placed on reserve for students to access, as well as academic papers accessible through JHU Library holdings.

Required Software

Students are required to access the Internet with a modern browser to complete the ML Tutorial.  Free online resources leveraged will be GitHub and Google Collab GCP.

Student Coursework Requirements

This is a high-level description of the expected student coursework.  Detailed instructions are provided in the course assignments and guides.

It is expected that each module will take approximately 7–10 hours per week to complete. 

Course Lectures:

Recorded lectures for each module topic are available through CANVAS.  

This course will consist of the following basic student coursework requirements:

Research Readings Presentations (30% of Final Grade)

• Choose two papers from different course topics: one from the required reading and another researched independently.
• Create a 15-20 minute voice-over presentation for each paper by the scheduled date.
• Submit a discussion question for each paper and actively engage in discussions by responding to classmates' questions.

ML Tutorial (5% of Final Grade)

• Complete a tutorial on running an image segmentation model from the Advanced Driver Assistance System (ADAS) using the OpenCV framework.
• Run the model against various road condition images, analyze the segmentation output, and compare it to the original results.
• Submit an analysis that includes accuracy commentary and screenshots of the images used.

Experiment Proposal (15% of Final Grade)

• Develop and present a proposal that tests your paper’s hypothesis.
• Design the experiment, conduct it, analyze the results, and present them with graphs in a reproducible format.
• Components include an experiment outline, a 5-minute presentation, peer reviews, and a recorded voice-over of the proposal.

Course Project (50% of Final Grade)

• Complete a project that culminates in an academic workshop or conference-style paper.
• The project will focus on an aspect of assured autonomy (learning-enabled cyber-physical systems).
• Major components include:
  • Submission of three topic ideas
  • Light literature reviews and topic selection in collaboration with the instructor
  • Deeper literature review if needed
  • Multiple drafts and peer reviews
  • Final paper and voice-over presentation
• The emphasis is on framing the project: defining the problem, goals, hypothesis, and designing an experiment to test the hypothesis. Implementation is not graded, ensuring that the project is well-motivated and produces a compelling conclusion.

Although most academic papers submitted to workshops are written in LaTeX, this course will accept MS WORD for ease of editing and review through MS Office suite provided by JHU.  IEEE-Template Selector

Collaboration between students on a topic application is encouraged because combined brainpower has a higher probability of making impact and getting published. However, each student must complete a different subcomponent of the problem and must submit his/her own project paper.

Grading Policy

Final grades will be determined by the following:

EP uses a +/- grading system (see “Grading System”, Graduate Programs catalog, p. 10).

Course Evaluation

• Midway and at the end of the course, JHU sends out formal evaluation forms. 
• Reflections will be solicited at various times during the course as a safe space for learners to express their emotions, establish meaningful connections, and actively engage in their own learning.
  
• The instructor may send out a survey for more specific feedback on a focused aspect from students at the end of the course.

Course Policies

Late Submission and Re-Submission Policy

Understanding that unexpected circumstances may arise, my goal is to support students while maintaining fairness across the class. To balance flexibility and accountability, the following Late Policy is in place for this master's degree course:

• Late Submission: Late submissions will incur a 10% deduction immediately, with an additional 10% deducted for each week thereafter.

• Re-Submission: You may re-submit an assignment for re-grading, but the late penalty may still apply.

Planning and Communication: If you anticipate needing an extension due to specific circumstances, please communicate with me as early as possible. Together, we can agree on a completion plan that you will be responsible for following.

While I strive to accommodate unforeseen challenges, it's important to plan ahead for predictable events such as vacations, medical leave, or work commitments. Please notify me in advance if you foresee any potential conflicts.

Limits on Extensions: While I aim to be flexible, the decision to grant extensions is at my discretion. To ensure fairness and course progression:

• Extensions will not typically be granted within 48 hours of the assignment due date unless a valid reason is provided.
• I may limit extensions to a maximum of two per student throughout the semester.

By adhering to this policy, we can manage unexpected situations effectively while ensuring fairness and maintaining the flow of the course. Thank you for your understanding and cooperation.

USE OF AI IN THIS CLASS

Students are encouraged to leverage their experience with AI tools such as GPT, Perplexity, Gemini, and Copilot, and be ready to further develop these skills as essential in researching academic topics like Assured Autonomy. Since this is an AI course, utilizing AI tools is an expected and integral part of the learning process.

However, it's crucial to use AI tools as aids to enhance your critical thinking and research capabilities, not as substitutes. AI can assist in tasks like summarizing complex topics, drafting initial versions of your work, and identifying relevant sources. That said, it's essential to critically assess the outputs of these tools to ensure they meet academic standards in terms of accuracy and reliability.  Ultimately, the integrity of your assignments rests with you, so use AI to deepen your understanding and support your learning, not as a shortcut to bypass the effort required to master the course content.

Academic Policies

Deadlines for Adding, Dropping and Withdrawing from Courses

Students may add a course up to one week after the start of the term for that particular course. Students may drop courses according to the drop deadlines outlined in the EP academic calendar (https://ep.jhu.edu/student-services/academic-calendar/). Between the 6th week of the class and prior to the final withdrawal deadline, a student may withdraw from a course with a W on their academic record. A record of the course will remain on the academic record with a W appearing in the grade column to indicate that the student registered and withdrew from the course.

Academic Misconduct Policy

All students are required to read, know, and comply with the Johns Hopkins University Krieger School of Arts and Sciences (KSAS) / Whiting School of Engineering (WSE) Procedures for Handling Allegations of Misconduct by Full-Time and Part-Time Graduate Students.

This policy prohibits academic misconduct, including but not limited to the following: cheating or facilitating cheating; plagiarism; reuse of assignments; unauthorized collaboration; alteration of graded assignments; and unfair competition. Course materials (old assignments, texts, or examinations, etc.) should not be shared unless authorized by the course instructor. Any questions related to this policy should be directed to EP’s academic integrity officer at ep-academic-integrity@jhu.edu.

Students with Disabilities - Accommodations and Accessibility

Johns Hopkins University values diversity and inclusion. We are committed to providing welcoming, equitable, and accessible educational experiences for all students. Students with disabilities (including those with psychological conditions, medical conditions and temporary disabilities) can request accommodations for this course by providing an Accommodation Letter issued by Student Disability Services (SDS). Please request accommodations for this course as early as possible to provide time for effective communication and arrangements.

For further information or to start the process of requesting accommodations, please contact Student Disability Services at Engineering for Professionals, ep-disability-svcs@jhu.edu.

Student Conduct Code

The fundamental purpose of the JHU regulation of student conduct is to promote and to protect the health, safety, welfare, property, and rights of all members of the University community as well as to promote the orderly operation of the University and to safeguard its property and facilities. As members of the University community, students accept certain responsibilities which support the educational mission and create an environment in which all students are afforded the same opportunity to succeed academically. 

For a full description of the code please visit the following website: https://studentaffairs.jhu.edu/policies-guidelines/student-code/

Classroom Climate

JHU is committed to creating a classroom environment that values the diversity of experiences and perspectives that all students bring. Everyone has the right to be treated with dignity and respect. Fostering an inclusive climate is important. Research and experience show that students who interact with peers who are different from themselves learn new things and experience tangible educational outcomes. At no time in this learning process should someone be singled out or treated unequally on the basis of any seen or unseen part of their identity. 
 
If you have concerns in this course about harassment, discrimination, or any unequal treatment, or if you seek accommodations or resources, please reach out to the course instructor directly. Reporting will never impact your course grade. You may also share concerns with your program chair, the Assistant Dean for Diversity and Inclusion, or the Office of Institutional Equity. In handling reports, people will protect your privacy as much as possible, but faculty and staff are required to officially report information for some cases (e.g. sexual harassment).

Course Auditing

When a student enrolls in an EP course with “audit” status, the student must reach an understanding with the instructor as to what is required to earn the “audit.” If the student does not meet those expectations, the instructor must notify the EP Registration Team [EP-Registration@exchange.johnshopkins.edu] in order for the student to be retroactively dropped or withdrawn from the course (depending on when the "audit" was requested and in accordance with EP registration deadlines). All lecture content will remain accessible to auditing students, but access to all other course material is left to the discretion of the instructor.