Project Group/Seminar/Lab Report:
Putting Things on a Table Efficiently
Lola Learnalot
Mat. Nr.: 1234567
January 16, 2021
Figure 1: The robot as a means to put things on tables efficiently.
Abstract 3 Methodology
Every day we pick things up from the ground and put them We will now discuss our novel approach in detail.
on tables. Despite the ubiquitous presence of this task, this
problem does not have a sufficiently optimized solution yet. 3.1 Robot
In this report, we will explore the usage of robotics in order The base of the robot is a cube with wheels. In order to be
to make putting things on tables more efficient. able to grab things, it also has a robotic arm. At the end of
the arm is a robotic hand with three fingers. The complete
1 Introduction robot can be seen in Figure 1, while the single parts of the
robot are depicted in Figure 2.
Everyone has to put something on a table at some point.
However, picking things up is quite a tedious task. Reducing 3.2 Robot
the effort needed to do this would make everyone’s life much
easier. The base of the robot is a cube with wheels. In order to be
able to grab things, it also has a robotic arm. At the end of
We will introduce a novel robot to tackle this problem in
the arm is a robotic hand with three fingers. The complete
a much more efficient way. The efficiency is assessed in a
robot can be seen in Figure 1, while the single parts of the
thorough evaluation.
robot are depicted in Figure 2.
2 Related Work 3.3 Robot
The work of First and Second (2014) and others (Third, The base of the robot is a cube with wheels. In order to be
2015) is fundamental in this research area. They show how able to grab things, it also has a robotic arm. At the end of
difficult it can be to pick things up and put them on a table. the arm is a robotic hand with three fingers. The complete
All of these approaches work, but none of them is as robot can be seen in Figure 1, while the single parts of the
efficient as ours, as can be seen in Section 4. robot are depicted in Figure 2.
1
(a) The robots body. (b) The robots arm.
Figure 2: The different components of the proposed robot.
3.4 Algorithm
The algorithm is very simple and consists of the following
steps:
1. Grab something using the pickup() function
Tears
2. Move arm to table
Robotic Support
3. Open hand with open_hand()
Due to our efficient implementation, the algorithms run time
complexity is in O(n log n). No Tears
Data sets avg. speed avg. error
Robot 125.1 2.2
Human 87.4 2.1
Figure 3: Qualitative assessment of emotional changes
Table 1: Pickup speed and error comparison. during the period of robotic support.
4 Evaluation 5 Future Work
In order to find out, how useful the proposed robot is in While our robot is already able to outperform most of our
reality, I will do a user study with 500 participants, some of test subjects in a fully autonomous manner, it still can be
which are novices and some of which are experts in putting improved with respect to the mobility. Right now, due to the
things on tables. Table 1 shows the average pickup speed of small wheels, it is not suited in situation with a potentially
our test subjects compared to the pickup speed of our robot. very bumpy ground, e.g. gardening.
During our experiments we discovered, that people being
supported by our robot are happier than people, who have to
6 Conclusion
grab their stuff themselves. This is qualitatively evaluated in We have developed a novel robotic solution to the problem
Figure 3. of picking things up and putting them on a table. Despite
2
the shortcomings described in Section 5, we still believe
in widespread usage of the presented robot within the next
decade.
