Learning Japanese

Today was a very exciting day. In the were jumping over the fences to save some time but in the end we could enter just by nine. We love the precision of Japanese people, they are even stricter than Germans in many cases. The previous sentence contains compliments for both cultures :).

Ivanna has a little bit of cold and decided to fight it with a vitamin inception through 2 liters of orange juice. That must be healthy. All in all it was a quite good day. TIAGo passed the security checks and cleaned the toilette and served in a future convenience store. We are exited about tomorrow and will go to our capsules early tonight. Later that day there was a surprise welcome reception with a lot of food, beer and sake like drinks involved. During the day we were provided with all of the needed setup information which turned out to be fully in fluent Japanese. After only a few hours of communication and questioning of a lot of people we finally figured out most of it. This was continued by team leader meetings held in Japanese. Luckily we got instant translations by our Happy Mini friends and visual input from a screen. We are coming along quite good and are now motivated to take some Japanese lessons.

TIAGo also starts preparing for the Storing and Disposal task. Here this is our custom prepared container. Note there are markers attached. That’s something we usually don’t do but it eases up things in this task a lot.

Today we are in the mood to post some slightly more technical pictures and we like to present our “recipe” for extracting toilet seats to clean.

  • Step 1) Find planar surface in front of the toilet

  • Step 2) Do some morphology to get a closed form of the toilet seat

  • Step 3) And reduce it to a line

Those lines then serve as input for sampled trajectory points

  • Step 4) Attack!

When you code all day and need to fix urgent things you get creative about the places and poses you code.

To be honest, a domestic environment like RoboCup@Home and the European Robotics League for Service Robots has it’s benefits in that case.

We have a lot of fun here and TIAGo improves every day in big steps. Let’s face some new challenges tomorrow.

Sadly Lukas doesn’t improve like TIAGo and faces new bug all time. This time posing on the official competition toilet.

Tome to go asleep.

World Robot Summit first preparation day

wrs arrival

This morning we arrived at the Big Sight exhibition center in Tokyo. The event is very nice organized. The registration went quite fast and everything was already set. Soon we got our TIAGo and could start testing quite fast. Beside some time synchronization errors everything went smooth this far. Seems like that not all teams are participating in all challenges like we do and many use heavily customized robots for each task. Our approach is to use one mobile robot for all of the tasks. There are some also big companies as well participating. For now we have to leave the competition place and will face new challenges tomorrow. The actual challenges start on Thursday.

preparation After we fixed the synchronization issues we were ready to test.

toilet_cleaning Tobias was testing the toilet cleaning task. TIAGo managed to find the toilet seat and executed a trajectory to clean the seat. Further we managed to find the trash on the ground. Up to now it is a bit tricky because we are using a sponge as a gripper for the prior cleaning task.

toilet_cleaning2 This is TIAGo in action during the cleaning of the toilette.

Tokyo we are coming

Half a year ago we qualified for the World Robot Summit in Tokyo. Now we are in Nagoya slowly approaching our destination with a sub sized team consisting of TIAGo, Ivanna, Tobias, Lukas and Raphael. We are taking part in the Future Convenience Store Challenge where we compete in tasks like Restocking a convenience store, cleaning a customers toilet or an individual visionary view customer interaction of how robots could be used in the convenience store of the future. We are looking forward to our participation and are also happy to meet some of our friends there.

This is us after packing up all the stuff. When you compare this picture to the old ones it looks like a easy travel. TIAGo was shipped by cargo and we just take minimal stuff with us for the competition.

In Nagoya we spotted a Hawaiian dance festival that we joined for quite a while until our connection flight came.

More information about the WRS.

A big thanks to PAL Robotics for all the support and the Japanese government which funded the WRS and thereby covered most of our expenses.

IROS TIAGo Manipulation Challenge

TIAGo inspecting the table during the preparation
TIAGo inspecting the table during the preparation.

Yesterday at 17:00 we had our mobile manipulation demonstration with TIAGo at the IROS conference. For the finals six teams from all over the world have been qualified.

The preparation was quite intense, as there was just half a day of preparation on site and we had to use a robot that we have not used or configured before. But this is also an opportunity to challenge participants and actually it is quite comfortable for us to attend challenges where we don’t have to ship the robot.

We intended to show our approach for imitation learning. But due to the issues we had to configure the robot on-site we could not concentrate on the preparation of that and decided to run an old demonstration where TIAGo cleans a table and puts hard to grasp objects like forks, knifes and spoons from a table into a bowl.

During the preparation we faced a lot issues that where caused by time differences between the robot and our notebook that we attach for computations. Even when the differences are quite low that can cause behaviours like destroyed maps or stooping the robot before an obstacle later as it is supposed to.

We overcame this issue remotely with Niklas via telephone. Another issue that we did not figure out initially was that on the robot itself was a mapping component running that was fighting with ours. We where thinking about a wrong transformation somewhere in the robots laser position. This was fixed by just disabling the mapping component running on the robot and rely on our custom solution. These are small issues when you have more time but for a scheduled demo with preparation of just one day those issues can stress you. Therefore we decided spontaneously to show another demo that did not need that much preparation from our side. Up to the end the time was still fluctuating quite a bit but during the demo it was constant and we didn’t face any further problems.

During the presentation TIAGo was doing a good job. We also got remote help to run this demo from Tobias back in Koblenz. Even so it was not calibrated we managed to put some objects into the bowl and in cases where the robot was not gripping correctly it tried again because the offset between robot end-effector and the RGB-D camera. There was also a closed loop sensing for identifying when to close the gripper after getting feedback on touch with the table. This is highly relevant for hard to grasp objects like the cutlery as in the depth image it’s hard to estimate a accurate position for those small objects because there is usually no or a very low difference between the object and the table.

Once we are back we will focus on the World Robot Summit in Tokyo.