Master Thesis - Robotics Motion Control

Västerås,Vaestmanland County,Sweden
09 Oct 2016
30 Nov 2016
Contract Type
Full Time
You will be part of the motion control group at ABB Robotics. We are responsible for a wide range of areas within the robot controller development spanning from modeling, identification, control design and tuning to signal processing for diagnosis and supervision as well as optimization for path planning.

Here are some possible areas for a thesis project within the motion control area. The actual scope of the project will depend on the applicants cv and the priorities within the development teams:
1.Learning local models for improved feedforward control. In this project the global robot model will be extended by local models allowing for more accurate feedforward control. Since local errors are highly non-linear it is of interest to investigate machine learning modelling techniques in addition to more traditional modelling.
2.Diagnosis and supervision on control loop level. It is possible to change the loop gains in the controller and there is always a risk that a too high gain can introduce increased disturbances and sometime even instabilities. The loop level diagnosis and supervision should be able to detect these phenomenon and also provide support on what to change to reduce the unwanted effects.
3.Sensor based path and trajectory generation. This project consider the optimization of path and trajectory in applications such as conveyor tracking where the desired path changes dynamically due to external sensor inputs. The goal is to react fast to changes in the senor input but, at the same time, still be able to fulfill the constraints, such as speed and acceleration, in the optimization.
4.Data-driven services for supervision and diagnosis. Based on the data provided by robots connected to the cloud or locally to some data collector, this project aims at exploring data driven methods, such as machine learning, to develop robot supervision and diagnosis functionalities. One application could be to find patterns in large amount of data to be able to find robots with exceptional usage profiles, robots with incorrect load definitions, etc.

The master thesis project requires good knowledge in automatic control and signal processing as well as experience of the tools Matlab and Simulink.