Instructor: Chunyi Peng
Lecture time: TR 12:00PM - 13:15PM
Location: LWSN B134
Credit Hours: 3.00
Spring break: March 16 - 21 (no lectures)
Midterm (in class): *4:30PM - 5:45PM Thur April ?
Final Project: presentationdemo (tentative): April 2830, 2026; report: May 7, 2026
This is a NEW graduate-level seminar course, which is approved for both MS & PhD plans of study.
Unmanned Aerial Vehicles (aka. drones) are gaining significant momentum. With unparallel advantages of flying in the low sky (say, small drones below 400ft, regulated by FAA in the USA), drones have moved many existing activities from the ground to the sky and enabled new thrilling applications across a wide range of verticals such as aerial photography, surveillance, smart agriculture, transportation and logistics, public safety and rescue, to name many.
In this course, we will explore the ongoing revolution to autonomous drones. Students expect to learn (reproduce and develop) core technologies enabling autonomous drones, spanning perception, communication, and control, as well as the integration and field tests. Students also expect to understand the state-of-art and recent trends, explore emerging technical problems, master a suite of research skills (e.g., paper reading and discussions, communication and presentation, report writing, critical thinking, problem solving and teamwork), and gain experience of carrying out original research through course projects. Hopefully, through this course, students will generate publishable results from course projects or find some interesting topics for long-term research.
We will take an inter-disciplined approach over AI (computer vision, machine learning, robotics and world models) and systems (edge computing, wireless sensing, mobile networking and distributed systems).
Throughout this course, students will learn and implement algorithms for autonomous and intelligent drones, and demonstrate the developed algorithms in an end-to-end drone system (commercial-of-the-shelf drones and aerial simulators). Topics include but not limited to
Aerial perception, mainly on aerial vision (semantic segmentation, object detection and tracking, depth estimation, drone localization, scene understanding and modeling).
Drone control (motion and path planning, obstacle avoidance, trajectory monitoring and control, drone traffic management)
Edge-assisted computing (ultra-low latency and reliable communication, 5G/6G in the field, mobile edge computing).
Integration and field test (demonstrated for one drone application and use).
As an advanced topic course, we assume that students already have a basic understanding on AI and systems. Project experience and good programming skills are a must, as the course project is an important part of this course.
Many topics in this course are inter-disciplinary and require to apply technologies in computer vision (CV), LLM/VLM, reinforcement learning (RL), robotics, edge networking and computing. Prior experience is a great plus but optional.
No textbooks are required. The course materials are mainly from research papers from top conferences like ICRAIROSHRI (robotics), CVPRICCVECCV (computer vision), AAAIICML NeurIPS (machine learning), and MobiCom/MobiSys (mobile systems).
Lab assignments: 25 %
In-class presentation, discussion and participation: 15%
Mid-term Exam: 25%
Final Project: 35%
Lab assignments. Students will do 2 out of 3 lab assignments which cover three pillar technologies: perception, control and edge computing. Students are encouraged to use testbeds developed and operated by Purdue teams such as AirLab (http:airlab.cs.purdue.edu) and MI-LAB (http:milab.cs.purdue.edu).
In-class presentation and participation. Every student is going to present one paper and participate paper discussion in class. Papers can be selected from the reading list (or out of the list but from other top conferences). It is encouraged to present and discuss papers relevant to final course project.
Midterm exam. An in-class midterm exam is to cover the lectures, lab assignments and topics discussed as a regular course.
Final project. One final course project will be done in a team of 2-4 students. Team and topic will be determined in the first few weeks. A course project report, with an in-class presentation (and demo) in the final week is required.
Week 1: Course Introduction and background
Week 2: Hot topics and ongoing research highlights
Week 3-4: Aerial Vision and Perception (basic)
Week 5: In-class presentation and discussion (Lab 1)
Week 6: Drone control (basic)
Week 7: In-class presentation and discussion (Lab 2)
Week 8: Mobile edge computing for drones (basic)
Week 9: In-class presentation and discussion (Lab 3)
Week 10: Midterm (and project mid-term presentation)
Week 11: Drone applications and systems
Week 12-13: advanced topics
Week 14: Final course project presentation and demo
This course uses the SAME policy used in a regular CS course. It means that you need to obey course polices for all the courses in the department of Computer Science, Purdue University. Here, I higlhight some important ones.
Students are expected to be present for every meeting of the classes in which they are enrolled. Only the instructor can excuse a student from a course requirement or responsibility. When conflicts or absences can be anticipated, such as for many University-sponsored activities and religious observations, the student should inform the instructor of the situation as far in advance as possible and plan to make up for missed work.
There is no partial credit for late assignments; you must submit by the deadline. However, each student is granted three grace days (24-hour period each) that can be used for any homework or lab assignment. The three days can be applied to a single assignment or one day can be applied to each of three assignments. Note that you need to notify TAs before you want to use late days.
If you feel that you have been unfairly graded on a lab assignment, homework or exam, you should petition the appropriate TA or Professor in writing within the regrading window of distribution of the graded work. After two weeks, NO regrade requests will be honored. For lab assignments, you are allowed to change a few lines of code if that makes your program work, but there will be a penalty per change.
You are expected to read and follow Purdue’s guide to academic integrity: the link. To foster an open and collegial class environment, we are vigorously opposed to academic dishonesty because it seriously detracts from the education of honest students.
No ChatGPT or AI used in class. Students are explicitly prohibited from using artificial intelligence tools including but not limited ChatGPT during this course.
It is permissible to discuss a GENERAL METHOD of solution with other students, or to make use of high-level reference materials in the library or online. If you do this, you will be expected to CLEARLY DISCLOSE with whom you discussed the method of solution, or to cite the references used. Failure to do so will be considered cheating or plagiarism. The use of “method of solution” means a GENERAL discussion of technique or algorithm, such as one would reasonably expect to occur standing in front of a whiteboard, and precludes the detailed discussion of code or written assignments.
Specifically, looking at another student's code on his/her computer monitor or copying code from an online source is NOT allowed.
Using any code or copying any assignment from others or from an online source is strictly prohibited without advance prior permission from the instructor. This includes but not limited to the use of code others have submitted in the past, or solutions found on the Internet.
Unless otherwise explicitly specified, all written assignments or code that is submitted is to be ENTIRELY the student's own work. Moreover, all students work is their own. Students who do share their work with others are as responsible for academic dishonesty as the student receiving the material. Students are not to show work to other students, in the class or outside. Students are responsible for the security of their work.
Students who encourage others to cheat or plagiarize, or students who are aware of plagiarism or cheating and do not report it are also participating in academically dishonest behavior.
Be aware that we will use a software tool called MOSS to check for copying among submitted assignments. Additionally, the instructor and TA will be inspecting all submitted material to ensure honesty.
The course policy is that students who are found guilty of dishonesty will not only receive a zero for the work in question but also receive a severe grade penalty (at least double grades assigned to the work and even FAILURE in this course). Moreover, the Dean of Students will be notified for possible further action.
In the event of a major campus emergency, course requirements, deadlines and grading percentages are subject to change that may be necessitated by a revised semester calendar or other circumstances. If an emergency occurs, you can consult the CS web page for details.
In case of any personal emergency, please do contact Prof Peng as soon as you can.
Purdue University is required to respond to the needs of students with disabilities as outlined in both the Rehabilitation Act of 1973 and the Americans with Disabilities Act of 1990 through the provision of auxiliary aids and services that allow a student with a disability to access and participate fully in the programs, services, and activities at Purdue University. If you have a disability that requires special academic accommodation, please make an appointment to speak with the instructor within the first three (3) weeks of the semester in order to discuss any adjustments. It is the student’s responsibility to notify the Disability Resource Center of an impairment/condition that may require accommodations and/or classroom modifications. We cannot arrange special accommodations without confirmation from the Disability Resource Center.
If you are experiencing stress or personal problems, Purdue provides counseling services through the Purdue CAPS Center. Please see CAPS for more details.