Abstract: A computing system can generate a map constraint interface enabling a fleet operator to update map constraints for autonomous vehicles (AVs). The map constraint interface can comprise a unified document model enabling the fleet operator to configure a set of constraint layers of autonomy maps utilized by the AVs. Each constraint layer can include a toggle feature that enables the fleet operator to enable and disable the constraint layer. The system can receive, via the map constraint interface, a set of inputs configuring the set of constraint layers of the one or more autonomy maps, compile a set of updated map constraints, corresponding to the configured set of constraint layers, into a document container, and output the document container to a subset of the AVs to enable the subset of AVs to integrate the set of updated map constraints with the autonomy maps.

Abstract: A system can analyze a sensor view of a surrounding area of a self-driving vehicle (SDV). Based on analyzing the sensor view, the system can determine that a decision point along a current route of the SDV exceeds a predetermined risk threshold, and diverge the SDV from the current route based at least in part on the decision point exceeding the predetermined risk threshold.

Abstract: A control system for an autonomous vehicle can determine a risk value for each respective path segment of a plurality of path segments in a given area that includes a destination of the autonomous vehicle. The risk value can correspond to a cost layer in a map that includes the respective path segment. Based on the risk value for each respective path segment, the control system can determine a travel route for the autonomous vehicle to the destination, and autonomously control the autonomous vehicle to navigate along the travel route to the destination.

Abstract: A control system of a self-driving vehicle (SDV) can process sensor data from the sensor system to autonomously operate acceleration, braking, and steering systems of the SDV throughout a given region. The control system can receive a transport directive from a transport facilitation system to service a pick-up request from a requesting user, the transport directive indicating an inputted pick-up location by the requesting user. The control system can then autonomously operate the acceleration, braking, and steering systems along a current route to a pick-up area encompassing the inputted pick-up location. The control system can further determine a corresponding set of pick-up location options for the pick-up area, and as the SDV approaches the pick-up area, perform a hierarchical operation to identify, via the sensor data, an optimal pick-up location to rendezvous with the requesting user.

Abstract: An autonomous vehicle can access map data comprising travel ways within a surrounding environment of the autonomous vehicle, and further access constraint data that define original navigational constraints within the map data. The vehicle can further receive constraint files comprising additional navigational constraints within the map data and modify the constraint data based on the constraint files. The vehicle can determine a travel route to a destination using composite constraint data and autonomously driver to the destination along the travel route accordingly.

Abstract: Systems and methods for controlling the motion of an autonomous vehicle are provided. In one example embodiment, one or more computing devices on-board an autonomous vehicle receive one or more constraint files including constraint data descriptive of one or more geographic identifiers (e.g., a polygon) and an application type (e.g., partial inclusion, complete inclusion, partial exclusion, complete exclusion) associated with each of the one or more geographic identifiers. Map data descriptive of the identity and location of different travel ways within the surrounding environment of the autonomous vehicle is accessed. A travel route for navigating the autonomous vehicle is determined, wherein the travel route is determined at least in part from the map data evaluated relative to the constraint data. Motion of the autonomous vehicle can be controlled based at least in part on the determined travel route.

Abstract: A computing system can receive sensor view data from each self-driving vehicle (SDV) in a fleet of SDVs operating throughout a given region. The system may further determine, based on the sensor view data, a set of properties of one or more vehicles external to the SDV. Based on the set of properties of the one or more vehicles, the system can generate traffic models for the given region and generate map data for users that indicate traffic flow for at least part of the given region.

Abstract: A transport system can receive vehicle data from each self-driving vehicle (SDV) in a fleet of SDVs operating throughout a given region. The transport system may further detect, in the vehicle data, a set of properties of one or more other vehicles external to the SDV. Based on the set of properties of the one or more vehicles, the transport system can construct traffic model(s) for the given region. Utilizing the traffic model(s), the transport system can provide estimated time of arrival (ETA) data, corresponding to SDVs in the fleet, to users of a transportation arrangement service in the given region.

Abstract: A hybrid trip planning system can receive transport requests from requesting users, and determine a pick-up location from each transport request. The pick-up location can be within or external to an autonomy grid on which a plurality of autonomous vehicles (AVs) can operate in an autonomous mode. The system can further determine a drop-off location from the transport request, the drop-off location also being within or external to the autonomy grid. The system can select and route an AV to a most optimal entry and/or exit point of the autonomy grid based on the transport request, where the selected AV is to switch between a manual and an autonomous mode.

Abstract: A control system for an autonomous vehicle can determine a risk value for each respective path segment of a plurality of path segments in a given area that includes a destination of the autonomous vehicle. The risk value can correspond to a cost layer in a map that includes the respective path segment. Based on the risk value for each respective path segment, the control system can determine a travel route for the autonomous vehicle to the destination, and autonomously control the autonomous vehicle to navigate along the travel route to the destination.

Abstract: A computing system can generate a map constraint interface enabling a fleet operator to update map constraints for autonomous vehicles (AVs). The map constraint interface can comprise a unified document model enabling the fleet operator to configure a set of constraint layers of autonomy maps utilized by the AVs. Each constraint layer can include a toggle feature that enables the fleet operator to enable and disable the constraint layer. The system can receive, via the map constraint interface, a set of inputs configuring the set of constraint layers of the one or more autonomy maps, compile a set of updated map constraints, corresponding to the configured set of constraint layers, into a document container, and output the document container to a subset of the AVs to enable the subset of AVs to integrate the set of updated map constraints with the autonomy maps.

Abstract: A control system of a self-driving vehicle (SDV) can process sensor data from the sensor system to autonomously operate acceleration, braking, and steering systems of the SDV throughout a given region. The control system can receive a transport directive from a transport facilitation system to service a pick-up request from a requesting user, the transport directive indicating an inputted pick-up location by the requesting user. The control system can then autonomously operate the acceleration, braking, and steering systems along a current route to a pick-up area encompassing the inputted pick-up location. The control system can further determine a corresponding set of pick-up location options for the pick-up area, and as the SDV approaches the pick-up area, perform a hierarchical operation to identify, via the sensor data, an optimal pick-up location to rendezvous with the requesting user.

Abstract: A hybrid trip planning system can receive transport requests from requesting users, determine pick-up and/or drop off locations from the transport request, and select available autonomous vehicles (AV) to service the transport requests. For each transport request, the planning system can identify a plurality of entry points from the pick-up location to an autonomy grid on which the AVs operate, and a plurality of exit points from the autonomy grid to the drop-off location. The planning system may determine optimal entry and/or exit points and transmit transport data to the selected AV. The transport data can provide optimal routing for a human safety driver to drive the selected AV in manual segments that are off grid, and switch the AV into an autonomous driving mode within the autonomy grid.

Abstract: A hybrid trip planning system can receive transport requests from requesting users, and determine a pick-up location from each transport request. The pick-up location can be within or external to an autonomy grid on which a plurality of autonomous vehicles (AVs) can operate in an autonomous mode. The system can further determine a drop-off location from the transport request, the drop-off location also being within or external to the autonomy grid. The system can select and route an AV to a most optimal entry and/or exit point of the autonomy grid based on the transport request, where the selected AV is to switch between a manual and an autonomous mode.

Abstract: A system and method for autonomous vehicle routing using annotated maps. For at least some path segments within a geographic region in which the vehicle is operating, values are determined for the path segments based at least on risk factors associated with autonomous operation of the vehicle along each path segment. Path segments are combined to generate a travel route, from a first location to a second location, based on the determined values, and the vehicle is controlled to navigate along the travel route.

Abstract: A system can analyze a sensor view of a surrounding area of a self-driving vehicle (SDV). Based on analyzing the sensor view, the system can determine that a decision point along a current route of the SDV exceeds a predetermined risk threshold, and diverge the SDV from the current route based at least in part on the decision point exceeding the predetermined risk threshold.

Abstract: A control system of a self-driving vehicle (SDV) can process sensor data from the sensor system to autonomously operate acceleration, braking, and steering systems of the SDV throughout a given region. The control system can receive a transport directive from a transport facilitation system to service a pick-up request from a requesting user, the transport directive indicating an inputted pick-up location by the requesting user. The control system can then autonomously operate the acceleration, braking, and steering systems along a current route to a pick-up area encompassing the inputted pick-up location. The control system can further determine a corresponding set of pick-up location options for the pick-up area, and as the SDV approaches the pick-up area, perform a hierarchical operation to identify, via the sensor data, an optimal pick-up location to rendezvous with the requesting user.

Abstract: A system and method for autonomous vehicle routing using annotated maps. For at least some path segments within a geographic region in which the vehicle is operating, values are determined for the path segments based at least on risk factors associated with autonomous operation of the vehicle along each path segment. Path segments are combined to generate a travel route, from a first location to a second location, based on the determined values, and the vehicle is controlled to navigate along the travel route.

Abstract: A system and method for dynamic vehicle routing using annotated maps and profiles. The system receives a transport request for a user and generates a travel route for the user based on the transport request, data indicative of autonomous operation of the vehicle along the travel route, and data indicative of preferences for the user. The vehicle is controlled to traverse autonomously along the travel route.

Abstract: A self-driving vehicle (SDV) can dynamically analyze a sensor view of a surrounding area of the SDV, and a current localization map in order to autonomously operate acceleration, braking, and steering systems of the SDV along a current route to a destination. Upon approaching a decision point along the current route, the SDV can perform a cost optimization to determine whether to diverge from the current route.