Abstract: The disclosed technology provides solutions for providing an accurate pick-up location for an autonomous vehicle and a rider during a ride hailing pick-up. A method of the disclosed technology can include steps for determining map information associated with at least one thoroughfare for routing an autonomous vehicle, wherein the map information is based on location data associated with a client device requesting the autonomous vehicle; receiving sensor data from the client device corresponding to the at least one thoroughfare; determining, based on the sensor data and the map information, a first position of the client device relative to the at least one thoroughfare; and routing the autonomous vehicle based on the first position of the client device relative to the at least one thoroughfare. Systems and machine-readable media are also provided.

Abstract: Systems and techniques are provided for automated door opening and automated door closing in an autonomous vehicle (AV). An example method can include sending a first signal to at least one automatic door actuator for opening at least one door of an autonomous vehicle (AV), wherein the at least one door gives access to the AV to one or more passengers for a ridehail service provided by the AV: determining, based on data received from at least one AV sensor, that the one or more passengers are seated within the AV; and in response to determining that the one or more passengers are seated within the AV, sending a second signal to the at least one automatic door actuator for closing the at least one door of the AV.

Abstract: Perception data based multipath identification and correction is based on recognition that sensors such as radar, LIDAR, and cameras can generate perception data indicative of locations and properties of terrestrial objects in an environment surrounding a satellite navigation device (e.g., a GNSS receiver), which data may then be used in training, or updating, a model for determining or correcting distances to satellites to account for multipath. Multipath identification includes identifying multipaths to train the model, e.g., by using perception data to perform ray tracing. Multipath correction includes using the model to correct distance errors due to the multipaths or, equivalently, using the model to determine distances to satellites in a manner that accounts for the multipaths.

Abstract: The disclosed technology provides solutions for providing an accurate pick-up location for an autonomous vehicle and a rider during a ride hailing pick-up. A method of the disclosed technology can include steps for determining map information associated with at least one thoroughfare for routing an autonomous vehicle, wherein the map information is based on location data associated with a client device requesting the autonomous vehicle; receiving sensor data from the client device corresponding to the at least one thoroughfare; determining, based on the sensor data and the map information, a first position of the client device relative to the at least one thoroughfare; and routing the autonomous vehicle based on the first position of the client device relative to the at least one thoroughfare. Systems and machine-readable media are also provided.

Abstract: Systems and techniques are provided for controlling an active seating system in an autonomous vehicle (AV). An example method can include determining an anticipated movement of an autonomous vehicle (AV) based on at least one of AV route data, AV map data, and AV sensor data; determining, based on the anticipated movement, one or more seat operations for an active seating system associated with at least one AV seat, wherein the one or more seat operations are configured to mitigate an effect of the anticipated movement on the at least one AV seat; and sending at least one instruction that includes the one or more seat operations to the active seating system.

Abstract: The disclosed technology provides solutions for improving the accuracy of localization error estimates and in particular, provides methods for improving the accuracy of error estimates associated with individual localizers. A method of the disclosed technology can include steps for receiving a first location error estimate, corresponding with a first localizer of a first autonomous vehicle (AV), receiving a second location error estimate, corresponding with a second localizer of the first AV, and associating the first location error estimate and the second location error estimate with first location metadata and first environmental metadata corresponding with the first AV. The method can further include steps for determining a location error variance for the first localizer, based on the first location metadata, and the first environmental metadata. Systems and machine-readable media are also provided.

Abstract: Techniques are described for aligning a vehicle to a wireless charger. Wireless communication is performed between at least a first wireless device of the vehicle and at least a second wireless device external to the vehicle. The first wireless device has a stationary position relative to the vehicle. The second wireless device has a stationary position relative to the wireless charger. Based on the wireless communication, a distance between the first and second wireless devices is measured and used to determine the relative position of the vehicle. A trajectory is calculated, based on the relative position of the vehicle, to enable the vehicle to be maneuvered into a charging position in which a charge receiving device of the vehicle is aligned with respect to the wireless charger. In some embodiments, multiple wireless devices on the vehicle or external to the vehicle participate in determining the relative position of the vehicle.

Abstract: Systems and methods for determining precise pick-up locations for passengers who have requested autonomous vehicle rides. In particular, systems and methods are provided for using wireless signals to determine user location. In some examples, wireless ranging technology, such as Ultra Wide Band (UWB), is used to determine the user location. Wireless transceivers are used to determine a mobile device's range, and range information from multiple transceivers is used to determine the mobile's device's position. In some examples, triangulation is used to determine user location, such as triangulation between one or more wireless transceivers and the mobile device. In various examples, wireless transceivers are installed on autonomous vehicles, and in some examples, wireless transceivers are installed in various static locations (e.g., on buildings, lamp posts, or other structures.

Abstract: Perception data based multipath identification and correction is based on recognition that sensors such as radar, LIDAR, and cameras can generate perception data indicative of locations and properties of terrestrial objects in an environment surrounding a satellite navigation device (e.g., a GNSS receiver), which data may then be used in training, or updating, a model for determining or correcting distances to satellites to account for multipath. Multipath identification includes identifying multipaths to train the model, e.g., by using perception data to perform ray tracing. Multipath correction includes using the model to correct distance errors due to the multipaths or, equivalently, using the model to determine distances to satellites in a manner that accounts for the multipaths.

Abstract: Perception data based multipath identification and correction is based on recognition that sensors such as radar, LIDAR, and cameras can generate perception data indicative of locations and properties of terrestrial objects in an environment surrounding a satellite navigation device (e.g., a GNSS receiver), which data may then be used in training, or updating, a model for determining or correcting distances to satellites to account for multipath. Multipath identification includes identifying multipaths to train the model, e.g., by using perception data to perform ray tracing. Multipath correction includes using the model to correct distance errors due to the multipaths or, equivalently, using the model to determine distances to satellites in a manner that accounts for the multipaths.

Abstract: A method includes obtaining position information of a first vehicle collected in real time by a first positioning system during a first trip on a route, post-processing the collected position information to determine corrected position data of the first vehicle during the first trip, computing position errors of the first positioning system at a plurality of locations during the first trip, determining integrity performance of the first positioning system at the plurality of locations, and providing the integrity performance of the first positioning system at the plurality of locations to the first vehicle or a second vehicle for determining real-time integrity performance of the first positioning system on the first vehicle or a second positioning system on the second vehicle at the plurality of locations.

Abstract: Perception data based multipath identification and correction is based on recognition that sensors such as radar, LIDAR, and cameras can generate perception data indicative of locations and properties of terrestrial objects in an environment surrounding a satellite navigation device (e.g., a GNSS receiver), which data may then be used in training, or updating, a model for determining or correcting distances to satellites to account for multipath. Multipath identification includes identifying multipaths to train the model, e.g., by using perception data to perform ray tracing. Multipath correction includes using the model to correct distance errors due to the multipaths or, equivalently, using the model to determine distances to satellites in a manner that accounts for the multipaths.

Abstract: A method includes obtaining position information of a first vehicle collected in real time by a first positioning system during a first trip on a route, post-processing the collected position information to determine corrected position data of the first vehicle during the first trip, computing position errors of the first positioning system at a plurality of locations during the first trip, determining integrity performance of the first positioning system at the plurality of locations, and providing the integrity performance of the first positioning system at the plurality of locations to the first vehicle or a second vehicle for determining real-time integrity performance of the first positioning system on the first vehicle or a second positioning system on the second vehicle at the plurality of locations.

Abstract: A method for determining positions of a mobile system is disclosed. The method involves receiving, by a receiver of the mobile system, a first set of correction data which is broadcasted from a first transmitter, wherein the first set of correction data comprises Differential Global Navigation Satellite System (D-GNSS) correction data, estimating, using a real-time kinematics (RTK) method, a first position of the mobile system using at least a portion of the first set of correction data, estimating one or more unknown parameters of a precise point positioning (PPP) estimation method based at least on the estimated first position of the mobile system and the first set of correction data, and estimating a second position of the mobile system using the estimated one or more parameters and the PPP estimation method, wherein the second position of the mobile system is different from the first position of the mobile system.

Abstract: Techniques for remote operation of vehicles are presented. Remote operation can involve maneuvering, by a vehicle computer system, a vehicle based on driving instructions from a remote computer system. The vehicle computer system collects sensor data from a plurality of sensors onboard the vehicle. Based on the sensor data, data associated with a visual representation of the surrounding environment is generated and sent to the remote computer system. The generating of the data can involve fusing sensor data to identify one or more features of a surrounding environment. The generated data may be indicative of the identified features. The visual representation is output on a display device of the remote computer system. The driving instructions can be based on human input supplied in response to the visual representation. In certain embodiments, the vehicle is maneuvered toward a location within proximity of a parking space before performing automated parking.

Abstract: Techniques are described for aligning a vehicle to a wireless charger. Wireless communication is performed between at least a first wireless device of the vehicle and at least a second wireless device external to the vehicle. The first wireless device has a stationary position relative to the vehicle. The second wireless device has a stationary position relative to the wireless charger. Based on the wireless communication, a distance between the first and second wireless devices is measured and used to determine the relative position of the vehicle. A trajectory is calculated, based on the relative position of the vehicle, to enable the vehicle to be maneuvered into a charging position in which a charge receiving device of the vehicle is aligned with respect to the wireless charger. In some embodiments, multiple wireless devices on the vehicle or external to the vehicle participate in determining the relative position of the vehicle.

Abstract: A method, apparatus and computer readable medium that determine if an authorized mobile device is in a vicinity of a vehicle, upon determination that the authorized mobile device is in the vicinity of the vehicle, capture a plurality of images from an environment surrounding the vehicle, detect one or more pedestrians in the plurality of images, correlate a movement trajectory of the authorized mobile device with movement trajectory of the one or more detected pedestrians to determine an authorized person, and actuate a function of the vehicle when the authorized person crosses a first threshold distance from the vehicle.

Abstract: Techniques for remote operation of vehicles are presented. Remote operation can involve maneuvering, by a vehicle computer system, a vehicle based on driving instructions from a remote computer system. The vehicle computer system collects sensor data from a plurality of sensors onboard the vehicle. Based on the sensor data, data associated with a visual representation of the surrounding environment is generated and sent to the remote computer system. The generating of the data can involve fusing sensor data to identify one or more features of a surrounding environment. The generated data may be indicative of the identified features. The visual representation is output on a display device of the remote computer system. The driving instructions can be based on human input supplied in response to the visual representation. In certain embodiments, the vehicle is maneuvered toward a location within proximity of a parking space before performing automated parking.

Abstract: A method, apparatus and computer readable medium that determine if an authorized mobile device is in a vicinity of a vehicle, upon determination that the authorized mobile device is in the vicinity of the vehicle, capture a plurality of images from an environment surrounding the vehicle, detect one or more pedestrians in the plurality of images, correlate a movement trajectory of the authorized mobile device with movement trajectory of the one or more detected pedestrians to determine an authorized person, and actuate a function of the vehicle when the authorized person crosses a first threshold distance from the vehicle.

Abstract: A telematics control unit (TCU) of a vehicle includes at least one processor coupled to a memory, the at least one processor comprising a local authentication server configured to authenticate at least one device of a plurality of devices in the vehicle based on a first list of approved devices, and establish, upon successful authentication of the at least one device, a trusted communication link between the TCU and the at least one device to receive a first data from the at least one device and transmit a second data to the at least one device, wherein the first data is stored in the memory for future transmission to a remote server.