Announcement of Results of xDR Challenge 2018

National Institute of Advanced Industrial Science and Technology
Announcement of
Results of xDR Challenge 2018
xDR Challenge 2018 Organizers
(Ryosuke Ichikari1, Ryo Shimomura12
AIST1, University of Tsukuba2)
1
IPIN 2018@Nantes
SS A Survey on Indoor Localization Competitions
10:20 - 12:20 Sept. 26th, 2018
National Institute of Advanced Industrial Science and Technology
xDR Challenge for Warehouse Operations
• xDR Challenge for Warehouse Operations 2018 was held as an
sequel competition to "PDR Challenge in Warehouse Picking“
• Host:PDR Benchmark Standardization Committee
• Competition of Dead-Reckoning for Pedestrian and Vehicle
– xDR=PDR+VDR
• Important dates
– Testing period: Mid May to Mid Aug., 2018
– Results submission due: 18th Sept, 2018
– Announcement of Winners:
Now (This Special Session)
• Sponsors:
2
National Institute of Advanced Industrial Science and Technology
Two competition tracks
• Individually determining winners in each tracks
• PDR-Track
– Tracking workers who move by foot during warehouse
operations
– Shared data: Smartphone sensor data for PDR, BLE tag’s
signal, warehouse’s spec, Partial WMS log. reference movie
for typical picking
• VDR-Track
– Tracking forklift driven by employee during warehouse
operations
– Smartphone sensor data measured by attaching
smartphone onto the forklifts
– Shared data: Smartphone sensor data for VDR, BLE tag’s
signal, warehouse’s spec, forklift spec., partial WMS log.
– Sample data with known path are prepared. (For beginners)
3
National Institute of Advanced Industrial Science and Technology 44
Ubicomp/ISWC 2015 PDR
Challenge
PDR Challenge in Warehouse
Picking in IPIN 2017
xDR Challenge for
Warehouse Operations
2018
Scenario
Indoor pedestrian
navigation
Picking work inside a
logistics warehouse
(Specific Industrial Scenario)
General warehouse
operations including picking,
shipping and driving forklift
Walking
/motion
Continuous walking while
holding smartphone and
looking at navigation screen
Includes many motions
involved in picking work, not
only walking
Includes many motions
involved in picking, shipping
operations and, not only
walking. Some workers
may drive forklift
On-site or
off-site
Data collection: on-site
Evaluation: off-site
Off-site Off-site
Number
of people
and trial
90 people, 229 trials 8 people, 8 trials
34 people + 6 forklifts,
170 trials (PDR) +
30 trials (VDR)
Time
per trial
A few minutes About 3 hours About 8 hours
Evaluation
metric
Mean Error, SD of Error
Integrated Evaluation
(integrated by accuracy,
naturalness, warehouse
dedicated metrics)
Integrated Evaluation
(integrated by accuracy,
naturalness, warehouse
dedicated metrics)
Remark
Collection of data of
participants walking. The
data are available at HASC
(http://hub.hasc.jp/) as
corpus data
Competition over integrated
position using not only PDR,
but also correction information
such as BLE beacon signal,
picking log (WMS), and maps
Consists of PDR and VDR
tracks.Referential motion
captured by MoCap. also
shared for introducing
typical motions.
Comparison of PDR Challenges
National Institute of Advanced Industrial Science and Technology
Prizes
• VDR Track: (a) { VDR module (SSEI, Eq. to 200,000) +
Android IoT device BL-02 (BIGLOBE) + 150,000 cash}
or (b) {200,000 cash +BL-02}
• PDR Track: (a) {TECCO (Eq. to 100,000) + BL-02 +
150,000 cash}
or (b) {200,000 cash + BL-02}
• Runner-Up:BL-02 + 100,000 cash
5
VDR module TECCO BL-02
National Institute of Advanced Industrial Science and Technology
VDR Module (SUC-VDR100)
• Relative vehicle tracking module by VDR
• Manufactured by Sugihara SEI, and its vibration-
based VDR algorithm is licensed by AIST
• Spec
– Battery life:
12 hours
6
National Institute of Advanced Industrial Science and Technology
Tecco (TC-A01)
• Wearable RFID-tag reader for picking operation
• Manufactured by GOV
• Spec
– Interface: Bluetooth
– Battery life: 40 hours
7
National Institute of Advanced Industrial Science and Technology
Android IoT device (BL-02)
• Android IoT device sold by BIGLOBE
• Ideal characteristics for industrial use
– LTE capable
– No camera (for security/confidential point of view)
– 10-axis sensors for PDR
– Android version (6.0) is fixed.
8
National Institute of Advanced Industrial Science and Technology
Rigorous evaluation of error accumulation by BUP
(BLE Unreachable Period)
• Intentionally deleting partial BLE signal logs from the
test data for evaluating PDR accumulated error
Period when BLE signals are deleted: BLE unreachable period (BUP)
• WMS Reference points provided before and after BUP
BUPBUP BUPRSSI
of BLE tag.
Evaluation Points by WMS
⇒ Position data are hided
Correction Points by WMS
⇒ Position data are provided
t
Evaluating positional errors of integrated localization system with BLE beacon
Evaluating accumulated errors caused by only PDR
Emedian_error
Eaccum_error
National Institute of Advanced Industrial Science and Technology
Results of xDR Challenge 2018
10
National Institute of Advanced Industrial Science and Technology
List of Participants
We allow participants to use team name for admission
• # of preadmission: 7
• PDR Track
– No PDR, No future
– HBSM
– KisekioL
– Team:SL_MCL
– Xiamen University
• VDR Track
– HBSM
– Team:SL_MCL
11
National Institute of Advanced Industrial Science and Technology
List of test data used for competition
12
National Institute of Advanced Industrial Science and Technology
Statistics of test data (Added)
• PDR test data:
– Total # of trajectory: 15
– Total time length of sensor data: 176 h. 58min. 54sec.
– Total # of WMS points shared: 271
– Total # of WMS points used for evaluation: 4877
• VDR test data:
– Total # of trajectory: 8
– Total time length of sensor data: 84 h. 15min. 43sec.
– Total # of WMS points shared: 125
– Total # of WMS points used for evaluation: 1027
13
National Institute of Advanced Industrial Science and Technology
Submitted trajectories (3/14 PDR#10)
14
Submitted trajectories (3/14 PDR#13)
National Institute of Advanced Industrial Science and Technology
Example of VDR trajectories
15
Submitted trajectories (3/19 VDR#57)Submitted trajectories (3/15 VDR#57)
National Institute of Advanced Industrial Science and Technology
Final Results (modified)
16
PDR Track:
Winner : HBSM
Runner-Up : No PDR, No Future!
VDR Track:
Winner :HBSM
PDR
E_median_
error
CE50(m)
E_accum_
error
EAG50
(m/sec.)
E_velocity
E_
frequency
E_obstacle E_picking C.E
HBSM 69.46 11.18 98.40 0.0655 99.00 99.87 100.00 98.73 90.18
KisekioL 26.50 26.27 93.63 0.1640 99.00 79.06 99.93 99.00 73.78
Xiamen University 50.42 3637.97 78.04 0.7652 98.40 40.10 86.69 98.27 70.31
No PDR, No future 70.45 10.85 98.53 0.0660 96.93 100.00 97.60 95.80 89.82
VDR
E_median_
error
CE50(m)
E_accum_er
ror
EAG50
(m/sec.)
E_velocity
E_
frequency
E_obstacle E_picking C.E
HBSM 54.65 16.12 98.19 0.0706 99.75 99.25 100.00 97.38 85.62
Note that scores are calculated for individual trajectories and calculating average for
filling this table. CE50 means Circular Error 50%, EAG50 means 50 percentile of EAG.
National Institute of Advanced Industrial Science and Technology
Thank you!
• Contact Info.
– Ryosuke Ichikari, Ph.D.(r.ichikari@aist.go.jp)
17
1 of 17

Recommended

Announcement of Results of xDR Challenge 2018 by
Announcement of Results of xDR Challenge 2018Announcement of Results of xDR Challenge 2018
Announcement of Results of xDR Challenge 2018Ryosuke Ichikari
59 views17 slides
Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge by
Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge
Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge Ryosuke Ichikari
133 views34 slides
Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge by
Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge
Review of PDR Challenge in Warehouse Picking and Advancing to xDR Challenge Ryosuke Ichikari
309 views34 slides
Making Pier Data Broader and Deeper: PDR Challenge and Virtual Mapping Party by
Making Pier Data Broader and Deeper: PDR Challenge and Virtual Mapping PartyMaking Pier Data Broader and Deeper: PDR Challenge and Virtual Mapping Party
Making Pier Data Broader and Deeper: PDR Challenge and Virtual Mapping PartyKurata Takeshi
613 views36 slides
EGNOS benefits for General Aviation by
EGNOS benefits for General AviationEGNOS benefits for General Aviation
EGNOS benefits for General AviationThe European GNSS Agency (GSA)
1.5K views19 slides
EGNOS benefits for aviation by
EGNOS benefits for aviationEGNOS benefits for aviation
EGNOS benefits for aviationThe European GNSS Agency (GSA)
602 views10 slides

More Related Content

What's hot

Energy Oil Gas Presentation by
Energy  Oil  Gas  PresentationEnergy  Oil  Gas  Presentation
Energy Oil Gas Presentationjlai
9.5K views51 slides
CATS Brochure by
CATS BrochureCATS Brochure
CATS BrochureBalfour Beatty Rail
305 views6 slides
Automated Verification of an Onboard Mission Planning and Execution System fo... by
Automated Verification of an Onboard Mission Planning and Execution System fo...Automated Verification of an Onboard Mission Planning and Execution System fo...
Automated Verification of an Onboard Mission Planning and Execution System fo...Florian-Michael Adolf
28 views16 slides
Experiences on AtoN's gained in the NEWADA DUO project by
Experiences on AtoN's gained in the NEWADA DUO projectExperiences on AtoN's gained in the NEWADA DUO project
Experiences on AtoN's gained in the NEWADA DUO projectDamir Obad
254 views30 slides
FACT 2 Case Study Presentation by
FACT 2 Case Study PresentationFACT 2 Case Study Presentation
FACT 2 Case Study PresentationMichael Forte
61 views10 slides
Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3) by
 Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3) Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3)
Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3)system_plus
785 views26 slides

What's hot(12)

Energy Oil Gas Presentation by jlai
Energy  Oil  Gas  PresentationEnergy  Oil  Gas  Presentation
Energy Oil Gas Presentation
jlai9.5K views
Automated Verification of an Onboard Mission Planning and Execution System fo... by Florian-Michael Adolf
Automated Verification of an Onboard Mission Planning and Execution System fo...Automated Verification of an Onboard Mission Planning and Execution System fo...
Automated Verification of an Onboard Mission Planning and Execution System fo...
Experiences on AtoN's gained in the NEWADA DUO project by Damir Obad
Experiences on AtoN's gained in the NEWADA DUO projectExperiences on AtoN's gained in the NEWADA DUO project
Experiences on AtoN's gained in the NEWADA DUO project
Damir Obad254 views
FACT 2 Case Study Presentation by Michael Forte
FACT 2 Case Study PresentationFACT 2 Case Study Presentation
FACT 2 Case Study Presentation
Michael Forte61 views
Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3) by system_plus
 Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3) Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3)
Aptiv’s Third Generation of 77 GHz-Based Short-Range Radar (SRR3)
system_plus785 views
Mediatek Autus R10 (MT2706) 77/79 GHz eWLB/AiP Radar Chipset by system_plus
Mediatek Autus R10 (MT2706) 77/79 GHz eWLB/AiP Radar ChipsetMediatek Autus R10 (MT2706) 77/79 GHz eWLB/AiP Radar Chipset
Mediatek Autus R10 (MT2706) 77/79 GHz eWLB/AiP Radar Chipset
system_plus391 views

Similar to Announcement of Results of xDR Challenge 2018

Industry 4.0 Silabhadra das (1).pptx by
Industry 4.0 Silabhadra das (1).pptxIndustry 4.0 Silabhadra das (1).pptx
Industry 4.0 Silabhadra das (1).pptxssuser0d82cd
10 views69 slides
Automated Driving Test and Issuing Of Driving Licenses by
Automated Driving Test and Issuing Of Driving LicensesAutomated Driving Test and Issuing Of Driving Licenses
Automated Driving Test and Issuing Of Driving LicensesIRJET Journal
37 views4 slides
Towards Realization of 6M Visualization in Manufacturing Sites by
Towards Realization of 6M Visualization in Manufacturing SitesTowards Realization of 6M Visualization in Manufacturing Sites
Towards Realization of 6M Visualization in Manufacturing SitesKurata Takeshi
584 views15 slides
Tod Levitt by
Tod LevittTod Levitt
Tod LevittAFCEA International
1.4K views28 slides
PDR Challenge in Warehouse Picking and Virtual Mapping Party by
PDR Challenge in Warehouse Picking and Virtual Mapping PartyPDR Challenge in Warehouse Picking and Virtual Mapping Party
PDR Challenge in Warehouse Picking and Virtual Mapping PartyKurata Takeshi
918 views34 slides
SCFT-Training_v8.2-1 by
SCFT-Training_v8.2-1SCFT-Training_v8.2-1
SCFT-Training_v8.2-1mahesh savita
8.7K views156 slides

Similar to Announcement of Results of xDR Challenge 2018 (20)

Industry 4.0 Silabhadra das (1).pptx by ssuser0d82cd
Industry 4.0 Silabhadra das (1).pptxIndustry 4.0 Silabhadra das (1).pptx
Industry 4.0 Silabhadra das (1).pptx
ssuser0d82cd10 views
Automated Driving Test and Issuing Of Driving Licenses by IRJET Journal
Automated Driving Test and Issuing Of Driving LicensesAutomated Driving Test and Issuing Of Driving Licenses
Automated Driving Test and Issuing Of Driving Licenses
IRJET Journal37 views
Towards Realization of 6M Visualization in Manufacturing Sites by Kurata Takeshi
Towards Realization of 6M Visualization in Manufacturing SitesTowards Realization of 6M Visualization in Manufacturing Sites
Towards Realization of 6M Visualization in Manufacturing Sites
Kurata Takeshi584 views
PDR Challenge in Warehouse Picking and Virtual Mapping Party by Kurata Takeshi
PDR Challenge in Warehouse Picking and Virtual Mapping PartyPDR Challenge in Warehouse Picking and Virtual Mapping Party
PDR Challenge in Warehouse Picking and Virtual Mapping Party
Kurata Takeshi918 views
Railroad Application of ABI Electronics BoardMaster PCB Test Equipment by Alan Lowne
Railroad Application of ABI Electronics BoardMaster PCB Test EquipmentRailroad Application of ABI Electronics BoardMaster PCB Test Equipment
Railroad Application of ABI Electronics BoardMaster PCB Test Equipment
Alan Lowne1.2K views
Real-time Bangla License Plate Recognition System for Low Resource Video-base... by MD Abdullah Al Nasim
Real-time Bangla License Plate Recognition System for Low Resource Video-base...Real-time Bangla License Plate Recognition System for Low Resource Video-base...
Real-time Bangla License Plate Recognition System for Low Resource Video-base...
Activities of Smart Ship Application Platform 2 Project (SSAP2) by MTI Co., Ltd.
Activities of Smart Ship Application Platform 2 Project (SSAP2)Activities of Smart Ship Application Platform 2 Project (SSAP2)
Activities of Smart Ship Application Platform 2 Project (SSAP2)
MTI Co., Ltd.1.7K views
RDSO Training ppt by Pooja A
RDSO Training pptRDSO Training ppt
RDSO Training ppt
Pooja A3.5K views
Timothy Fenwick - Crankshaft Sensor Tester by Timothy Fenwick
Timothy Fenwick - Crankshaft Sensor TesterTimothy Fenwick - Crankshaft Sensor Tester
Timothy Fenwick - Crankshaft Sensor Tester
Timothy Fenwick178 views
Paul Jackson by JumpingJaq
Paul JacksonPaul Jackson
Paul Jackson
JumpingJaq289 views
RFID Based Asset Management case stories by Leon Smiers
RFID Based Asset Management case storiesRFID Based Asset Management case stories
RFID Based Asset Management case stories
Leon Smiers798 views
Yakaiah_Resume_9Yrs by Yakaiah S
Yakaiah_Resume_9YrsYakaiah_Resume_9Yrs
Yakaiah_Resume_9Yrs
Yakaiah S105 views
Updates on Benchmarking of Vision-based Geometric Registration and Tracking M... by Kurata Takeshi
Updates on Benchmarking of Vision-based Geometric Registration and Tracking M...Updates on Benchmarking of Vision-based Geometric Registration and Tracking M...
Updates on Benchmarking of Vision-based Geometric Registration and Tracking M...
Kurata Takeshi546 views
ERTMS Solutions general company presentation by ERTMS Solutions
ERTMS Solutions general company presentationERTMS Solutions general company presentation
ERTMS Solutions general company presentation
ERTMS Solutions1.3K views
IRJET- Features Extraction OCR Algorithm in Indian License Plates by IRJET Journal
IRJET- Features Extraction OCR Algorithm in Indian License PlatesIRJET- Features Extraction OCR Algorithm in Indian License Plates
IRJET- Features Extraction OCR Algorithm in Indian License Plates
IRJET Journal12 views
IRJET - Driver Monitoring System by IRJET Journal
IRJET - Driver Monitoring SystemIRJET - Driver Monitoring System
IRJET - Driver Monitoring System
IRJET Journal20 views
IRJET- A Case Study on Weaving Capacity Under Heterogeneous Traffic Condition... by IRJET Journal
IRJET- A Case Study on Weaving Capacity Under Heterogeneous Traffic Condition...IRJET- A Case Study on Weaving Capacity Under Heterogeneous Traffic Condition...
IRJET- A Case Study on Weaving Capacity Under Heterogeneous Traffic Condition...
IRJET Journal22 views

Recently uploaded

TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors by
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensorssugiuralab
21 views15 slides
SAP Automation Using Bar Code and FIORI.pdf by
SAP Automation Using Bar Code and FIORI.pdfSAP Automation Using Bar Code and FIORI.pdf
SAP Automation Using Bar Code and FIORI.pdfVirendra Rai, PMP
23 views38 slides
Zero to Automated in Under a Year by
Zero to Automated in Under a YearZero to Automated in Under a Year
Zero to Automated in Under a YearNetwork Automation Forum
15 views23 slides
Microsoft Power Platform.pptx by
Microsoft Power Platform.pptxMicrosoft Power Platform.pptx
Microsoft Power Platform.pptxUni Systems S.M.S.A.
53 views38 slides
Evolving the Network Automation Journey from Python to Platforms by
Evolving the Network Automation Journey from Python to PlatformsEvolving the Network Automation Journey from Python to Platforms
Evolving the Network Automation Journey from Python to PlatformsNetwork Automation Forum
13 views21 slides
Vertical User Stories by
Vertical User StoriesVertical User Stories
Vertical User StoriesMoisés Armani Ramírez
14 views16 slides

Recently uploaded(20)

TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors by sugiuralab
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors
sugiuralab21 views
SAP Automation Using Bar Code and FIORI.pdf by Virendra Rai, PMP
SAP Automation Using Bar Code and FIORI.pdfSAP Automation Using Bar Code and FIORI.pdf
SAP Automation Using Bar Code and FIORI.pdf
Piloting & Scaling Successfully With Microsoft Viva by Richard Harbridge
Piloting & Scaling Successfully With Microsoft VivaPiloting & Scaling Successfully With Microsoft Viva
Piloting & Scaling Successfully With Microsoft Viva
Business Analyst Series 2023 - Week 3 Session 5 by DianaGray10
Business Analyst Series 2023 -  Week 3 Session 5Business Analyst Series 2023 -  Week 3 Session 5
Business Analyst Series 2023 - Week 3 Session 5
DianaGray10300 views
Future of AR - Facebook Presentation by ssuserb54b561
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
ssuserb54b56115 views
Data Integrity for Banking and Financial Services by Precisely
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial Services
Precisely25 views
STPI OctaNE CoE Brochure.pdf by madhurjyapb
STPI OctaNE CoE Brochure.pdfSTPI OctaNE CoE Brochure.pdf
STPI OctaNE CoE Brochure.pdf
madhurjyapb14 views

Announcement of Results of xDR Challenge 2018

  • 1. National Institute of Advanced Industrial Science and Technology Announcement of Results of xDR Challenge 2018 xDR Challenge 2018 Organizers (Ryosuke Ichikari1, Ryo Shimomura12 AIST1, University of Tsukuba2) 1 IPIN 2018@Nantes SS A Survey on Indoor Localization Competitions 10:20 - 12:20 Sept. 26th, 2018
  • 2. National Institute of Advanced Industrial Science and Technology xDR Challenge for Warehouse Operations • xDR Challenge for Warehouse Operations 2018 was held as an sequel competition to "PDR Challenge in Warehouse Picking“ • Host:PDR Benchmark Standardization Committee • Competition of Dead-Reckoning for Pedestrian and Vehicle – xDR=PDR+VDR • Important dates – Testing period: Mid May to Mid Aug., 2018 – Results submission due: 18th Sept, 2018 – Announcement of Winners: Now (This Special Session) • Sponsors: 2
  • 3. National Institute of Advanced Industrial Science and Technology Two competition tracks • Individually determining winners in each tracks • PDR-Track – Tracking workers who move by foot during warehouse operations – Shared data: Smartphone sensor data for PDR, BLE tag’s signal, warehouse’s spec, Partial WMS log. reference movie for typical picking • VDR-Track – Tracking forklift driven by employee during warehouse operations – Smartphone sensor data measured by attaching smartphone onto the forklifts – Shared data: Smartphone sensor data for VDR, BLE tag’s signal, warehouse’s spec, forklift spec., partial WMS log. – Sample data with known path are prepared. (For beginners) 3
  • 4. National Institute of Advanced Industrial Science and Technology 44 Ubicomp/ISWC 2015 PDR Challenge PDR Challenge in Warehouse Picking in IPIN 2017 xDR Challenge for Warehouse Operations 2018 Scenario Indoor pedestrian navigation Picking work inside a logistics warehouse (Specific Industrial Scenario) General warehouse operations including picking, shipping and driving forklift Walking /motion Continuous walking while holding smartphone and looking at navigation screen Includes many motions involved in picking work, not only walking Includes many motions involved in picking, shipping operations and, not only walking. Some workers may drive forklift On-site or off-site Data collection: on-site Evaluation: off-site Off-site Off-site Number of people and trial 90 people, 229 trials 8 people, 8 trials 34 people + 6 forklifts, 170 trials (PDR) + 30 trials (VDR) Time per trial A few minutes About 3 hours About 8 hours Evaluation metric Mean Error, SD of Error Integrated Evaluation (integrated by accuracy, naturalness, warehouse dedicated metrics) Integrated Evaluation (integrated by accuracy, naturalness, warehouse dedicated metrics) Remark Collection of data of participants walking. The data are available at HASC (http://hub.hasc.jp/) as corpus data Competition over integrated position using not only PDR, but also correction information such as BLE beacon signal, picking log (WMS), and maps Consists of PDR and VDR tracks.Referential motion captured by MoCap. also shared for introducing typical motions. Comparison of PDR Challenges
  • 5. National Institute of Advanced Industrial Science and Technology Prizes • VDR Track: (a) { VDR module (SSEI, Eq. to 200,000) + Android IoT device BL-02 (BIGLOBE) + 150,000 cash} or (b) {200,000 cash +BL-02} • PDR Track: (a) {TECCO (Eq. to 100,000) + BL-02 + 150,000 cash} or (b) {200,000 cash + BL-02} • Runner-Up:BL-02 + 100,000 cash 5 VDR module TECCO BL-02
  • 6. National Institute of Advanced Industrial Science and Technology VDR Module (SUC-VDR100) • Relative vehicle tracking module by VDR • Manufactured by Sugihara SEI, and its vibration- based VDR algorithm is licensed by AIST • Spec – Battery life: 12 hours 6
  • 7. National Institute of Advanced Industrial Science and Technology Tecco (TC-A01) • Wearable RFID-tag reader for picking operation • Manufactured by GOV • Spec – Interface: Bluetooth – Battery life: 40 hours 7
  • 8. National Institute of Advanced Industrial Science and Technology Android IoT device (BL-02) • Android IoT device sold by BIGLOBE • Ideal characteristics for industrial use – LTE capable – No camera (for security/confidential point of view) – 10-axis sensors for PDR – Android version (6.0) is fixed. 8
  • 9. National Institute of Advanced Industrial Science and Technology Rigorous evaluation of error accumulation by BUP (BLE Unreachable Period) • Intentionally deleting partial BLE signal logs from the test data for evaluating PDR accumulated error Period when BLE signals are deleted: BLE unreachable period (BUP) • WMS Reference points provided before and after BUP BUPBUP BUPRSSI of BLE tag. Evaluation Points by WMS ⇒ Position data are hided Correction Points by WMS ⇒ Position data are provided t Evaluating positional errors of integrated localization system with BLE beacon Evaluating accumulated errors caused by only PDR Emedian_error Eaccum_error
  • 10. National Institute of Advanced Industrial Science and Technology Results of xDR Challenge 2018 10
  • 11. National Institute of Advanced Industrial Science and Technology List of Participants We allow participants to use team name for admission • # of preadmission: 7 • PDR Track – No PDR, No future – HBSM – KisekioL – Team:SL_MCL – Xiamen University • VDR Track – HBSM – Team:SL_MCL 11
  • 12. National Institute of Advanced Industrial Science and Technology List of test data used for competition 12
  • 13. National Institute of Advanced Industrial Science and Technology Statistics of test data (Added) • PDR test data: – Total # of trajectory: 15 – Total time length of sensor data: 176 h. 58min. 54sec. – Total # of WMS points shared: 271 – Total # of WMS points used for evaluation: 4877 • VDR test data: – Total # of trajectory: 8 – Total time length of sensor data: 84 h. 15min. 43sec. – Total # of WMS points shared: 125 – Total # of WMS points used for evaluation: 1027 13
  • 14. National Institute of Advanced Industrial Science and Technology Submitted trajectories (3/14 PDR#10) 14 Submitted trajectories (3/14 PDR#13)
  • 15. National Institute of Advanced Industrial Science and Technology Example of VDR trajectories 15 Submitted trajectories (3/19 VDR#57)Submitted trajectories (3/15 VDR#57)
  • 16. National Institute of Advanced Industrial Science and Technology Final Results (modified) 16 PDR Track: Winner : HBSM Runner-Up : No PDR, No Future! VDR Track: Winner :HBSM PDR E_median_ error CE50(m) E_accum_ error EAG50 (m/sec.) E_velocity E_ frequency E_obstacle E_picking C.E HBSM 69.46 11.18 98.40 0.0655 99.00 99.87 100.00 98.73 90.18 KisekioL 26.50 26.27 93.63 0.1640 99.00 79.06 99.93 99.00 73.78 Xiamen University 50.42 3637.97 78.04 0.7652 98.40 40.10 86.69 98.27 70.31 No PDR, No future 70.45 10.85 98.53 0.0660 96.93 100.00 97.60 95.80 89.82 VDR E_median_ error CE50(m) E_accum_er ror EAG50 (m/sec.) E_velocity E_ frequency E_obstacle E_picking C.E HBSM 54.65 16.12 98.19 0.0706 99.75 99.25 100.00 97.38 85.62 Note that scores are calculated for individual trajectories and calculating average for filling this table. CE50 means Circular Error 50%, EAG50 means 50 percentile of EAG.
  • 17. National Institute of Advanced Industrial Science and Technology Thank you! • Contact Info. – Ryosuke Ichikari, Ph.D.(r.ichikari@aist.go.jp) 17

Editor's Notes

  1. This presentation contain the presentation about the regular paper and survey of the exiting competitions and the announcement of Winer of our new competition xDR challenge.
  2. This years competition xDR challenge in warehouse operations 2018 was held as an sequent competition to the PDR challenge. In the new competition, we added dead reckoning for forklift as the tracking target. We renamed competitions name xDR challenge: xDR means PDR plus VDR (Vehicle dead-reckoning) Maybe we are going to add other types of dead-rekoning in the future Here are important date for the competition, it was very tight schedule for the competitors. In this presentation we will announce the winner of the competitions. Our sponsors are: BIGLOBE, Sugihara software & electron industry, GOV, sumitomo electric Industries, and PDR benchmark Standardization committee.
  3. As I mentioned, In this year, There are two competition tracks And they individually determine winner in each track. In the PDR, as the same as last year’s competition, The competitors’ PDR algorithm is suppose to track worker who move by foot during warehouse operations This is a off-site competition, We share the smartphone and warehouse data as same as last year In the VDR track, which is a new track this year, The VDR algorithm is supposed to track forklift driven by employee during the operation. The shared data are saved in same format and contends are almost same with PDR track, The smartphone data for VDR are measured by attaching smartphone onto the forklift. For the VDR beginners, we provide sample easy test data with know path. Also we plan to give some points for those who can only estimate partial element such as speed in operation or not.
  4. Finally, we introduced xDR Challenge parts The scenario of the xDR Challenge is warehouse work, It become more general including tracking the forklift. The added the scale of the data measument, We measured the warehouse work for 5 Full-business days. Total 34 people, 6 forklift equals 170 (PDR data ) and 30 VDR data. About 8 hours / data.
  5. Here are Prizes (読まない) We awarded winner and runner-up for each tracks. The winners can cases and extra prize shown in the figure.
  6. One extra prize is VDR module. As you can see, winner can get the devices which can track the forklift.
  7. As we documented in the regulation documents, This year, we adopt rigorous evaluation of error accumulation. Last year, we only evaluation the submitted result which potentially include effort with PDR, BLE-beacon, WMS, and MAP Map matching. It is hard to extract the effect purely from the PDR. This year, we Intentionally delete partial BLE signal logs from the test data for evaluating PDR accumulated error. We call these period the BLE signal are deleted as BLE unreachable period: BUP in short. With BUP, we evaluation absolute median error of integrated localization only outsize of BUP. And we evaluate the PDR accumulating error in BUP
  8. Finally I’m going to announce the result of this years xDR Challenge.
  9. The xDR Challenge is successfully gather the participants from three contrites # number of pre-admission was 7. 5 teams registered final registration for PDR track, And 2 teams registers in VDR track Unfortunately 1 team for registered both tracks withdrew at the last moment.
  10. Here is a list of the sensor data provided for the competitors. Despite, We measured much more data in the measuring we selected the data. The amount data is still big. The competitors submit 16 trajectories for PDR track (130 hours) And 8 (60 hours) trajectories for VDR track. We think this huge amount of data works for avoiding fine-tuning.
  11. OK, here is a final result I guess the what makes a difference between winner and runner-up is that High level balance of error related metric and other metrics. In other words, 1th ranked team and 2nd ranked team almost get similar score for Emedian_error nad E_accumu_error The perfectness of the other mtrics makes the difference. I think this is very good result for evaluating metric designer, because many metrics are contribute The final results.