xDR Challenge in industrial Scenario: IPIN 2019’s Official Off-site Competition Track (Track5)
Proof practical performance of your PDR algorithm under realistic industrial scenarios!
Winner and Runner-up can get more than 100,000JPY cash prize and extra prize!
We are accepting pre-admission，now.
- 19 July, 2019
- Deadline extended: technical description to 30 August.
- 16 July, 2019
- Added external organizer for xDR Challenge 2019.
- 25 Jun, 2019
- Categories of the competition are added.
- 23 May, 2019
- Call for participation are updated. (E-mail address for pre-admission is added!)
- 22 May, 2019
- Call for participation are added.
A link for sample evaluation script are provided.
- 15 May, 2019
- Contents are updated.
- 5 May, 2019
- Overview is updated. Important dates and Prize are added.
- 23 April, 2019
- First call for participation of xDR challenge 2019 has been announced!
xDR Challenge in Industrial Scenarios 2019 (hereinafter referred to as xDR Challenge 2019) will be held as a sequel competition to "PDR Challenge in Warehouse Picking" at IPIN2017 and “xDR Challenge for Warehouse Operations 2018” at IPIN2018. This year’s competition will be held as IPIN2019’s official competition track (track5). The competition is an off-site tracking competition by sharing sensor data measured in actual industrial fields. The aim of the competition is to encourage the researchers to develop the xDR algorithms which can be utilized for realistic industrial scenarios. The xDR Challenge 2019 will be hosted by PDR benchmarking standardization committee.
This year, we will change the target fields of the competition from warehouse to other fields. First, we selected a Japanese restaurant as a target. The restaurant is very unique because employees and dish delivering robots are collaboratively working together in the restaurant. Additionally, we also selected a factory in manufacturing industry as another typical types of industry. The operations of employees can be objectively analyzed for improving the operations by data-driven service engineering. The results of estimation by Indoor localization and action recognition are the most important inputs for the objective analysis.
In those scenarios, we will prepare two categories of the competition in the xDR Challenge 2019.
- PDR based indoor localization track with a waist-mounted sensor
- Action recognition track with body-mounted sensors
If you tell us an intention to join the competition, we can provide you previous competition’s dataset as sample data.
We look forward to your participation!
- Ryosuke Ichikari, Katsuhiko Kaji, Ryo Shimomura, Masakatsu Kourogi, Takashi Okuma, Takeshi Kurata: Off-Site Indoor Localization Competitions Based on Measured Data in a Warehouse, Sensors, vol. 19, issue 4, article 763, 2019.
- Masakatsu Kourogi and Tomohiro Fukuhara, Case studies of IPIN services in Japan: Advanced trials and implementations in service and manufacturing fields in special session "Value Creation in LBS (Location-Based Services)", IPIN 2017.
- Takeshi Kurata, Ryosuke Ichikari, Ryo Shimomura, Katsuhiko Kaji, Takashi Okuma, Masakatsu Kourogi: "Making Pier Data Broader and Deeper: PDR Challenge and Virtual Mapping Party", MobiCASE 2018 (9th EAI International Conference on Mobile Computing, Applications and Services) (2018)
Call for Participation
Currently, ｗe are accepting pre-admission.
We will provide sample data for those who completed pre-admission.
For pre-admission, please send following information to xDR-Challenge2019@aist.go.jp.
- Name of team
- Name of representative person in your team
- Affiliation of the representative person
- E-mail address of the representative person
Pre-admission is a preliminary registration just for providing sample dataset and information.
We will open the real registration for the actual entry of the competition, when the actual datasets are ready for delivery.
Sample data and evaluation script
As described in the call for participation, we are providing sample dataset those who completed pre-admission.
As the sample data, we will provide you previous competition datasets with ground truth for now.
You can objectively evaluate your algorithm with the dataset for xDR Challenge 2018 and evaluation script uploaded on Github
(We can provide sample data, if you registered)
- Technical description:
- 15th July, 2019
30th August, 2019 (Extended!)
- Result submission:
- 14th September, 2019
- Announcement of Winners:
- During IPIN2019
Categories of the competition
(Manufacturing track & Restaurant track)
- Manufacturing track: Estimating trajectories of employees who work in a factory in manufacturing industries.
In the manufacturing track, we utilized PulsarGum as BLE beacons. The PulsarGum is battery-free beacon. BLE signals are emitted disproportionally, and dependent of the condition of photovoltaics.
The shortest interval of the BLE signal emission is 1.26 sec. The sensor data used for the competition is measured by BL-02.
A typical image of the target factory is shown in Fig. A.
How to carry the device is shown in Fig. B. Floor plan of the manufacturing track is shown in Fig. C.
- Restaurant track: Estimating trajectories of employees who work in a Japanese restaurant together
with food delivering robots. Action recognition is also planned to be included.
In the restaurant track, we utilized BLE beacons by Aplix and Nexus 5 for sensor logging.
They are same as used in the xDR challenge 2018.
A typical image of the target factory is shown in Fig. D.
How to carry the device is shown in Fig. E. Floor plan of the manufacturing track is shown in Fig. F.
Prizes: Manufacturing track:
- - Winner: JPY150,000+BL-02P or JPY100,000+BL-02P+TECCO+PulsarGum
- - Runner-up: JPY100,000
- - Winner: JPY150,000+BL-02P or JPY100,000+BL-02P+PDRmini+PulsarGum
- - Runner-up: JPY100,000
BIGLOBE’s BL-02 GOV’s TECCO
Sugihara SEI 's PDR Mini sensor PulsarGum (FUJITSU)
We suggest you to learn from very valuable PDR tutorial by Antonio R. Jiménez at IPIN 2017.
You can download tutorial slides and sample PDR code and sensor logger from
PDR code authored by LOPSI group at Centre for Automation and Robotics (CAR), CSIC-UPM, Spain.
Sensor data contained in competition dataset are measured with similar sensor logger introduced in the tutorial.Note that the way to carry sensor devices will be different with the tutorial. The sensor devices used for this competition are mounted on waist or stored in chest pocket.
National Institute of Advanced Industrial Science and Technology (AIST), Japan
Centre for Automation and Robotics (CAR), CSIC-UPM, Spain
Soyeon Lee, Ph.D.
Electronics and Telecommunications Research Institute (ETRI), S. Korea