CSCI 3302 “Introduction to Robotics”

The overarching learning goal of this class is to create an appreciation for the tight interplay between mechanism, sensor, and control in the design of intelligent systems. This includes (1) formally describing the forward and inverse kinematics of a mechanism, (2) understanding the sources of uncertainty in sensing and actuation as well as to describe them mathematically, (3) how to discretize the robot’s state and reason about it algorithmically, and (4) experiencing 1-3 on a real robotic platform.

After using a variety of platforms, this iteration of the class will use the “Sparki“, a simple differential wheel platform from ArcBotics, allowing students to implement simple odometry, Markov localization and simple planning for object retrieval tasks.

The distributed robotic garden in MIT Technology review. Advanced Robotics 2011 The "Ratslife" environment PrairieDog with a CrustCrawler manipulating arm

Meetings

This class consists of a lecture and a laboratory component. Meetings are Tuesday 3:30-4:45pm in FLM157 (lecture) and Friday 12-2pm in TBD (lab).

Grading

The grade is based on written homework assignments (30%), laboratory assignments (20%), a final project (30%), and class participation (20%).

Office Hours

Thursday, 9-11am in ECES 118C.

Textbook

We will be using my free, open-source textbook “Introduction to Autonomous Robotics”, which can be downloaded on Github or purchased from Amazon.

Schedule

Please refer to the class’ moodle site.

Project

Students will conduct an independent project in groups of 3-5. Each project should highlight innovative sensing,  localization, and planning.

   
Intercepting a moving object (Eric, Ryan, Ethan)  Object retrieval and delivery: Hazardous waste (Justin, Arnaud, Will, Yadira) Object retrieval and delivery: Barkeeper (Ian, Steffen, Chris, Justin, Connor)
   
Hybrid reactive-deliberative control for coverage: fire fighting (Alessandro, Brent, Jacob, Vincent)  Object retrieval and delivery: Garbage collection (Henrik, Matthew, Sean) Object retrieval and delivery: color sorting (Zack, Jared, Brian, Jennifer and Brian)
   
Reactive control and odometry: party game (Sarah, Phillip and Brian)  Planning and control: battery exchange (Shane, Branden, Dan, Cameron and Peter)  Planning & Android integration: guide bot (Emily, Erin, Thomas, and Lauren)
 
Reactive control & Localization (David, Sean, Kyle, Michael)  Tele-operation (Mario, Jesus, Brooke, and Jordan)

Debates

Debates will be “Oxford-style”, following this format:

  •  audience pre-debate vote (for, against, undecided)
  •  7 minute presentations “pro”, 7 minute presentations “contra”
  •  5 minutes discussions
  •  2 minute closing statement “pro”, 2 minute closing statement “contra”
  •  audience vote

Topics

  • Robots putting humans out of work is a risk that needs to be mitigated.
  • As robots from autonomous lawnmowers to robotic cars are sold as “intelligent systems”, liability for robots should entirely lie by its manufacturer.
  • Robots should have the capability to autonomously discharge weapons / drive around in cities (autonomous cars).
  • Intelligence is only possible with embodiment
  • Robots do not need to be as cognitive as humans in order to be useful as making the environment intelligent is sufficient.
  • Robots need to be made differently than from links, joints, and gears in order to reach the agility of people

Grading

Debates will be evaluated in equal parts to the
  • quality of the presentation and defense. Note: it is not your personal opinion that counts but to execute a clear Pro or Contra argument.
  • quality of the background research. What is the (technical) state of the art in robotics in your debate topic?
  • ability to ground arguments in technical facts.

Misc

Please refer to the following guidelines on disability, medical conditions, religious observances, behavioral rules, and honor code.

Previous classes

 

Comments are closed.

Set your Twitter account name in your settings to use the TwitterBar Section.