Project Ideas
1) Have an idea? Add it!
2) Want to joint a group? Contact them!
3) Group leader updates the names on the project
*Based on the size of the class there should be approximately 8-10 groups for final projects. There is now a column where Mike lets you know that the basic concept of the project is approved. You will still need to get Mike and undergraduate reviewers to approve the specifics of your proposed algorithms / implementations.
Member Name(s) | Project Idea | Description | Mike Approves |
---|---|---|---|
Alex Cunningham, Philip Rogers, Oktay Arslan | Robot Soccer Planner | RoboCup Small Size Robots - A team of real robots and a full simulator are available, with much of the basic groundwork complete. | Yes |
Hyun-Soo Yi, Evan Seguin, Abel Rayan Infantdani, Sethumadhavan Narayanaswamy | Organization Of Randomized Movable Obstacles | http://www.youtube.com/watch?v=Hi-vIMSr9pQ Please watch this video first. We propose a planner that will organize an environment full of tightly clustered movable obstacles. Each object will have a desired location and orientation that may or may not be obstructed by another object. It will be the goal of our planner to determine a course of actions that will lead to a fully organized environment. To demonstrate this, we will use the well defined structure of chess pieces on a chess board. Our problem will begin with a pile of chess pieces in random locations and orientations, and it will be the task of our planner to determine a way in which all pieces can be returned to their proper location. | Yes |
Martin Levihn, Abhishek Verma, Scott Koziol | Autonomous Golem Limbo | As many have seen in class the Humanoid Robot is quite cool. However during the presentation its was totally controlled by a human, and thus kind of seemed just like a big remote controlled vehicle. In this project we are going to mount a laser-sensor on the robot to get distance information about obstacles in front of the robot. With the help of this information we will than enable the robot to do a kind of "dynamic limbo" where he dynamically tries to duck underneath "suddenly appearing" objects while trying to not lose a lot of speed. | Yes |
Will Wagstaff, Chandan Sheth, Rahul Ravu, Dae-Min Cho | Obstacle Avoidance And Overtaking For Autonomous Rally Car Racing | Trajectory planning for autonomous rally car racing while avoiding collision and overtaking if necessary | Yes |
David MacNair, Raghvendra V Cowlagi, Eohan George, Pascal Minnerup | Learning and Planning Manipulation | UPDATED: A set of objects (like blocks) are placed on a table. An overhead camera can detect their positions and orientations. The robot arm's task is to move the object(s) around to (1) identify kinematic relationships between the objects (e.g., if two blocks are connected by a hinge or by a rigid joint) and (2) move the object(s) to some specified goals. In other words, the arm must learn the kinematic constraints that exist, and then produce a plan which obeys these constraints. | Yes |
Crystal Chao, Tiffany Chen, Advait Jain | Humanoid Table Cleaning | Abstract? | |
Hae Won Park, Hai-Ning Wu, Kasemsit Teeyapan | Golem Batting using LQR-Tree | Making Golem Krang trace the randomly thrown ball and batting it involves delicate planning. We propose in this project a LQR-Tree based system using the current robot and ball state as its input variables. The goal is to find the optimal batting spot in space and time. This system will be implemented in srlib simulation we developed in Mike's Humanoids class. | Yes |
Daniela Steidl, Martin Schuster, Saul Reynolds-Haertle, Richard Bormann | Mixed Palletizing | In our final project we intend to find a heuristic for the mixed palletizing problem with the optimization criteria stability and density. This problem is about stacking as many rigid parcels of different sizes as possible onto a pallet such that the pile is stable. As a first approach we have planned to solve the problem for five different box sizes, which may have arbitrary continuous lenghts, packing only one pallet at a time and considering weight constraints, too, which may restrict which sort of and how many parcels can be stacked on top of each other. We chose the scenario of a supermarket distribution center where we have complete knowledge about the desired amounts of each kind of packet. The goal is to receive a sequence of which parcel has to be put where and in which order to yield a stable but high and densely packed stack. The plan should be visualized by the USARSim simulator since we want to participate in the ICRA robot challenge. | Yes |
page revision: 70, last edited: 29 Nov 2009 22:52