Abstract: Determining positioning of a sensor system associated with a vehicle involves: (i) identifying a given time when the vehicle was driving in a lane having substantially-straight lane geometry, (ii) inferring that, because the lane had substantially-straight lane geometry at the given time, the vehicle was laterally positioned in alignment with a lateral centerline of the lane at the given time, (iii) detecting a lane boundary of the lane in which the vehicle was driving at the given time, (iv) determining, at the given time, a first lateral distance between the lane boundary and the vehicle's associated sensor system and a second lateral distance between the lane boundary and the lateral centerline of the lane, and (v) based on the first and second lateral distances, determining a given measure of a lateral offset between the vehicle's associated sensor system and the lateral center of the vehicle for the given time.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) identify, within a given period of operation of a vehicle having an associated sensor system for capturing sensor data, one or more times when the vehicle was driving in a lane having substantially-straight lane geometry, (ii) for each identified time, determine a respective measure of a lateral offset between the vehicle's associated sensor system and a lateral reference point of the vehicle, and (iii) based on the respective measure of the lateral offset that is determined for each of the one or more identified times, determine the lateral offset between the vehicle's associated sensor system and the lateral reference point of the vehicle.

Abstract: Systems and methods for assessing the performance of an automated autonomous driving evaluator are disclosed herein.

Abstract: In one embodiment, a method includes, by a computing system associated with a vehicle, determining a current location of the vehicle in a first region, identifying one or more first sets of model parameters associated with the first region and one or more second sets of model parameters associated with a second region, generating, using one or more machine-learning models based on the first sets of model parameters, one or more first inferences based on first sensor data captured by the vehicle, switching the configurations of the models from the first sets of model parameters to the second sets of model parameters, generating, using the models having configurations based on the second sets of model parameters, one or more second inferences based on second sensor data generated by the sensors of the vehicle in the second region, and causing the vehicle to perform one or more operations based on the second inferences.

Abstract: Systems and methods for assessing the performance of an automated autonomous driving evaluator are disclosed herein.

Abstract: In particular embodiments, a computing system may determine a measured driving characteristic of a driving control system based on observations of vehicles driven by the driving control system. The system may determine a difference between the measured driving characteristic and a target driving characteristic, which is based on objectivations of one or more manually controlled vehicles. The system may determine an evaluation objective for the driving control system. The system may determine a weight function for the evaluation objective. The system may determine a score for the driving control system with respect to the evaluation objective by weighting the difference between the measured driving characteristic and the target driving characteristic using the weight function. The system may apply, based on the score, an adjustment to the driving control system to reduce a difference between a subsequently measured driving characteristic of the driving control system and the target driving characteristic.

Abstract: Systems, methods, and non-transitory computer-readable media can determine a raster representative of a surrounding environment of a vehicle, wherein the raster depicts one or more objects in the surrounding environment of the vehicle. A plurality of trajectory proposals are determined for a first object of the one or more objects. For each trajectory proposal of the plurality of trajectory proposals, a score indicative of a likelihood that the first object will take a trajectory consistent with the trajectory proposal, and an offset for modifying the trajectory proposal are generated. A predicted trajectory is determined for the first object based on the scores and the offsets for the plurality of trajectory proposals.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) identify, within a given period of operation of a vehicle having an associated sensor system for capturing sensor data, one or more times when the vehicle was driving in a lane having substantially-straight lane geometry, (ii) for each identified time, determine a respective measure of a lateral offset between the vehicle's associated sensor system and a lateral reference point of the vehicle, and (iii) based on the respective measure of the lateral offset that is determined for each of the one or more identified times, determine the lateral offset between the vehicle's associated sensor system and the lateral reference point of the vehicle.

Abstract: In one embodiment, a method includes, by a computing system associated with a vehicle, determining a current location of the vehicle in a first region, identifying one or more first sets of model parameters associated with the first region and one or more second sets of model parameters associated with a second region, generating, using one or more machine-learning models based on the first sets of model parameters, one or more first inferences based on first sensor data captured by the vehicle, switching the configurations of the models from the first sets of model parameters to the second sets of model parameters, generating, using the models having configurations based on the second sets of model parameters, one or more second inferences based on second sensor data generated by the sensors of the vehicle in the second region, and causing the vehicle to perform one or more operations based on the second inferences.

Abstract: In particular embodiments, a computing system may determine a measured driving characteristic of a driving control system based on observations of vehicles driven by the driving control system. The system may determine a difference between the measured driving characteristic and a target driving characteristic, which is based on objectivations of one or more manually controlled vehicles. The system may determine an evaluation objective for the driving control system. The system may determine a weight function for the evaluation objective. The system may determine a score for the driving control system with respect to the evaluation objective by weighting the difference between the measured driving characteristic and the target driving characteristic using the weight function. The system may apply, based on the score, an adjustment to the driving control system to reduce a difference between a subsequently measured driving characteristic of the driving control system and the target driving characteristic.

Abstract: Systems, methods, and non-transitory computer-readable media can determine a raster representative of a surrounding environment of a vehicle, wherein the raster depicts one or more objects in the surrounding environment of the vehicle. A plurality of trajectory proposals are determined for a first object of the one or more objects. For each trajectory proposal of the plurality of trajectory proposals, a score indicative of a likelihood that the first object will take a trajectory consistent with the trajectory proposal, and an offset for modifying the trajectory proposal are generated.

Abstract: In one embodiment, a method includes accessing a first set of driving metrics of a vehicle navigating a segment using a driving control system; computing, based on the first set of driving metrics, a driving characteristic for the vehicle. The driving characteristic of the vehicle being represented by the first set of driving metrics. The method also includes comparing the driving characteristic of the vehicle to a driving characteristic of a number of manually controlled vehicles represented by a second set of driving metrics collected while navigating the segment; and computing a score indicating an elegance of the driving control system in navigating the segment based on the comparison of the driving characteristic of the vehicle to the driving characteristic of the number of manually controlled vehicles.

Abstract: An ad server logs web traffic regarding web page traffic by users. The web traffic is analyzed to determine web activity indicating that a user is being paid to fake legitimate web traffic. These users are referred to as abusive users. The web traffic is also analyzed to determine web activity indicating that a web page is artificially boosting its own traffic in order to earn undeserved advertising revenue. These web pages are referred to as honeypot web pages. Scores are determined for both users and web pages, where the scores indicate the likelihood that the associated user or web page is an abusive user or a honeypot web page, respectively. The ad server uses these scores to determine an amount to bid on future impressions to those users and web pages.

Abstract: An ad server logs web traffic regarding web page traffic by users. The web traffic is analyzed to determine web activity indicating that a user is being paid to fake legitimate web traffic. These users are referred to as abusive users. The web traffic is also analyzed to determine web activity indicating that a web page is artificially boosting its own traffic in order to earn undeserved advertising revenue. These web pages are referred to as honeypot web pages. Scores are determined for both users and web pages, where the scores indicate the likelihood that the associated user or web page is an abusive user or a honeypot web page, respectively. The ad server uses these scores to determine an amount to bid on future impressions to those users and web pages.

Abstract: The safe pixel is code embedded in a web page that is executed when the web page is accessed by a user agent. When the safe pixel is executed, the safe pixel collects information about the device and invokes the execution of one or more abuse detection functions. Each abuse detection function implements a different technique for estimating the likelihood of abusive behavior being the cause of the safe pixel being executed. The safe pixel transmits in a reporting message the local information and the results of the abuse detection function executions to a traffic server. The traffic server analyzes the reporting message to make a determination of the validity of the action that caused the safe pixel being executed.

Abstract: A third party company (also referred to as an ad server) provides an advertiser with computer code to place on the advertiser's web pages. The web page's code is configured to provide the ad server read and write access to an advertiser's first party cookie on a user's web browser. A user interacts with an ad on a mobile application or third party web page. Based on the user's interaction with the ad a URL containing a web address and ad instance information are sent to the user's web browser. The user's landing page associated with the URL contains code for retrieving the ad instance information and storing it in a first party cookie. When the user navigates to a purchasing page and purchases a product, the code contained in the purchasing page retrieves the ad instance information from the first party cookie and sends it to the ad server.

Abstract: A third party company (also referred to as an ad server) provides an advertiser with computer code to place on the advertiser's web pages. The web page's code is configured to provide the ad server read and write access to an advertiser's first party cookie on a user's web browser. A user interacts with an ad on a mobile application or third party web page. Based on the user's interaction with the ad a URL containing a web address and ad instance information are sent to the user's web browser. The user's landing page associated with the URL contains code for retrieving the ad instance information and storing it in a first party cookie. When the user navigates to a purchasing page and purchases a product, the code contained in the purchasing page retrieves the ad instance information from the first party cookie and sends it to the ad server.

Abstract: An ad server provides an advertiser with computer code to include in advertisement (ad) instances. Upon interaction with one of the ad instances, the computer code determines if a mobile software application associated with an advertiser is installed on a mobile device. The ad server may also provide mobile application developers with a software development kit (SDK) for use in creating mobile applications capable of determining if a mobile software application associated with the advertiser is installed on a mobile device, retrieving usage information associated with the user's use of the mobile device, receiving ad instances for display to a user through the mobile software application, and communicating this information to the ad server. Based on the installation status and the usage information the ad server selects ad instances to serve to the user of the mobile device.

Abstract: A third party company (also referred to as an ad server) provides an advertiser with computer code to place on the advertiser's web pages. The web page's code is configured to provide the ad server read and write access to an advertiser's first party cookie on a user's web browser. A user interacts with an ad on a mobile application or third party web page. Based on the user's interaction with the ad a URL containing a web address and ad instance information are sent to the user's web browser. The user's landing page associated with the URL contains code for retrieving the ad instance information and storing it in a first party cookie. When the user navigates to a purchasing page and purchases a product, the code contained in the purchasing page retrieves the ad instance information from the first party cookie and sends it to the ad server.