Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for planning the future trajectory of an autonomous vehicle in an environment. In one aspect, a method comprises obtaining multiple types of scene data characterizing a scene in an environment that includes an autonomous vehicle and multiple agents; receiving route data specifying an intended route for the autonomous vehicle; for each data type, processing at least the data type using a respective encoder network to generate a respective encoding of the data type; processing a sequence of the encodings using an encoder network to generate a respective alternative representation for each data type; and processing the alternative representations using a decoder network to generate a trajectory planning output that comprises respective scores for candidate trajectories that represent predicted likelihoods that the candidate trajectory is closest to resulting in the autonomous vehicle successfully navigating the intended route.

An apparatus and a method for controlling a velocity of an autonomous driving vehicle is provided. The method includes steps of: obtaining information of an environment surrounding the vehicle when an obstacle is detected to be on a planning path of the vehicle; obtaining an initial reference velocity profile of the vehicle; determining a safety factor based on the initial reference velocity profile, the information of the environment and information of the vehicle, wherein the safety factor at least comprises a safety distance between the vehicle and the obstacle for the vehicle to follow the obstacle; determining an optimized reference velocity profile based on the information of the environment, the information of the vehicle and the safety factor; and performing the step of determining the safety factor by using the optimized reference velocity profile as the initial reference velocity profile and the step of determining the optimized reference velocity iteratively.

A navigation system for a host vehicle may include a processor programmed to: receive, from an entity remotely located relative to the host vehicle, a sparse map associated with at least one road segment to be traversed by the host vehicle; receive point cloud information from a LIDAR system onboard the host vehicle, the point cloud information being representative of distances to various objects in an environment of the host vehicle; compare the received point cloud information with at least one of the plurality of mapped navigational landmarks in the sparse map to provide a LIDAR-based localization of the host vehicle relative to at least one target trajectory; determine an navigational action for the host vehicle based on the LIDAR-based localization of the host vehicle relative to the at least one target trajectory; and cause the at least one navigational action to be taken by the host vehicle.

Evasive steering assist (ESA) systems and methods for a vehicle utilize a set of vehicle perception systems configured to detect an object in a path of the vehicle, a driver interface configured to receive steering input from a driver of the vehicle via a steering system of the vehicle, a set of steering sensors configured to measure a set of steering parameters, and a controller configured to determine a set of driver-specific threshold values for the set of steering parameters, compare the measured set of steering parameters and the set of driver-specific threshold values to determine whether to engage/enable an ESA feature of the vehicle, and in response to engaging/enabling the ESA feature of the vehicle, command the steering system to assist the driver in avoiding a collision with the detected object.

A method includes obtaining, using at least one processing device, a vanishing point and a boundary based on image data associated with a scene, where the boundary is associated with a detected object within the scene. The method also includes repeatedly, during multiple iterations and using the at least one processing device, (i) identifying multiple patches within the boundary and (ii) determining a similarity of the image data contained within the multiple patches. The method further includes identifying, using the at least one processing device, a modification to be applied to the boundary based on the identified patches and the determined similarities. In addition, the method includes generating, using the at least one processing device, a refined boundary based on the modification, where the refined boundary identifies a specified portion of the detected object.

A sheet-shaped magnetic marker (1) to be laid on a road surface so as to be able to be detected by a magnetic sensor attached to a vehicle to achieve assist for driving operation of the vehicle by a driver or control on a vehicle side to achieve automatic driving independently from operation of the driver is divided into a plurality of regions in a matrix shape by a cut line (1C) cutting a magnet sheet (11) and a nonskid layer (181), with an adhesive layer being left. Thus, if peeling partially occurs, a region including the peeled part can be isolated, and expansion of peeling can be prevented.

A target vehicle recognition apparatus detects a stopped vehicle ahead of the host vehicle, detects a reference boundary line position where at least one of two boundary lines forming a travel lane of the host vehicle intersects a reference axis extending from a lower end of the stopped vehicle in an image horizontal direction on a captured image, recognizes the stopped vehicle as a target vehicle of steering control when the reference boundary line position between a vehicle left end position of the stopped vehicle and a vehicle right end position of the stopped vehicle is present, and does not recognize the stopped vehicle as a target vehicle of steering control when the reference boundary line position between the vehicle left end position of the stopped vehicle and the vehicle right end position of the stopped vehicle is not present.

Methods and systems for enabling an autonomous vehicle (AV) to determine a path to a stopping location are disclosed. Upon receipt of a service request, the AV will determine a desired stop location (DSL) and state information for the service request. The AV using the DSL and the state information to define a pickup/drop-off interval that comprises an area of a road that includes the DSL. When approaching the pickup/drop-off interval, the AV will uses its perception system to determine whether an object is occluding the DSL. If no object is occluding the DSL, the AV will continue along the path toward the DSL. However, if an object is occluding the DSL, the AV will identify and move to a non-occluded alternate stop location (ASL) within the pickup/drop-off interval. The ASL must satisfy one or more permissible stopping location criteria.

A system comprises an autonomous vehicle (AV) and an operation server operably coupled with the AV. The operation server accesses environmental data associated with a road traveled by the AV. The environmental data is associated with a time window during which the AV is traveling along the road. The operation server compares the environmental data with map data that comprises expected road conditions ahead of the AV. The operation server determines whether the environmental data comprises an unexpected road condition that is not included in the map data. In response to determining that the environmental data comprises the unexpected road condition that is not included in the map data, the operation server determines a location coordinate of the unexpected road condition, and communicates a command to the AV to maneuver to avoid the unexpected road condition.

The present disclosure provides a device and method for generating lane information. The method includes obtaining information on a structure located around a vehicle and driving information of a surround vehicle based on information collected by a sensor and prestored navigation information; and generating geometric information on a travel lane of the vehicle in a road area based on the information on the structure and the driving information of the surround vehicle.