Urban localization using robust filtering at multiple linearization points

EURASIP Journal on Advances in Signal Processing

Research

Adyasha Mohanty¹  Grace Gao¹  Shubh Gupta² 

[1]Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA

[2]Department of Electrical Engineering, Stanford University, Stanford, CA, USA

关键词: GNSS;    Camera;    Multi-sensor;    Multi-modal uncertainty;    Bayesian filtering;    Robust estimation;    Particle filter;    Kalman filter;    Rao–Blackwellization;    Safety-critical localization;   

DOI  :  10.1186/s13634-023-01062-7

 received in 2023-05-16, accepted in 2023-09-25,  发布年份 2023

来源: Springer

【 摘 要 】

We propose a robust Bayesian filtering framework for state and multi-modal uncertainty estimation in urban settings by fusing diverse sensor measurements. Our framework addresses multi-modal uncertainty from various error sources by tracking a separate probability distribution for linearization points corresponding to dynamics, measurements, and cost functions. Multiple parallel robust Extended Kalman filters (R-EKF) leverage these linearization points to characterize the state probability distribution. Employing Rao–Blackwellization, we combine the linearization point distribution with the state distribution, resulting in a unified, efficient, and outlier-resistant Bayesian filter that captures multi-modal uncertainty. Furthermore, we introduce a gradient descent-based optimization method to refine the filter parameters using available data. Evaluating our filter on real-world data from a multi-sensor setup comprising camera, Global Navigation Satellite System (GNSS), and Attitude and Heading Reference System (AHRS) demonstrates improved performance in bounding position errors based on uncertainty, while maintaining competitive accuracy and comparable computation to existing methods. Our results suggest that our framework is a promising direction for safe and reliable localization in urban environments.

【 授权许可】

CC BY   
© Springer Nature Switzerland AG 2023

【 图 表 】

Fig. 14

Fig. 11

12936_2017_1882_Article_IEq9.gif

Fig. 7

Fig. 3

12951_2017_283_Article_IEq3.gif

Fig. 13

Fig. 4

Fig. 3

Fig. 2

Fig. 7

12951_2017_255_Article_IEq54.gif

Fig. 5

12951_2017_255_Article_IEq53.gif

Fig. 2

Fig. 4

Fig. 2

Fig. 1

Fig. 1

Fig. 4

Fig. 10

Fig. 1

Fig. 1

Fig. 2

Scheme 1

12951_2016_223_Article_IEq1.gif

12951_2016_246_Article_IEq8.gif

Fig. 5

Fig. 6

Fig. 1

Fig. 1

12951_2017_255_Article_IEq48.gif

Fig. 3

Fig. 5

Fig. 1

Fig. 2

Fig. 10

Fig. 1

Fig. 4

Fig. 2

Fig. 8

12951_2016_246_Article_IEq7.gif

Fig. 1

12951_2016_246_Article_IEq6.gif

Fig. 8

40538_2023_473_Article_IEq1.gif

12951_2015_155_Article_IEq78.gif

Fig. 7

Fig. 3

Fig. 8

Fig. 2

12936_2015_836_Article_IEq25.gif

Fig. 4

12951_2016_246_Article_IEq5.gif

Fig. 2

Fig. 1: The conceptual framework for adherence to treatment guidelines in private drug outlets in Kisumu, Kenya

Fig. 4

12951_2015_155_Article_IEq77.gif

12951_2015_155_Article_IEq76.gif

Fig. 2

Scheme. 1

Fig. 1

Fig. 6

12951_2017_303_Article_IEq1.gif

12951_2016_246_Article_IEq3.gif

Fig. 6

Fig. 7

Fig. 3

12951_2015_155_Article_IEq75.gif

Fig. 2

12951_2015_155_Article_IEq74.gif

Fig. 2

Fig. 8

Fig. 5

Fig. 5

Fig. 1

Fig. 2

Fig. 4

Fig. 1

Fig. 2

12951_2016_246_Article_IEq1.gif

Fig. 1

Fig. 6

Fig. 7

12951_2015_155_Article_IEq73.gif

Fig. 6

12951_2015_155_Article_IEq72.gif

Fig. 3

Fig. 3

Fig. 1

Fig. 2

Fig. 2

Fig. 1

Fig. 2

Fig. 2

Fig. 4

Fig. 1

Fig. 3

Fig. 3

12947_2017_100_Article_IEq1.gif

Fig. 1

Fig. 1

Fig. 3

12951_2015_155_Article_IEq70.gif

Fig. 10

Fig. 2

Fig. 7

Fig. 5

Fig. 1

Fig. 19

12951_2017_255_Article_IEq45.gif

Fig. 3

Fig. 6

Fig. 4

12951_2015_155_Article_IEq69.gif

Fig. 18

12888_2023_5206_Article_IEq3.gif

Fig. 17

12888_2023_5206_Article_IEq1.gif

Fig. 16

Fig. 1

Fig. 15

Fig. 3

Fig. 14

Fig. 5

Fig. 2

Fig. 13

Fig. 1

Fig. 1

Fig. 1

Fig. 12

Fig. 6

Fig. 3

Fig. 11

Fig. 2

Fig. 9

Fig. 1

12936_2017_1963_Article_IEq41.gif

Fig. 8

Fig. 8

Fig. 6

12951_2016_177_Article_IEq1.gif

12951_2015_155_Article_IEq65.gif

Fig. 4

Fig. 5

Fig. 3

Fig. 1

12936_2015_836_Article_IEq14.gif

12951_2017_255_Article_IEq41.gif

12936_2015_836_Article_IEq13.gif

Fig. 2

12936_2017_2014_Article_IEq29.gif

Fig. 2

Fig. 4

12936_2017_2045_Article_IEq18.gif

Fig. 2

Fig. 2

Fig. 1

Fig. 1

Fig. 3

Fig. 2

Fig. 2

12936_2016_1182_Article_IEq39.gif

12951_2017_255_Article_IEq40.gif

Fig. 1

Fig. 4

Fig. 2

Fig. 6

Fig. 2

Fig. 1

Fig. 1

Fig. 4

Fig. 5

Fig. 6

Fig. 2

12960_2017_220_Article_IEq2.gif

Fig. 3

Fig. 1

Fig. 2

12951_2015_155_Article_IEq58.gif

12936_2017_2075_Article_IEq66.gif

12936_2017_2045_Article_IEq5.gif

Fig. 2

Fig. 1

Fig. 3

12936_2017_1963_Article_IEq60.gif

Fig. 2