Object Localization Using RFID Kirti Chawla Department of Computer Science University of Virginia
The Problem of Locating Objects Research Milestones Background Motivation Proposed Approach Experimental Evaluation Conclusion 1/23 Outline
2/23 Locate Environments Goal: Find positions of objects in an environment Hypothesis: Standard RFID is sufficient and effective Key-factors: Performance, applicability and shortcomings Locating ObjectsProblem Objects
Research DeliverablesMilestones Journal Publication: Kirti Chawla, and Gabriel Robins, An RFID-Based Object Localization Framework, International Journal of Radio Frequency Identification Technology and Applications, Inderscience Publishers, 2011, Vol. 3, Nos. 1/2, pp Conference Publications: Kirti Chawla, Gabriel Robins, and Liuyi Zhang, Efficient RFID-Based Mobile Object Localization, Proceedings of IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, 2010, Canada, pp Kirti Chawla, Gabriel Robins, and Liuyi Zhang, Object Localization using RFID, Proceedings of IEEE International Symposium on Wireless Pervasive Computing, 2010, Italy, pp Patent: Kirti Chawla, and Gabriel Robins, Object Localization with RFID Infrastructure, US Patent Application Number: PCT/US2011/053067, filed with WIPO/USPTO September 2011 Copyright: Kirti Chawla, and Gabriel Robins, An RFID-Based Object Localization Framework, US Copyright Case Number: , 2011 Startup Venture: Co-founded Diorama Technologies LLC, in partnership with private investors Raised venture capital funding and negotiated licensing terms Other investors have shown strong interest in commercializing our ideas
WIPO/USPTOPatent Object Localization with RFID Infrastructure
3/23 Technologies Mismatched Solutions Limiting Constraints Techniques Current State of the ArtBackground
4/23 RFID Reader RFID Tag Near-field Propagation Far-field Propagation Readers: Variety of form-factors and frequencies Tags: Flexible power source, frequency, and form factors RFID PrimerBackground
5/23 Motivation Dark Environment No Line of Sight Why locate objects using RFID ? Cost Effective Solid Obstacles Natural Fit Adaptive
6/23 Power-Distance RelationshipApproach Distance Reader Power Tag Power Problem: Radio variability renders Friis equation practically useless Insight: Utilize empirical power-distance relationship Comparison
7/23 Antenna Insight: Similarly behaving tags are close to each other Radio Wave Shared Region Empirical Power-Distance Relationship Approach
8/23 Tag Sensitivity CharacterizationApproach 13% 25%54%8% High SensitiveAverage SensitiveLow Sensitive Pile of Tags Problem: Tags have variable sensitivities / performance Insight: Bin tags based on their sensitivity Results Key Challenges
RFID Tag VerticalHorizontal RFID Reader 9/23 Reliability through Multi-TagsApproach Problem: Optimal tag reads occur at certain orientations Insight: Multi-tags provide orientation redundancy Results Platform Side View ParallelOrthogonal RFID Tag Platform Top View
Setup Phase 10/23 Tag Localization ApproachApproach Localization Phase Signal Strength Metric: MTDP
11/23 Tag Localization AlgorithmsApproach Linear SearchBinary SearchParallel Search O(#Tags Log#Power-Levels) O(#Tags #Power-Levels) O(#Power-Levels) Reader Output Power Range 0MAXMID
12/23 Reader Localization ApproachApproach Setup Phase Localization Phase
13/23 Localization ErrorApproach Problem: Assumption that target and reference tag locations coincide leads to localization error Insight: Consider other nearby reference tags in order to minimize the localization error Heuristics Reference Tags Target Tag
14/23 Experimental SetupEvaluation Robot Design Track Design
15/23 Empirical Power-Distance Relationship Evaluation Insight: Only empirical power-distance relationship can provide high localization performance Theoretical (N = 2) Theoretical (N = 3) Theoretical (N = 6)Empirical Back
16/23 Localization AccuracyEvaluation Insight: Performance can be improved by denser reference tag deployment Actual Position Inferred Position
17/23 Localization TimeEvaluation Insight: Faster algorithms provide lower tag detectability Linear Search (HL) Parallel Search Linear Search (LH) Binary Search
18/23 Localization Performance Vs #Tags Evaluation Insight: Localization performance varies with tag density Diminishing returns
Approach Average Time (minutes) Test Area (m 2 ) Localization Error (m) Notes Setup Phase Localization Phase Ni et al., Pure RFID Alippi et al., Bekkali et al., – 1.0 Senta et al., Wang et al., – 0.9 Zhang et al., Hybrid Seo and Lee, – 1.6Pure RFID Choi and Lee, Hybrid Choi et al., Pure RFID Joho et al., Linear Search (LH) Linear Search (HL) Binary Search Parallel Search Measure and Report Combined Approach Pure RFID 19/23 Comparative EvaluationEvaluation Preliminary new experiments show: 1) Reference tags optional 2) Instantaneous localization 3) High accuracy
20/23 Applications Warehouses Hospitals Supply Chains Monitor life-critical events Smart Carts Provide ground truth Tier-II Applications Assisted Living Location-Aware Services Energy Saving in Buildings Locating Objects Tier-I Applications
21/23 Object Location VisualizationInterface
22/23 Future DirectionsConclusion RFID-only Object Localization Framework: - Showed that pure RFID can be used for object localization - Introduced a power-distance relationship metric - Proposed tag binning to mitigate tag sensitivity variability - Devised effective localization algorithms and heuristics - Identified / mitigated key localization challenges Future Research Directions: - Scalability - Technology Evolution - Localization performance - Visualization tools - Field testing and Commercialization
Research DeliverablesMilestones Journal Publication: Kirti Chawla, and Gabriel Robins, An RFID-Based Object Localization Framework, International Journal of Radio Frequency Identification Technology and Applications, Inderscience Publishers, 2011, Vol. 3, Nos. 1/2, pp Conference Publications: Kirti Chawla, Gabriel Robins, and Liuyi Zhang, Efficient RFID-Based Mobile Object Localization, Proceedings of IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, 2010, Canada, pp Kirti Chawla, Gabriel Robins, and Liuyi Zhang, Object Localization using RFID, Proceedings of IEEE International Symposium on Wireless Pervasive Computing, 2010, Italy, pp Patent: Kirti Chawla, and Gabriel Robins, Object Localization with RFID Infrastructure, US Patent Application Number: PCT/US2011/053067, filed with WIPO/USPTO September Copyright: Kirti Chawla, and Gabriel Robins, An RFID-Based Object Localization Framework, US Copyright Case Number: , Startup Venture: Co-founded Diorama Technologies LLC, in partnership with private investors Raised venture capital funding and negotiated licensing terms Other investors have shown strong interest in commercializing our ideas 23/23
WIPO/USPTOPatent Object Localization with RFID Infrastructure
Backup Slides
Localization Solutions Localization Type Localization Technique Signal StrengthSignal Phase Arrival Time Environmental Self Organizing Localization SpaceBackground
Localization ChallengesApproach Radio Interference OcclusionsTag SensitivityTag SpatialityTag Orientation Reader Locality Back
Tag Sensitivity – Single TagEvaluation Constant Distance/Variable Power Variable Distance/Constant Power Back
Tag Sensitivity – Multi-Tag (Proximity) Evaluation Constant Distance/Variable Power Variable Distance/Constant Power Back
Tag Sensitivity – Multi-Tag (Rotation-1) Evaluation Constant Distance/Variable Power Back
Tag Sensitivity – Multi-Tag (Rotation-2) Evaluation Variable Distance/Constant Power Back
Error-Reducing HeuristicsApproach Root Sum Square Minimum Power Selection Absolute Difference Localization Error Meta Heuristic Problem: There can be multiple nearby reference tags Insight: Select nearby reference tags using different schemes Back