Robot Macgyver Project
Fetch Robot
Research Project in developing a generalized framework for robot tool improvization using affordances. Complex reasoning allows robots to “think outside the box” using available items to improvize in unforseen environments.
- Advised by Prof. Henrik Christensen
- Developed recognizing and using affordances of objects and tools.
- Explored the use of behavior trees in dynamic task planning.
- Implemented an end-to-end working pipeline on V-Rep CoppeliaSim Simulation Environment, and on a real Fetch robot for table-top settings.
- Thesis available online.