Merge pull request #88 from CMUBOB97/master

Added elective 16-384 and 16-664

README.md

@@ -48,7 +48,9 @@ expect from the core classes from the ECE and CS programs at CMU.
 - [15-455: Undergraduate Complexity Theory](electives/15455.md)
 - [15-462: Computer Graphics](electives/15462.md)
 - [16-311: Introduction to Robotics](electives/16311.md)
+- [16-384: Robot Kinematics and Dynamics](electives/16384.md)
 - [16-385: Computer Vision](electives/16385.md)
+- [16-664: Self Driving Cars: Perception & Control](electives/16664.md)
 - [16-720: Computer Vision](electives/16720.md)
 - [16-833: Robot Localization and Mapping](electives/16833.md)
 - [17-214: Principles of Software Construction](electives/17214.md)

electives/16384.md

@@ -0,0 +1,98 @@
+# 16-384: Robot Kinematics and Dynamics
+
+| **Category** | **Difficulty (Out of 5)** |
+| --- | --- |
+| Homework - Programming | 3 |
+| Homework - Written | 4 |
+| Final Project | 3.5 |
+| Exams | 5 |
+
+16-384 is a required class for students interested in pursuing an additional major in Robotics.
+This course mainly focuses on:
+ - how to manipulate a robot arm with multiple degrees of freedom
+ - how to know where the end of your robot arm is given a specific configuration (angles in joints)
+ - how to know your robot arm's configuration given the end position
+ - how to change your robot arm's position and velocity
+ - how much torque your robot arm experiences and exerts
+ - how to mathematically represent a complicated, multiple-joint robotics arm
+ - ...
+This class has the fundamental mathematics and techniques in kinematics and dynamics.
+By completing programming assignments on using the Hebi robotics arm and
+written assignment to practice the math, students will have the skill to accomplish
+the final project: making the robot arm build a Jenga tower.
+The workload in this class is moderate and details about topics, class structure,
+and assignments are mentioned below:
+
+# Topics
+
+1. Rigid Body Motions
+2. Forward Kinematics
+3. Jacobian 
+4. Inverse Kinematics
+5. Dynamics of Point Masses
+6. Denavit-Hartenberg Representation
+7. Angular Velocity
+8. Forward Differential Kinematics
+9. Inverse Differential Kinematics
+
+*note that all topics are extended from 2D to 3D as the class proceeds.
+
+# Class Structure
+
+1. Lectures on the above topics
+  - there are mini lectures on OLI modules that can help you review/preview
+  - lectures consist of concepts and examples
+  - TAs will go through HW problems during the class
+2. Homework
+  - programming: uses the robotics arm in REL (robotics education lab, in NSH 3rd floor)
+  - written: mathematics on topics mentioned above
+  - **no late handin**
+3. Midterm
+  - during the class time
+  - quite **hard**
+4. Final project & competition
+  - robot building Jenga tower
+  - the team building the tower the highest in 30 seconds gets 100 on the final 
+
+# Homeworks
+
+The homework usually comes in two parts: the written one and the programming one.
+The written part will guide you through the calculation and give you a picture on
+how to implement this in the programming part. The programming part will be in
+MATLAB. It's okay to not have the prior knowledge about it (there is a warm up homework 0).
+Most stuff in this class is about linear algebra, so it is good to take classes
+about linear algebra before taking this class. This class does not allow late
+submissions. If you need extensions, be sure to take with instructors ahead of time.
+
+# OLI modules
+
+A small portion of the grade in this class goes to OLI module, and their deadlines
+are pretty frequent. Although it is okay to miss one or two, make sure you do not
+miss a lot of them.
+
+# Exams
+
+There will be two exams in this class, and both of them are pretty intense.
+Students from last year were struggling trying to finish the Lagrangian question.
+Be sure to review homework and be comfortable doing the calculation before the exam.
+
+# Final project
+
+The final project consists of two parts: a checkpoint and a final. Final project
+will be in teams of 2. The checkpoint is about laying a single layer of Jenga blocks,
+and the final is about laying 3 layers of Jenga blocks with a time constraint.
+Therefore, try to reserve enough time for the final, because you can use plenty
+methods to get away with the checkpoint, but not the same for final. There is a
+competition on building the highest Jenga structure in 30 seconds, with auto 100
+on the final exam as a reward. This competition is not mandatory, so you can
+also have fun watching other people's robot in the competition!
+
+# Tips and Tricks to do Well
+
+- Attend lectures and keep up with lectures.
+- Ask questions on Piazza when in doubt.
+- There are modules on OLI for helping you review/preview materials.
+- Pay attention to homeowrk feedback and don't submit them late.
+- Be sure to prepare the exam both in concepts and calculations.
+- Start the final project early! Otherwise people fight for robot usage 3 AM before the demo day.
+- Have fun!

electives/16664.md

@@ -0,0 +1,68 @@
+# 16-664: Self Driving Cars: Perception & Control
+
+| Category | Difficulty |
+|:-:       | :-:        |
+| HW       | 3          |
+| Project  | 3          |
+
+Self Driving Cars: Perception & Control is a new class introduced to Robotics Department
+in Spring 2023. This class combines both the perception and control knowledge in the field of
+self driving car and gives students homework and project that solves problems using real work
+and simulation data samples. The course is split into two halves: the first half semester
+covers perception, and the second half covers control.
+
+# Topics covered
+
+Perception 
+- Pose sensors
+- Camera & Lidar geometry
+- Localization & SLAM
+- Machine Learning for Computer Vision
+
+Control
+- State space models
+- Linear Quadratic Regulators (LQR)
+- Vehicle Dynamics
+- Model Predictive Controls (MPC)
+- Trajectory Optimization
+
+# Class structure
+
+The class only has one lecture per week, and it is 2 hour and 50 minute long, from 4 pm
+to 6:50 pm. During the lecture period there will have two intermissions, so it won't be
+too exhausting. During the lecture, professors will cover how certain perception/control
+techniques were developed and how to deploy them in self driving car scenarios. The
+lectures assume students have some prior knowledge in linear algebra, so it is good to
+take some linear algebra courses before taking this class. However, you are welcome to
+ask questions or concepts that you have not heard of and both perception and control
+professors will happily answer you.
+
+# Homework
+
+Homework is due biweekly. The difficulty is not too hard, so you have plenty of time to work
+on the assignment. Note that there is only one TA per half of the semester (so one perception
+TA and one control TA), you should work on the assignment ahead of time and ask questions
+during the limited office hour time. There is one assignment you are allowed to submit up to
+48 hours late. Since most materials are related to linear algebra, the assignment will be
+submitted using MATLAB grader and you can test your submissions for unlimited number of times
+before the due. It's better if you have worked with MATLAB before this class. However, you
+can still take it without the prior knowledge as there will be a warmup assignment on MATLAB
+before everything.
+
+# Project
+
+The final project is about perceiving other vehicles and controling your own vehicle's movement
+in the simulation environment of GTA5 (Wow!). This final project is pretty cool and you are
+allowed to use any perception and control technique. The baseline for passing the final
+project is fair, and you can explore more techniques after getting a passing score. The final
+project is in groups.
+
+# Exams
+
+There are no exams in this class.
+
+# How to do well in this class
+- Ask questions about anything during the class time
+- Start your homework early
+- Ask your classmates or on Piazza since TAs have few office hour slots
+- Have fun :)