US 11,987,251 B2
Adaptive rationalizer for vehicle perception systems toward robust automated driving control
Mohammadali Shahriari, Markham (CA); Reza Zarringhalam, Whitby (CA); Haley Marie Dalzell, Ann Arbor, MI (US); Khizar Ahmad Qureshi, Pickering, MI (US); and Patrick Francis Pirrmann, Detroit, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Nov. 15, 2021, as Appl. No. 17/526,662.
Prior Publication US 2023/0150514 A1, May 18, 2023
Int. Cl. B60W 40/10 (2012.01); G01C 21/34 (2006.01)
CPC B60W 40/10 (2013.01) [G01C 21/3461 (2013.01); B60W 2552/15 (2020.02); B60W 2552/30 (2020.02); B60W 2552/53 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system in a vehicle traveling on a roadway, the system comprising a computing device including a processor and a memory, the memory including instructions such that the processor is configured to:
transform vehicle dynamics data, received from one or more sensors mounted on the vehicle, to corresponding roadway geometry data;
calculate a rationalization value based on a difference between the roadway geometry data and map-based roadway geometry data, wherein the rationalization value is calculated according to:
eρ=ρmap−ρV,
eθ=θmap−θV,
eØ=Ømap−ØV,
where eρ comprises a curvature estimation error, eθ comprises a bank angle estimation error, eØ represents a grade angle estimation error, ρmap comprises a map-based curvature estimation, θmap comprises a map-based bank angle estimation, Ømap comprises a map-based grade angle estimation, ρV comprises a vehicle curvature estimation, θV comprises a vehicle bank angle estimation, and ØV comprises a vehicle grade angle estimation;
determine whether to modify a vehicle state based on the rationalization value; and
command a change in the vehicle state from an autonomous state to at least one of a semi-autonomous state or a non-autonomous state based on the rationalization value.