Abstract: Aspects of the disclosure provide systems and methods for confirming the identity of a passenger and changing destination of a vehicle. This may include receiving dispatching instructions to pick up a first passenger at a pickup location and to drop off the first passenger at a first destination as well as authentication information for authenticating a first client computing device of the first passenger. Once the client device is authenticated and a second passenger enters the vehicle, the vehicle is maneuvered towards the first destination. While doing so, a location of the vehicle is compared to location information received from the client computing devices. A notification is sent to a dispatching server based on the comparison and a second destination location is received in response. The vehicle is then maneuvered towards the second destination instead of the first destination.

Abstract: Aspects of the technology relate to exception handling for a vehicle. For instance, a current trajectory for the vehicle and sensor data corresponding to one or more objects may be received. Based on the received sensor data, projected trajectories of the one or more objects may be determined. Potential collisions with the one or more objects may be determined based on the projected trajectories and the current trajectory. One of the potential collisions that is earliest in time may be identified. Based on the one of the potential collisions, a safety-time-horizon (STH) may be identified. When a runtime exception occurs, before performing a precautionary maneuver to avoid a collision, waiting no longer than the STH for the runtime exception to resolve.

Abstract: The technology provides ride hailing systems and methods. This can include receiving, by a ride hailing system, a ride hail request from a user's client device. The ride hail request includes information about a pickup or a drop-off to be scheduled. The process includes obtaining real-time information including fleet constraint information associated with a fleet of vehicles, and applying the received information and the real-time information to a ride hailing model that was trained on training data including customer preference data and historical fleet trip information. The process includes obtaining from the model a set of ride hail suggestions including pickup positions, drop-off positions, walking paths from a given pickup position to a vehicle, and/or walking paths from a given drop-off position to a destination. The process also includes sending the set of ride hail suggestions to the client device for presentation to the user.

Abstract: The technology relates to a seamless interface between an autonomous vehicle service provider and one or more ridesharing or ride-hailing partner companies. An API enables efficient and robust communication with such partner companies for effective rider services and support. The API enables a partner company to determine how quickly an autonomous vehicle from the service provider could pick up a rider from a given location, as well as the cost of the ride. Customers may request rides or modify scheduled trips via an app running on the user's mobile phone or other communication device. The service may allow customers to directly communicate with the ride provider company, and may also allow customers to book or modify rides via interaction with a partner company that works with the ride provider company, either with the same or a different app.

Abstract: A control system for an autonomous vehicle is configured to pick up a passenger at a pickup location. The autonomous vehicle includes a self-driving system and one or more computing devices in communication with the self-driving system. The one or more computing devices are configured to receive a trip request including a pickup location and a destination location, the trip request being associated with a client device; cause the self-driving system to navigate the autonomous vehicle to the pickup location; send a prompt to the client device to collect semantic information; determine a specified location based on the semantic information received in response to the prompt; identify one or more semantic markers for the specified location from the semantic information; and send a message to the client device identifying the specified location using the one or more semantic markers.

Abstract: Aspects of the disclosure relate to determining and responding to an internal state of a self-driving vehicle. For instance, an image of an interior of the vehicle captured by a camera mounted in the vehicle is received. The image is processed in order to identify one or more visible markers at predetermined locations within the vehicle. The internal state of the vehicle is determined based on the identified one or more visible markers. A responsive action is identified action using the determined internal state, and the vehicle is controlled in order to perform the responsive action.

Abstract: Aspects of the disclosure relate to evaluating quality of a predetermined pullover location for an autonomous vehicle. For instance, a plurality of inputs for the predetermined pullover location may be received. The plurality of inputs may each include a value representative of a characteristic of the predetermined pullover location. The plurality of inputs may be combined to determine a pullover quality value for the predetermined pullover location. The pullover quality value may be provided to a vehicle in order to enable the vehicle to select a pullover location for the vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automatically designating traffic scenarios as safety-relevant traffic conflicts between agents in a driving environment. One of the methods includes receiving data representing a traffic scenario involving two agents; computing a safety-relevant metric for a first plurality of time points of the traffic scenario; computing a surprise metric for a second plurality of time points of the traffic scenario; determining that the surprise metric satisfies a surprise threshold within a threshold time window of the safety-relevant metric satisfying a safety-relevant threshold; and in response, designating the traffic scenario as a safety-relevant traffic conflict.

Abstract: Aspects of the disclosure relate to testing situational awareness of a test driver tasked with monitoring the driving of a vehicle operating in an autonomous driving mode. For instance, a signal that indicates that the test driver may be distracted may be identified. Based on the signal, that a question can be asked of the test driver may be determined. A plurality of factors relating to a driving context for the vehicle may be identified. Based on the determination, a question may be generated based on the plurality of factors. The question may be provided to the test driver. Input may be received from the test driver providing an answer to the question.

Abstract: An autonomous vehicle configured for active sensing may also be configured to weigh expected information gains from active-sensing actions against risk costs associated with the active-sensing actions. An example method involves: (a) receiving information from one or more sensors of an autonomous vehicle, (b) determining a risk-cost framework that indicates risk costs across a range of degrees to which an active-sensing action can be performed, wherein the active-sensing action comprises an action that is performable by the autonomous vehicle to potentially improve the information upon which at least one of the control processes for the autonomous vehicle is based, (c) determining an information-improvement expectation framework across the range of degrees to which the active-sensing action can be performed, and (d) applying the risk-cost framework and the information-improvement expectation framework to determine a degree to which the active-sensing action should be performed.

Abstract: An example method includes receiving point cloud information about a field of view of a lidar system. The point cloud information includes spatiotemporal and amplitude information about return light received. The method also includes determining, based on the point cloud information, a set of bright light returns from at least one highly reflective object. The bright light returns include return light having an amplitude above a photon threshold and a corresponding bright light return range. The method yet further includes determining, based on the point cloud information, a set of crosstalk returns. The crosstalk returns include return light having a corresponding crosstalk return range. The method includes adjusting, based on a normalized number of crosstalk returns, at least one of: a cleaning system, an operating mode of a lidar system, or an operating mode of a vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting actions for an agent at a specific real-world location using historical data generated at the same real-world location. One of the methods includes determining a current geolocation of an agent within an environment; obtaining historical data for geolocations in a vicinity of the current geolocation of the agent from a database that maintains historical data for a plurality of geolocations within the environment, the historical data for each geolocation comprising observations generated at least in part from sensor readings of the geolocation captured by vehicles navigating through the environment; generating an embedding of the obtained historical data; and providing the embedding as an input to a policy decision-making system that selects actions to be performed by the agent.

Abstract: Example embodiments relate to transmitter charging modules for light detection and ranging (lidar) devices. An example embodiment includes a method. The method includes receiving, from a controller, an indication of a first set of light emitters to be fired during a firing cycle. The first set of light emitters is a subset of a plurality of light emitters of the lidar device. The method also includes selectively charging, by a charging circuit of the lidar device during a charging cycle, a first set of energy storage devices of the lidar device. Additionally, the method includes refraining from charging, by the charging circuit of the lidar device during the charging cycle, each energy storage device in the plurality of energy storage devices that is not in the first set of energy storage devices. Further, the method includes emitting light signals from the first set of light emitters during the firing cycle.

Abstract: The technology relates to generating a representation of an object detected by a perception system of a vehicle. For instance, a set of data points corresponding to an object is received from the perception system. Map information identifying shapes and locations of lanes as well as locations of center points for the lanes is retrieved. A representative point of the center points is selected based on the set of data points. A first position is determined based on the location of the representative point. A second position is determined based on the set of data points. The first and second positions are used to determine a third position for a representation of the object based on a distance the first position and the second position. The representation of the object is generated using the third position. The representation of the object is displayed on a display of the vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for assessing driving plans for autonomous vehicles. One of the methods includes obtaining data representing a goal for an agent in a driving environment, generating one or more available trajectories for the agent, and selecting one or more future actions for the agent.

Abstract: The technology relates to planning trajectories for self-driving vehicles in order to transport passengers or cargo from a pickup location to a destination. Trajectory planning includes generating a speed plan for an upcoming portion of the trip in view of one or more constraints. The constraints may be due to proximity to an adjacent vehicle or other road user, and can include projected overlaps between the vehicle and other objects in the vehicle's nearby environment. Certain constraints may be binary or otherwise discontinuous in nature, in which a condition either exists at a given point in time or it does not. Noise in sensor data or prediction models may trigger such binary conditions, which in turn may cause the vehicle to alter the speed plan. Aspects of the technology employ permeable speed constraints that enable the vehicle to avoid problems associated with discontinuous constraints.

Abstract: The technology relates to assisting large self-driving vehicles, such as cargo vehicles, as they maneuver towards and/or park at a destination facility. This may include a given vehicle transitioning between different autonomous driving modes. Such a vehicles may be permitted to drive in a fully autonomous mode on certain roadways for the majority of a trip, but may need to change to a partially autonomous mode on other roadways or when entering or leaving a destination facility such as a warehouse, depot or service center. Large vehicles such as cargo truck may have limited room to maneuver in and park at the destination, which may also prevent operation in a fully autonomous mode. Here, information from the destination facility and/or a remote assistance service can be employed to aid in real-time semi-autonomous maneuvering.