Progress for week 49 (2018)

Fra Robin

Versjonen fra 7. des 2018 kl. 11:34

David Kolden

Budget

• Get an overview of already implemented solutions.
• Implement FDCM.
• Write background of FDCM.
• Play around.

Accounting

• FDCM with D2CO now finds pose of an object.
• Created simulation model of gripper.
• Created simulation model of wrist force/torque sensor, but will not simulate its functionality because this is poorly supported by ROS at the moment.
• Wrote some background
• General system clean up

Malin Aandahl

Budget

• Implement new fitness function.
• Find out where the position to the robot is calculated(and change to be the back instead of the front of the robot)
• Finish tutorials about Docker.
• If time set up Docker or implement function to find position.

Accounting

• Worked more with Docker. Currently working on finding environmental variables and putting them in the Dockerfile.
• Made new fitness function, but something might be wrong.
• (Reading to my exam)

Jonas S. Waaler

Budget

• Finish implementing the new baselines to the experiments
• Tune data to fit the classification task (experiment 2)
• Construct algorithms/architectures to solve the classification task

Anders Rønningstad

Budget

• General code cleanup (Structure change)
• Find and implement better value functions for the optimization methods.
• Start looking at swarm optimization

Accounting

• Cleaned up in code for better overview, and making it easier to simulate.
• Created new value function wich I will use to evaluate the methods.
• Updated the objective funciton in the mathematical optimization method