US 12,442,638 B2
Vision-aided inertial navigation system for ground vehicle localization
Stergios I. Roumeliotis, St. Paul, MN (US); Kejian J. Wu, Minneapolis, MN (US); and Chao Guo, Minneapolis, MN (US)
Assigned to Regents of the University of Minnesota, Minneapolis, MN (US)
Filed by Regents of the University of Minnesota, Minneapolis, MN (US)
Filed on Feb. 15, 2024, as Appl. No. 18/443,035.
Application 18/443,035 is a continuation of application No. 16/425,422, filed on May 29, 2019, granted, now 11,940,277.
Claims priority of provisional application 62/677,438, filed on May 29, 2018.
Prior Publication US 2024/0230335 A1, Jul. 11, 2024
Int. Cl. G01C 21/00 (2006.01); G01C 21/16 (2006.01); G01C 21/28 (2006.01); G06T 7/246 (2017.01); G06T 7/277 (2017.01); G06T 7/73 (2017.01); G07C 5/08 (2006.01)
CPC G01C 21/1656 (2020.08) [G01C 21/28 (2013.01); G06T 7/246 (2017.01); G06T 7/277 (2017.01); G06T 7/73 (2017.01); G07C 5/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A vision-aided inertial navigation system (VINS) comprising:
at least one image source configured to produce image data along a trajectory of the VINS within an environment, wherein the image data contains a plurality of features observed for a plurality of poses of the VINS along the trajectory;
an inertial measurement unit (IMU) configured to produce IMU data indicative of motion of the VINS; and
a processor communicatively coupled to the at least one image source and the IMU, wherein the processor is configured to derive state estimates by:
maintaining a state vector for a sliding window of two or more most recent poses of the VINS;
generating:
a set of one or more motion estimate geometric constraints between poses within the sliding window based on a first set of features of the plurality of features, and
the state estimates within the state vector for the sliding window based on the set of one or more motion estimate geometric constraints;
computing a motion manifold for the environment based on the state estimates;
using the motion manifold to generate a set of one or more motion manifold geometric constraints, wherein the set of one or more motion manifold geometric constraints are used to constrain the motion of the VINS within a particular range of deviation from planar motion; and
updating the state estimates according to the set of one or more motion estimate geometric constraints and the set of one or more motion manifold geometric constraints.