# US 12,179,794 B2 · Systems and methods for implementing an autonomous vehicle response to sensor failure > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,179,794 B2 - Document ID: US12179794B2 - Status: Granted - Kind: B2 - Application number: 18/092,960 - Filed: 2023-01-04 - Published: 2023-05-11 - Granted: 2024-12-31 - Earliest claimed: 2019-04-29 - Assignees: Motional AD LLC - Applicants: Motional AD LLC - Inventors: Zachary Thomas Batts; Ludong Sun; Ky Woodard; Qian Wang; Yiming Zhao; Stephanie Lee; Lin Zhao - Web page: https://patentgrep.com/patent/US12179794B2 ## CPC - B60W 60/001: {Planning or execution of driving tasks} - B60W 60/00186: {related to the vehicle} - B60Q 1/46: for giving flashing caution signals during drive, other than signalling change of direction, e.g. flashing the headlights {or hazard lights} - B60Q 5/005: {automatically actuated} - B60W 50/0205: {Diagnosing or detecting failures; Failure detection models} - B60W 50/023: Avoiding failures by using redundant parts - B60W 50/029: Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts - G05D 1/0214: {in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13)} - G05D 1/617: Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards (arrangements for controlling the position or course of two or more vehicles for avoiding collisions therebetween G05D1/693; arrangements for reacting to or preventing system or operator failure G05D1/80) - B60W 2050/0215: {Sensor drifts or sensor failures} - B60W 2050/0292: {Fail-safe or redundant systems, e.g. limp-home or backup systems} - B60W 2552/00: Input parameters relating to infrastructure - B60W 2556/20: Data confidence level - B60W 2756/10: Involving external transmission of data to or from the vehicle - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - B60Q: ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES ## Abstract Among other things, we describe techniques for implementing a vehicle response to sensor failure. In general, one innovative aspect of the subject matter described in this specification can be embodied in methods that include receiving information from a plurality of sensors coupled to a vehicle, determining that a level of confidence of the received information from at least one sensor of a first subset of sensors of the plurality of sensors is less than a first threshold, comparing a number of sensors in the first subset of sensors to a second threshold, and adjusting the driving capability of the vehicle to rely on information received from a second subset of sensors of the plurality of sensors, wherein the second subset of sensors excludes the at least one sensor of the first subset of sensors. ## Claims ### Claim 1 A method comprising: receiving information from a set of two or more sensors of an autonomous vehicle (AV); determining that a level of confidence of the received information from at least one sensor of a first subset of the set of two or more sensors is less than a first threshold; in response to determining that the level of confidence of the received information from the at least one sensor of the first subset of sensors is less than the first threshold, determining whether to adjust a driving function of the AV based on a number of sensors in the first subset of sensors or a number of sensors in a second subset of sensors that excludes the first subset of sensors; in accordance with the determination to adjust the driving function, causing the driving function to be adjusted by accessing last known data for controlling the driving function of the AV, wherein the last known data includes information received from a particular sensor before the received information of the particular sensor indicated that the level of confidence was less than the first threshold; and using the last known data, navigating the AV to a safe location. ### Claim 2 (depends on 1) The method of claim 1, wherein the level of confidence of the received information for each sensor of the first subset of sensors exceeds the first threshold. ### Claim 3 (depends on 1) The method of claim 1, wherein each sensor is allocated a weight indicative of a corresponding importance of each respective sensor, and wherein determining whether to adjust the driving function of the AV based on the number of sensors in the first subset of sensors or the number of sensors in a second subset of sensors that excludes the first subset of sensors comprises: weighting each sensor in the first subset of sensors according to a respective weight; and comparing a weighted number of the sensors in the first subset of the set of two or more sensors to a second threshold. ### Claim 4 (depends on 1) The method of claim 1, wherein causing the driving function to be adjusted comprises: adjusting the driving function of the AV to execute emergency maneuvers to navigate the AV to the safe location. ### Claim 5 (depends on 4) The method of claim 4, wherein adjusting the driving function of the AV to execute emergency maneuvers comprises one or more of activating one or more lights or moving away from a traveled route by dead reckoning. ### Claim 6 (depends on 4) The method of claim 4, wherein adjusting the driving function of the AV to execute emergency maneuvers comprises: querying one or more other vehicles for driving information; in response to the querying, receiving, from at least one of the one or more other vehicles, information on or more of road conditions or navigation instructions; and using the received information on or more of road conditions or navigation instructions, navigating the AV to the safe location. ### Claim 7 (depends on 1) The method of claim 1, wherein the safe location is one of a road shoulder, an emergency lane, a service station, or a home base for the AV. ### Claim 8 (depends on 1) The method of claim 1, further comprising: upon determining that the level of confidence of the received information from at least one sensor of the first subset of the set of two or more sensors is less than the first threshold, activating one or more backup sensors; and configuring the one or more backup sensors to perform operations previously performed by the first subset of sensors. ### Claim 9 (depends on 8) The method of claim 8, wherein the one or more backup sensors are different from sensors included in the set of two or more of sensors. ### Claim 10 (depends on 8) The method of claim 8, wherein one or more the backup sensors include at least one sensor of the set of two or more sensors. ### Claim 11 (depends on 1) The method of claim 1, further comprising: upon determining that the number of sensors in the first subset of the set of two or more sensors is greater than or equal to a second threshold, providing a warning to other vehicles indicative of an emergency corresponding to the AV. ### Claim 12 (depends on 11) The method of claim 11, wherein the warning includes one or more of activating a light emitting device of the AV, or activating a sound emitting device of the AV. ### Claim 13 (depends on 11) The method of claim 11, wherein the warning includes sending a wireless signal to at least one of emergency services and a command center for teleoperation. ### Claim 14 (depends on 1) The method of claim 1, wherein determining that the level of confidence of the received information from at least one sensor of the first subset of the set of two or more sensors is less than the first threshold comprises: comparing measurements received from sensors in the first subset of the set of two or more sensors to a measurement threshold; and determining whether the measurements received from the sensors in the first subset of the set of two or more sensors are less than or equal to the measurement threshold. ### Claim 15 (depends on 14) The method of claim 14, wherein comparing measurements received from sensors in the first subset of the set of two or more sensors to the measurement threshold comprises: for each respective sensor in the first subset of the set of two or more sensors that the level of confidence of the received information is less than the first threshold, determining a sensor type and a coverage area of the respective sensor; identifying a third subset of other sensors of at least one of the same sensor type of the respective sensor or of the same coverage area, wherein each identified sensor in the third subset of other sensors does not have a level of confidence of the received information less than the first threshold; acquiring measurements received from the third subset of other sensors; and determining whether measurements received from each sensor in the third subset of other sensors compared to measurements received from the respective sensor in the first subset of sensors are greater than or equal to a sensor agreement threshold. ### Claim 16 (depends on 15) The method of claim 15, further comprising: upon determining that measurements received from each sensor in the third subset of other sensors compared to measurements received from each respective sensor in the first subset of the set of two or more sensors are greater than or equal to the sensor agreement threshold, determining that the measurements received from the respective sensor in the first subset of sensors are less than or equal to the measurement threshold. ### Claim 17 (depends on 1) The method of claim 1, wherein determining that a level of confidence of the received information from at least one sensor of a first subset of the set of two or more sensors is less than a first threshold comprises: comparing measurements received from sensors in the first subset of the set of two or more sensors to a range of values corresponding to a statistical confidence interval; and determining that the measurements received from the sensors in the first subset of the set of two or more sensors are outside the range of values corresponding to the statistical confidence interval. ### Claim 18 A vehicle comprising: a set of two or more sensors; one or more processors; memory storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising: receiving information from the set of two or more sensors; determining, based on the received information, that a level of confidence of the received information from at least one sensor of a first subset of the set of two or more sensors is less than a first threshold; in response to determining that the level of confidence of the received information from the at least one sensor of the first subset of sensors is less than the first threshold, determining whether to adjust a driving function of the vehicle based on a number of sensors in the first subset of sensors or a number of sensors in a second subset of sensors that excludes the first subset of sensors; and in accordance with the determination to adjust the driving function, causing the driving function to be adjusted by accessing last known data for controlling the driving function of the vehicle, wherein the last known data includes information received from a particular sensor before the received information of the particular sensor indicated that the level of confidence was less than the first threshold; and using the last known data, navigating the vehicle to a safe location.