CSCI 235 - Intelligent Robotics

Fall 2018

Course Overview: In this course, we will study the application of concepts from artificial intelligence to solving problems in robotics. Each student will assemble their own robot. Each robot will be assembled from a combination of an Arduino microcontroller, motors, sensors, breadboards, cables, 3D printed parts, and a Kindle Fire 7" tablet.

Tuesday class periods will typically consist of video demonstrations of the work completed in the previous week, followed by a lecture covering the week's new topic and project. Thursday class periods may include some lecture material not completed on Tuesday, but the majority of the Thursday class periods will consist of hands-on work with the robots. Robots may be kept in the lockers in the MARS Lab (MCReynolds 316) for use outside of class time.

This course carries an Odyssey Special Projects credit. In the last three weeks of the semester, each student will complete a final project. Each student must log at least 30 hours of work in order to earn this credit.

At the end of this course, you will be expected to be able to:

Instructor:
Dr. Gabriel Ferrer
M.C. Reynolds 312

Office Hours:
By appointment. To make an appointment with me, visit http://drferrer.youcanbook.me. From there, you can see my availability and select an appointment time.
Also, please feel free to stop by whenever my door is open.

Class Web Page: http://ozark.hendrix.edu/~ferrer/courses/235/

Lecture Time: B4 (2:45-4:00, TR)

Final Exam Period: Thursday, December 6, 8:30-11:30 am

Required Equipment: Every student in the course is expected to purchase the necessary supplies to build themselves a robot. Most of the supplies will be sold to students in a comprehensive bundle. Students will also need to purchase or supply an Android tablet to serve as the robot's CPU. Please inform the instructor if this creates a financial hardship; limited funds are available to assist students in such a situation.

Grading: This course will employ specifications grading. Each assignment will be graded on a pass/fail basis. To earn a passing grade, the assignment must be substantively complete; minor imperfections are perfectly acceptable. Final course grades are earned based on the number of completed passing assignments, as follows: Revision Policy: If a submitted project is not of sufficient quality to receive a passing grade, the student may resubmit it to the instructor after the identified deficiencies are corrected. The instructor reserves the right to disallow revisions as circumstances indicate.

Weekly Projects: Every Tuesday, a project will be assigned. Students may complete projects individually. Students are also welcome to work in teams of two. In each project, students will program a robot to perform a task using a new concept introduced that week, potentially incorporating other concepts covered in previous weeks. Each project will be due on the following Tuesday, with a brief video presentation given in class. Some time will be available every Thursday during the class period for work on that week's project.

Project logs and reports: For each project, each student (even if part of a team) should submit an individual project report. Each report includes the following: Project video presentations: On the due date of each project, each team will play a video in class. The video should meet the following constraints: Late Policy: If a student needs an extension, the instructor must be notified by email by 4 pm on the day prior to the due date. This notification email must state the duration of the requested extension. The instructor reserves the right to decline a request for an extension, but the intention is that most requests for extensions will be granted.

Final Project: In the last three weeks of the semester, each student will undertake a final project. In this final project, you will build and program a robot that fulfills a contextualized purpose. A public demonstration will be made of the robot's capabilities, and a paper reflecting upon lessons learned will be submitted as well. In keeping with the Odyssey Special Project guidelines, the project will require at least 30 hours of work. As with the other course projects, final projects may be undertaken in teams.

Accommodations: It is the policy of Hendrix College to accommodate students with disabilities, pursuant to federal and state law. Students should contact Julie Brown in the Office of Academic Success (505-2954; brownj@hendrix.edu) to begin the accommodation process. Any student seeking accommodation in relation to a recognized disability should inform the instructor at the beginning of the course.

Schedule

DateDayTopic/ActivityAssignment Due
8/21TuesdayWhat is a robot?None
8/23ThursdayBehavior-Based RoboticsRead:
A Robust Layered Control System for a Mobile Robot
Intelligence Without Representation
Elephants Don't Play Chess
8/28TuesdayHTN PlanningProject 1: Robot Concepts
8/30ThursdayHTN PlanningNone
9/4TuesdayRobot AssemblyProject 2: HTN Planning
9/6ThursdayRobot AssemblyNone
9/11TuesdayPID ControlProject 3: Anytime Planning
9/13ThursdayLab WorkNone
9/18TuesdayLayered Mode Selection LogicProject 4: Configuring Robot Motors
Read Layered Mode Selection Logic for Unstructured Environments
9/20ThursdayLab WorkNone
9/25TuesdayReinforcement LearningProject 5: PID Control
9/27ThursdayLab WorkNone
10/2TuesdayImage Processing: Color ClusteringProject 6: Sonars, Conditions, Modes
10/4ThursdayLab WorkNone
10/9TuesdayPresentations and RetrospectiveProject 7: Color Clustering
10/11ThursdayFall Break: No classNone
10/16TuesdayNeural NetworksNone
10/18ThursdayLab WorkNone
10/23TuesdayMapsProject 8: Neural Networks
10/25ThursdayLab WorkNone
10/30TuesdayAutomated PlanningProject 9: Maps
11/1ThursdayLab WorkNone
11/6TuesdayFinal Project BrainstormingProject 10: Planning
11/8ThursdayFinal Project ConceptsNone
11/13TuesdayProgress ReportsNone
11/15ThursdayProgress ReportsNone
11/20TuesdayNo ClassNone
11/22ThursdayThanksgivingNone
11/27TuesdayProgress ReportsNone
11/29ThursdayProgress ReportsNone
12/6ThursdayFinal Exam PeriodFinal Project Demonstration