ToyCollect - A mobile robot which collects toys from unaccessible places
2020/02/22
I was motivated for this project by my - at project start - two-year old daughter who always
hid her toys under the couch. It was quite hard finding out what lay down below. So we built a robot that could be
remotely controlled by any Android device via Wifi, drove under
the couch, looked at the toys, and moved out what toys it found. It was
just under 6.5cm tall, streamed high-quality H264-encoded video in real time,
was controlled with a simple touch-based interface, and we even put
in a LED lamp so you could actually see something in dark places.
In the meantime, we have built numerous variants of the original robot and are researching on how to make them fully autonomous. Here is a short overview of the different robots, partly with blueprints, as well as the different remote controls.
Robots
| Type | Robot plattform | Camera | Main controller | Chassis | Power | Local DL? | Construction |
|---|
v1.0
 | Pololu Zumo (#1418) | 1x RPi Camera Rv1.3 (right) | 1x RPi 1B | Modified black chassis | 4x 1.5V 2900mAh Lithium batteries (non-rechargable) | No, <1fps | 2014
Blueprint |
v1.1
 | Pololu Zumo (#1418) | 1x RPi Camera Rv1.3 (centered) | 1x RPi 2B+ v1.2 | Modified transparent chassis | 4x 3.7V 14500 Lithium-Ion batteries | No, <1fps | 2016
Blueprint |
v1.2
 | Pololu Zumo (#1418) | 2x RPi Camera Rv2.1 (Stereo) | 2x RPi Zero W | 3D-printed chassis | 4x 3.7V 14500 Lithium-Ion batteries | No, <1fps | 2018 |
v1.21 (R2X)
 | Pololu Zumo (#1418) | 2x RPi Camera Rv2.1 (Stereo) | 2x RPi Zero W | Modular 3D-printed chassis | One of:- 4x 3.7V 14500 Lithium-Ion batteries
- 4x 1.5V Alkaline batteries
- 4x 1.2V NiMH batteries
- 4x 1.2V NiCd batteries
| No, <1fps | 2019
Blueprint |
v1.3 (K3D)
 | Pololu Zumo (#1418) | 1x RPi Camera Rv1.3 with Kúla3D Bebe Smartphone lens (Stereo) | 1x RPi 3B+ | Modified transparent chassis | 4x 3.7V 14500 Lithium-Ion batteries | Yes, 8fps | 2018
Blueprint |
v2.0
 | Dagu Robotics Wild Thumper 4WD (#RS10) | 2x RPi Camera Rv2.1 (Stereo) | 1x RPi Compute Module 1 on evalboard | None (open case) | 1x 7.2V 2S 5000mAh Lithium-Ion battery | No, <1fps | 2016 |
v2.1
 | Dagu Robotics Wild Thumper 4WD (#RS10) | 2x RPi Camera Rv2.1 (Stereo), Asus Xtion depth camera | 1x RPi Compute Module 1 on evalboard | None (open case) | 1x 7.2V 2S 5000mAh Lithium-Ion battery | No, <1fps | 2017 |
v2.2 (OUT)
| Dagu Robotics Wild Thumper 4WD (#RS10) | 2x RPi Camera Rv2.1 (Stereo), Asus Xtion depth camera | 1x RPi Compute Module 3 on evalboard | None (open case) | 1x 7.2V 2S 5000mAh Lithium-Ion battery | Yes, 8fps | 2018 |
Remote controls
| Type | Platform | Robot compatibility | Code |
|---|
| | v1.0 | v1.1 | v1.2 | v1.21 (R2X) | v1.3 (K3D) | v2.0 | v2.1 | v2.2 (OUT) | available? |
|---|
| Touch control with circle plus LED brightness | Android | Yes | Yes (old TCserver) | | | | | | | Yes |
| Touch control with two circles | Android | Yes | Yes (old TCserver) | | | | | | | on request |
| Head movement control via Google Cardboard | Android | | | Yes | Yes | Yes | Yes | Yes | Yes | on request |
| Touch control of robot and robot arm | Android | | | | | | Yes | | | on request |
| 2x Wii & Nunchuk controller for robot and robot arm, Google Cardboard as display | Linux & Android | | | | | | Yes | | | on request |
| Driving wheel and accelerator/brake (old PlayStation controller), display on 40" 3D-screen | Linux | | | | | | Yes | Yes | Yes | on request |
| Bluetooth controller | Linux (RPi, TCserver) | Yes (new TCserver) | Yes (new TCserver) | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Pretrained Deep-Learning models (autonomous behaviour) | Linux (RPi, TCcontrol) | | | Yes (server) | Yes (server) | Yes (local) | Yes (local) | Yes (local) | Yes (local) | Yes |
The pretrained deep learning models require video output in uncompressed format and low resolution for efficiency reasons. However, most other remote controls require video output in compressed format (H2.64) and high resolution for quality reasons. Therefore, at present, the use of pretrained deep learning models can only be combined with the Bluetooth controller remote control.
If you find our research helpful and use it for your own research publications or technical reports, please cite our paper:
Seewald, AK. Revisiting End-to-End Deep Learning for Obstacle Avoidance: Replication and Open Issues. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020), Valetta, Malta.
Partially funded by FFG Talente 2014,2016,2017,2018,2019
2020/02/06
Installation of TCserver
TCserver controls the robot, LEDs and cameras and receives commands via Bluetooth or Wifi. For V1.21 (R2X) we distinguish the MASTER Raspberry Pi with connected motor controller and the SLAVE. For the robot models with only one RPi, we conveniently also define it as MASTER.
The following three steps must be executed for the V1.21 (R2X) robot on MASTER and SLAVE, otherwise only on the one.
ol.tc li { padding-bottom:...
2019/07/30
Here is all the information so you can build yourself a ToyCollect V1.121 (R2X) robot.
Hardware
First you need to go shopping. We will need:
1x Zumo Chassis Kit (#1418)
2x 100:1 Micro Metal Gearmotor HP (#1101)
1x Pololu Qik 2s9v1 Dual Serial Motor Controller (#1110)
3x 5V Step-Up/Step-Down Voltage Converter S9V11F5 (#2836)
1x Mini MOSFET Slide Switch with Reverse Voltage Protection, LV (#2810)
1x 0.100" (2.54 mm) Breakaway Male...
2018/07/15
If you want to build a V1.1 robot, remove Kùla Bebe and its mount and add a Sumo Blade.
Here is all the information so you can build yourself a ToyCollect V1.1 or V1.3 (K3D) robot.
Hardware
First you need to go shopping. We will need:
1x Zumo chassis kit (#1418)
2x 100:1 Micro Metal Gearmotor HP (#1101)
Only for V1.1: 1x Basic Sumo Blade for Zumo Chassis (#1410)
1x Pololu Qik 2s9v1 Dual Serial Motor Controller (#1110)
1x 0.100"...
2015/07/15
If you need stereo cameras, please consider building a V1.21 (R2X) or V1.3 (K3D) robot instead.
Here is all the information so you can build yourself an original ToyCollect V1.0 robot.
Hardware
First you need to go shopping. We will need...
1x Zumo chassis kit (#1418)
2x 100:1 Micro Metal Gearmotor HP (#1101)
1x Basic Sumo Blade for Zumo Chassis (#1410)
1x Pololu Qik 2s9v1 Dual Serial Motor Controller (#1110)
1x 0.100" (2.54 mm)...
2020/02/22
Seewald, AK. Revisiting End-to-End Deep Learning for Obstacle Avoidance: Replication and Open Issues. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020), Valetta, Malta.
2019/03/07
As part of the Talente Internships for pupils 2018 by the Austrian Research Promotion Agency (FFG), Dr. Alexander K. Seewald was honoured for the excellent supervision of his intern Miriam Tokmak.
2019/07/14
Two day seminar on "Future Media" in lecture course Game Studies of Danube University Krems (class started in winter semester 2017)
2018/07/11
Two day seminar on "Future Media" in lecture course Game Studies of Danube University Krems (class started in winter semester 2017)
2018/04/07
Two day seminar on "Future Media" in lecture course MedienSpielPädagogik of Danube University Krems (class started in winter semester 2016). This time we were at the Edupole campus in Luxemburg.
2018/03/28
Two day seminar on "Future Media" in lecture course MedienSpielPädagogik of Danube University Krems (class started in winter semester 2017)
2017/07/19
Two day seminar on "Future Media" in lecture course Game Studies of Danube University Krems (class started in winter semester 2016)
2017/04/21
Two day seminar on "Future Media" in lecture course MedienSpielPädagogik of Danube University Krems (class started in winter semester 2015). This time we were at the Edupole campus in Luxemburg.
2017/04/12
Two day seminar on "Future Media" in lecture course MedienSpielPädagogik of Danube University Krems (class started in winter semester 2016)
2016/11/01
Invited talk on our ToyCollect platform for the Erasmus+ project "Game Based Learning to Alleviate Early School Leaving" (GBL4ESL), held at Danube University Krems, Austria.
2016/07/13
Two day seminar on "Future Media" in lecture course Game Studies of Danube University Krems (class started in winter semester 2015)
2016/03/23
Two day seminar on "Future Media" in lecture course MedienSpielPädagogik of Danube University Krems (class started in winter semester 2015)