To determine a path through a pose configuration space, trajectories of poses may be evaluated in parallel based at least on translating the trajectories along at least one axis of the pose configuration space (e.g., an orientation axis). A trajectory may include at least a portion of a turn having a fixed turn radius. Turns or turn portions that have the same turn radius and initial orientation can be translatively shifted along and processed in parallel along the orientation axis as they are translated copies of each other, but with different starting points. Trajectories may be evaluated based at least on processing variables used to evaluate reachability as bit vectors with threads effectively performing large vector operations in synchronization. A parallel reduction pattern may be used to account for dependencies that may exist between sections of a trajectory for evaluating reachability, allowing for the sections to be processed in parallel.

A method for data management for an autonomous vehicle may include transmitting a polling request to a first server to obtain a task. The task may be a remote task request, and the task may be associated with obtaining, from the autonomous vehicle, data related to one or more subjects via a mobile network. The method may also include receiving the task from the first server based on the polling request. The method may also include obtaining the data based on the task. The method may also include transmitting the data to a second server via the mobile network.

A method for checking an automated driving function by reinforcement learning includes providing at least one specification of an automated driving function; generating a scenario, the scenario being specified by a first set of parameters; and determining a reward function such that the reward is greater in the event in which the scenario fails to meet the at least one specification in a simulation, than in the event in which the scenario meets the at least one specification in the simulation.

A method for checking an automated driving function by reinforcement learning includes providing at least one specification of an automated driving function; generating a scenario, the scenario being specified by a first set of parameters; and determining a reward function such that the reward is greater in the event in which the scenario fails to meet the at least one specification in a simulation, than in the event in which the scenario meets the at least one specification in the simulation.

The present invention relates to methods and systems that utilize the production vehicles to develop new perception features related to new sensor hardware as well as new algorithms for existing sensors by using self-supervised continuous training. To achieve this the production vehicle's own perception output is fused with other sensors in order to generate a bird's eye view of the road scenario over time. The bird's eye view is synchronized with buffered sensor data that was recorded when the road scenario took place and subsequently used to train a new perception model to output the bird's eye view directly.

The present invention relates to methods and systems that utilize the production vehicles to develop new perception features related to new sensor hardware as well as new algorithms for existing sensors by using self-supervised continuous training. To achieve this the production vehicle's own perception output is fused with other sensors in order to generate a bird's eye view of the road scenario over time. The bird's eye view is synchronized with buffered sensor data that was recorded when the road scenario took place and subsequently used to train a new perception model to output the bird's eye view directly.

The disclosure relates to a lane departure warning method and a lane departure warning system. The lane departure warning method of the disclosure includes: a warning area calculation step in which a warning area for lane departure of a vehicle is calculated based on information about the vehicle and information around the vehicle; a decision making step in which a current position of the vehicle is compared with the warning area calculated in the warning area calculation step, to determine whether the vehicle is located in the warning area and output a decision instruction; and a warning step in which a warning action is performed based on the decision instruction. According to the disclosure, a lane departure status of the vehicle can be more accurately estimated and timely warning can be performed when there is a tendency for lane departure.

A motion planning system includes: a processor; and memory to store instructions that when executed by the processor, cause the processor to: identify a reference path between a departure point and a destination point in an environment including one or more obstacles; generate decomposition segments of a space surrounding the reference path, the decomposition segments including a first free-space segment and a second free-space segment that are devoid of the obstacles; generating a first path segment relative to the reference path for traversing the first free-space segment, and a second path segment relative to the reference path for traversing the second free-space segment; and connecting the first and second path segments to each other to generate a navigational path to traverse the environment.

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to input a fisheye image to a vector quantized variational autoencoder. The vector quantized variational autoencoder can encode the fisheye image to first latent variables based on an encoder. The vector quantized variational autoencoder can quantize the first latent variables to generate second latent variables based on a dictionary of embeddings. The vector quantized variational autoencoder can decode the second latent variables to a rectified rectilinear image using a decoder and output the rectified rectilinear image.

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to input a fisheye image to a vector quantized variational autoencoder. The vector quantized variational autoencoder can encode the fisheye image to first latent variables based on an encoder. The vector quantized variational autoencoder can quantize the first latent variables to generate second latent variables based on a dictionary of embeddings. The vector quantized variational autoencoder can decode the second latent variables to a rectified rectilinear image using a decoder and output the rectified rectilinear image.