US 12,330,678 B2
Probabilisic system and method for autonomous vehicle control
Hassan Askari, Thornhill (CA); Seyedalireza Kasaiezadeh Mahabadi, Novi, MI (US); Reza Zarringhalam, Whitby (CA); Mohammadali Shahriari, Markham (CA); and Khizar Ahmad Qureshi, Pickering (CA)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Mar. 3, 2023, as Appl. No. 18/177,913.
Prior Publication US 2024/0294184 A1, Sep. 5, 2024
Int. Cl. B60W 60/00 (2020.01); B60W 30/00 (2006.01); B60W 50/02 (2012.01); B60W 50/029 (2012.01); B62D 5/04 (2006.01)
CPC B60W 60/001 (2020.02) [B60W 50/0205 (2013.01); B60W 30/00 (2013.01); B60W 2050/0215 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for autonomous driving control, comprising:
receiving a plurality of unfiltered sensor signals from a plurality of sensor systems in a vehicle, wherein each of the plurality of sensor systems includes at least one sensor;
determining, in real time, a failure probability of each of the plurality of sensor systems using the unfiltered sensor signals;
generating a plurality of estimation signals from the unfiltered sensor signals by filtering, adjusting, and arbitrating the unfiltered sensor signals, wherein the estimation signals include data indicative of a state of the vehicle and an environment surrounding the vehicle;
determining a failure probability of the plurality of estimation signals at each time step based on the failure probability of each of the plurality of sensor systems;
communicating the plurality of estimation signals and the failure probability of the plurality of estimation signals to an Advanced Driver Assistance System (ADAS) in the vehicle;
generating, by the ADAS, a plurality of ADAS subfunction commands based on the estimation signals;
determining, using a Bayesian network, a failure probability of the plurality of ADAS subfunction commands based on the failure probability of the plurality of estimation signals at each time step;
determining remedial actions for the plurality of ADAS subfunction commands based on the failure probability of the plurality of ADAS subfunction commands;
comparing the failure probability of the ADAS subfunction commands with a predetermined threshold to determine whether the failure probability of the ADAS subfunction commands is equal to or less than the predetermined threshold;
in response to determining that the failure probability of the ADAS subfunction commands is equal to or less than the predetermined threshold, autonomously controlling the vehicle using the ADAS subfunction commands; and
in response to determining that the failure probability of the ADAS subfunction commands are greater than the predetermined threshold, performing the remedial action.