US 11,747,822 B2
Mobile robot system and method for autonomous localization using straight lines extracted from visual images
Ahti Heinla, Tallinn (EE); Kalle-Rasmus Volkov, Tallinn (EE); Lindsay Roberts, Tallinn (EE); and Indrek Mandre, Tallinn (EE)
Assigned to STARSHIP TECHNOLOGIES OÜ, Tallinn (EE)
Filed by STARSHIP TECHNOLOGIES OÜ, Tallinn (EE)
Filed on Jun. 10, 2021, as Appl. No. 17/344,048.
Application 17/344,048 is a continuation of application No. 16/525,730, filed on Jul. 30, 2019, granted, now 11,042,165.
Application 16/525,730 is a continuation of application No. 15/968,838, filed on May 2, 2018, granted, now 10,386,850, issued on Aug. 20, 2019.
Application 15/968,838 is a continuation of application No. PCT/EP2016/076467, filed on Nov. 2, 2016.
Claims priority of application No. 15192649 (EP), filed on Nov. 2, 2015.
Prior Publication US 2021/0302990 A1, Sep. 30, 2021
Int. Cl. G05D 15/00 (2006.01); G05D 1/02 (2020.01); G06T 7/579 (2017.01); G01C 21/00 (2006.01); G06T 7/73 (2017.01); G06T 7/00 (2017.01); G05D 1/00 (2006.01); G06Q 10/0833 (2023.01)
CPC G05D 1/0246 (2013.01) [G01C 21/3848 (2020.08); G05D 1/0088 (2013.01); G05D 1/0212 (2013.01); G05D 1/0223 (2013.01); G05D 1/0251 (2013.01); G05D 1/0274 (2013.01); G06Q 10/0833 (2013.01); G06T 7/579 (2017.01); G06T 7/73 (2017.01); G06T 7/97 (2017.01); G05D 1/024 (2013.01); G05D 1/027 (2013.01); G05D 1/0255 (2013.01); G05D 1/0272 (2013.01); G05D 1/0278 (2013.01); G05D 2201/0213 (2013.01); G05D 2201/0216 (2013.01); G06T 2207/10004 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20212 (2013.01); G06T 2207/30244 (2013.01); G06T 2207/30252 (2013.01)] 37 Claims
OG exemplary drawing
 
1. A vehicle comprising:
at least one memory component comprising existing map data, the existing map data comprising information reflective of straight lines belonging to buildings and/or fences and/or sidewalks and extracted from past visual images which were previously taken in the vehicle's current operating area;
at least two cameras mounted on the vehicle and adapted to take new visual images, said at least two cameras pointing in different directions and having non-overlapping fields of view; and
at least one processing component adapted to:
extract new straight lines from the new visual images taken by the at least two cameras; and
compare the extracted new straight lines to the existing map data and create localization data to localize the vehicle;
wherein:
the processing component is further adapted to localize the vehicle by executing an iterative algorithm estimating the vehicle's pose, said pose comprising a combination of position and orientation of the vehicle;
the existing map data corresponds to different pose possibilities of the vehicle; and
the iterative algorithm evaluates the likelihood of each of the different pose possibilities being the true one.