Provided is a multi-vehicle collaborative trajectory planning method, apparatus (600) and system, and a device, a storage medium, and a computer program product. The method comprises: determining a specific number of different multi-vehicle priority schemes for multiple vehicles (S101); determining, by using a sequential planning policy, a corresponding collaborative planning scheme for each multi-vehicle priority scheme (S102); performing quality evaluation on each collaborative planning scheme to obtain a quality evaluation result (S103); and according to the quality evaluation result, determining a target collaborative planning scheme from the specific number of collaborative planning schemes (S104).

A computing system for alternate path generation is disclosed. In aspects, the computing system can implement methods to generate the alternate paths by: identifying an optimal path to a destination node on a first graph, generating a path graph, and generating an alternate path sequence based on the path graph. In aspects, the computing system can further generate an interactive graphical user interface (GUI) for displaying the alternate path sequence and transmit the interactive GUI to a display unit for display.

A system for generating linear feature data is provided. The system may determine, from sensor data, detection data associated with at least one link. The at least one link comprises a plurality of sub links. The system may further determine, using map data, one or more linear feature clusters for each of the plurality of sub links, based on the detection data. Furthermore, the system may determine a plurality of linear feature groups for the at least one link, based on at least one set of feature matched distances and the determined linear feature clusters, where a given linear feature group respectively comprises at least one first linear feature cluster associated with a first sub link and at least one second linear feature cluster associated with a second sub link. Furthermore, the system may generate the linear feature data, based on the plurality of linear feature groups.

A parking cruise request is received. A network version starting segment is identified and a route determination algorithm is expended starting at the network version starting segment. When the route determination algorithm is expanded to a new segment, a cost value is determined for the new segment based at least on the likelihood of finding parking on the new segment. Responsive to determining that the likelihood of finding parking along the cruise route does satisfy the threshold probability requirement, map version agnostic identifiers for each segment of the cruise route are generated. Each of the map version agnostic identifiers are coded using at least one coding function to generate coded map version agnostic identifiers. A bloom filter having the coded map version agnostic identifiers as members is generated. A parking cruise route response comprising the bloom filter is provided such that a mobile apparatus receives the parking cruise route response.

An information processing device (20) includes a route acquisition unit (202) and an automatic driving section determination unit (204). The route acquisition unit (202) acquires route information indicating a moving route of a mobile body. The automatic driving section determination unit (204) acquires adaptation coefficients for a plurality of sections included in the moving route indicated by the route information, with reference to an adaptation coefficient storage unit (206) that stores automatic driving adaptation coefficients set for the respective sections. Further, the automatic driving section determination unit (204) determines the automatic driving sections of the mobile body in the moving route, based on the acquired adaptation coefficients.

Route planning is provided to a vehicle (or vehicle driver) based at least in part on the type of vehicle and the terrain conditions between the originating location and destination. The vehicle may employ a terrain monitoring system including a surface-penetrating radar (SPR) system for obtaining SPR signals as the vehicle travels along a route; the obtained SPR signals may be used for navigation against reference images associated with the route. In some embodiments, a navigation server bases route selection in part on the terrain associated with various routes and characteristics of the vehicle.

A personalized transportation plan for multi-modal transportation can be generated from an origin location, a destination location, and a route component server. A route data record might comprise a plurality of route components from the origin to the destination, represented in a route component record comprising indications of a route component start location, a route component end location, and a transportation mode for the route component. Route data records can be filtered based on user constraints determined from a user profile database. The filtered plurality of route data records can be used, with a transportation provider database, to determine a set of transportation option records for a given route component record wherein transportation option records indicate a provider of transportation from the route component start location for the route component record to the route component end location for the route component record. Bid messages can be generated for route components.

An autonomous vehicle (AV) described herein is configured to receive a pull over location specified by a passenger, and is further configured to refine the pull over location based upon one or more factors, where the factors include computer-readable content from a profile of the passenger, sensor data output by sensor systems of the AV, observed or predicted weather conditions, observed or predicted traffic, and/or observations recently generated by other AVs that belong to the same fleet as the AV.

Method and system for narrow passage path sampling based on levy flight is disclosed. The disclosed technique is an improvisation of Random Walk to Surface (RWS), wherein, instead of performing a random walk, the disclosed technique utilizes levy flight mechanism to identify samples in narrow passages (on the obstacle boundaries). The disclosed technique for identification of narrow passages sampling points in the narrow passage is based on several techniques that include random uniform sampling technique, a levy flight function (step size) and a collision detection technique. Moreover, in addition to identification of narrow passages sampling points, the disclosed technique also performs an additional check to ensure that the identified narrow passages sampling points are present in the narrow passage based on a levy flight bridge sampler technique.

A system described herein may provide a technique for the generation of a node map using contraction hierarchy techniques in a manner that accounts for multi-link constraints. Multi-link constraints may include a sequence of two or more links through the node map, and paths that include such multi-link constraints may be associated with an additional cost based on such inclusion. Shortcut links that represent paths through nodes contracted out of the node map may be associated with portions of multi-link constraints. Paths through such shortcut links, where such paths include the remainder of the multi-link constraint, may be considered as including the multi-link constraint, and the cost of such paths may be calculated accordingly. The costs of links and/or paths, including paths that include multi-link constraints, may be used in determining a path from a source node to a target node of the node map.