My publications are on Google Scholar.
I am working on bring best practices from flipped classrooms into Massive Open Online Courses (MOOCs). This work includes creating a peer grading system for grading short answer questions. I am also working on a design to create personalized exams for online students. These exams help students achieve their personal goals.
- Personalized Exams and Learning in Massive Open Online Courses
- Peer Reviewing Short Answers using Comparative Judgement
I am working on an online class that has over 500 students. I always want to discuss things that can improve teaching. So if you want to talk about it, write me an email.
Whole Body Dynamic Manipulation
This project investigates three effective manipulation strategies for wheeled, dynamically balancing robots with articulated links. By comparing these strategies through analysis, simulation and robot experiments, we show that contact placement and body posture have a significant impact on the robot’s ability to accelerate and displace environment objects. Given object geometry and friction parameters we determine the most effective methods for utilizing wheel torque to perform non-prehensile manipulation.
- Dynamic Pushing Strategies for Dynamically Stable Mobile Manipulators
- Equations of Motion for Dynamically Stable Mobile Manipulators
Also see the robot Golem Krang.
Planning for Logistics
We worked on framing the mixed palletizing problem as a knapsack problem and finding efficient ways of solving them. We designed a the VMAC (Virtual Manufacturing and Automation Competition) that was hosted in ICRA 2010 and 2011. To standardize testing across mixed palletizing solutions we designed standards for testing pallets.
We also worked on crating a design methodology for mapping the configuration space of multirobot systems in a warehouse.
Robots playing chess with each other is cool. I worked on the perception system of the Golem Chester robot. The perception was build on the MESA Range sensor which predates the Kinect.
We participated in the first Nao League at RoboCup 2008. Our team was called GTCMUnited (in collaboration with CMU). We reached the final of the International League and lost in a penalty shootout. You can see the final match in this video. You will notice that this was ancient because it was shot with a potato.
- Hybrid tracker for OpenCV. See video of it working.
- DART: Dynamic Animation and Robotics Toolkit
If ever there is a robot uprising, I want to leave proof here that I was involved.