direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Motion Planning Under Contact and Uncertainty with Dynamic Simulation

master thesis

Motivation Uncertainty is the major obstacle for robots manipulating objects in the real world. A robot can never perfectly know its position in the world, the position of objects, and the outcome of its actions. A particularly hard challenge is motion planning under uncertainty. How should the robot move, if the model of the world might be wrong or incomplete?  However, a robot can significantly reduce uncertainty if it uses contact sensing to establish controlled contact with the environment. Imagine a robot pushing objects into an edge of the environment - this action will reduce uncertainty over all objects positions. 

Description of Work

In our lab we implemented a sampling-based motion planner that combines controlled contact with configuration-space search (https://www.youtube.com/watch?v=mUbjuJ4pk8s). However, our planner is currently limited to static scenes and does not incorporate actions such as pushing or grasping. In this project you will use our uncertainty-based RRT-planner with a dynamic simulation including movable objects (using the bullet physics engine).

For this project you need good C++ programming skills. Experience with the roboticslibrary (from our robotics and compbio classes) or bullet physics is a plus.

People

Arne Sieverling
Oliver Brock

 

back

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions