Home Teaching WS1920 Lab Humanoid Robots (MA-INF 4214)

Lab Humanoid Robots (MA-INF 4214)

Humanoid robots are currently an active research platform. Since they have a human-like body plan they can act in environments designed for humans. Humanoid robots are able to, e.g., climb stairs, walk through cluttered environments, and open doors.

Participants will work in group of 2 or 3 on one of the possible topics. There will be 1 group for each topic.

At the end of the semester each group will give a live demonstration of their project with a real robot accompanied by oral moderation while the robot is performing the task. The demonstration should be approximately 10 minutes long. Every member of the group should speak up and explain there part of the system in a few sentences. There is no need to use any presentation slides. However, please use the large screen in the lab for the presentation so that everyone can see what your software is doing. The closest lab PC will be connected to the screen for this purpose, so be sure to test your code on that machine before the demo.

When the presentation is complete, each group will be asked a few questions by the HRL staff members or preferably the other students. Everyone is required to be present and to watch the presentation of the other groups.

Aside from the demonstration, every group is required to submit a lab report. The report is due on the morning before the demonstration. Please describe the task you had to solve, in what ways you approached the solution, what parts your system consists of, special difficulties you may have encountered, and how to compile and use your software. Please include a sufficient number of illustrations. Apart from the content, there are no formal requirements to this document. It is sufficient to submit one lab report per group, it must be be pushed to the groups git repository before the lab presentation.

The grade of the lab will be depended on the final presentation, the performance of the robot during it and how well the assigned task was solved.

 

Contact:

 

Important dates:

All interested students should attend the Introductory Meeting. In the Introductory Meeting, we will present the topics, the schedule, the registration process, and answer your questions.

Wednesday, 16. October 2019, 10:00 - 11:00, room 0.011
Introductory Meeting (old_slides)
Friday, 18. October 2019, 10:00 Registration deadline and topic selection on our website
Thursday, 31. October 2019, 23:59 Registration deadline in BASIS
Wednesday, 18. March 2020, time and room tbh Lab presentation and deadline for lab documentation

After the first lab meeting, the participants can arrange their working schedule individually after consulting with their supervisor.

 

Registration

The registration will be opened after the introductory meeting.

 

Topics:

You can choose between one of the following topics:

 

Follow the Path:nao_follow_the_line_small.JPG
In this project, the robot's task is to follow a path marked on the floor. The robot should evade obstacles and be able to bridge short gaps in the path. The path is marked by a yarn. Obstacle and yarn detection should be implemented using a Convolutional Neural Network.

Focus: computer vision, navigation
Programming language: Python, C++

 

 

 

Toy Detection:lab_pic_1.jpg
The goal of this project is to detect a specific toy among a  small group of given toys based on user input. The detection should be done using a Convolutional Neural Network and augmented training data. Once the toy is  detected the robot should move to it, grab it and return it to the user. 

Focus: computer vision, CNNs
Programming language: Python, C++

 

 

Soccer:soccer_pic.jpeg
We place a red ball on a soccer field in front of a goal consisting of two yellow goal posts. The robot has to detect  the goal and the ball with its built-in camera, walk to the ball in the right angle, and kick the ball into the goal.

Focus: computer vision, motion planning, navigation
Programming language: C++

 

 

Turtlebot:turtlebot_image.png
Program a mobile robot to avoid obstacles and to find an object in a labyrinth. The object needs to be picked up and brought back to the entrance.

Focus: computer vision, motion planning, mapping, navigation
Programming language: C++, ROS

 

 

Robot Arm:robo_arm_image.png
Program a robot arm to sort objects into a cup. The objects need to be detected in the sensor image and distinguished from the cup. The arm needs to be moved to pick up the object and to drop it into the cup while avoiding collisions.

Focus:motion planning, computer vision
Programming language: C++