A travel assistance device includes: an inner area prediction unit predicting a with-vehicle interaction that is a behavior taken, in response to a state of the subject vehicle, by a moving object within an inner area around the subject vehicle; an outer area prediction unit predicting a with-environment interaction that is a behavior taken by a moving object according to surrounding environment of the moving object within an outer area further to the subject vehicle than the inner area; an outer area planning unit planning a future behavior of the subject vehicle based on the predicted with-environment interaction, wherein the future behavior is a behavior pattern of the subject vehicle realized by traveling control; and an inner area planning unit planning a future trajectory of the subject vehicle in accordance with the future behavior based on the predicted with-vehicle interaction.

A trajectory for an autonomous machine may be evaluated for safety based at least on determining whether the autonomous machine would be capable of occupying points of the trajectory in space-time while still being able to avoid a potential future collision with one or more objects in the environment through use of one or more safety procedures. To do so, a point of the trajectory may be evaluated for conflict based at least on a comparison between points in space-time that correspond to the autonomous machine executing the safety procedure(s) from the point and arrival times of the one or more objects to corresponding position(s) in the environment. A trajectory may be sampled and evaluated for conflicts at various points throughout the trajectory. Based on results of one or more evaluations, the trajectory may be scored, eliminated from consideration, or otherwise considered for control of the autonomous machine.

The methods and systems are directed to computational approaches for training and using machine learning algorithms to predict the conditional marginal distributions of the position of agents at flexible evaluation horizons and can enables more efficient path planning. These methods model agent movement by training a deep neural network to predict the position of an agent through time. A neural ordinary differential equation (neural ODE) that represents this neural network can be used to determine the log-likelihood of the agent's position as it moves in time.

Methods of determining relevance of objects that a vehicle's perception system detects are disclosed. A system on or in communication with the vehicle will identify a time horizon, and a look-ahead lane based on a lane in which the vehicle is currently traveling. The system defines a region of interest (ROI) that includes one or more lane segments within the look-ahead lane. The system identifies a first subset that includes objects located within the ROI, but not objects not located within the ROI. The system identifies a second subset that includes objects located within the ROI that may interact with the vehicle during the time horizon, but not excludes actors that may not interact with the vehicle during the time horizon. The system classifies any object that is in the first subset, the second subset or both subsets as a priority relevant object.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that generates path prediction data for agents in the vicinity of an autonomous vehicle using one or more machine learning models. One of the methods includes identifying an agent in a vicinity of an autonomous vehicle navigating through an environment and determining that the agent is within a vicinity of a crossing zone across a roadway. The crossing zone can be a marked crossing zone or an unmarked crossing zone. For example, the crossing zone can be an unmarked crossing zone that has been identified based on previous observations of agents crossing the roadway. In response to determining that the agent is within a vicinity of a crossing zone: (i) features of the agent and of the crossing zone can be obtained; (ii) a first input that includes the features can be processed using a first machine learning model that is configured to generate a first crossing prediction that characterizes future crossing behavior of the agent, and (iii) a predicted path for the agent for crossing the roadway can be determined from at least the first crossing prediction.

A method for assisting in turning a vehicle, the method may include detecting or estimating that the vehicle is about to turn to a certain direction or is turning to the certain direction; sensing a relevant portion of an environment of the vehicle to provide sensed information, wherein the relevant portion of the environment is positioned at a side of the vehicle that corresponds with the certain direction; applying an artificial intelligence process on the sensed information to (i) detect objects within the relevant portion of the environment and (ii) estimate expected movement patterns of the objects within a time frame that ends with an expected completion of the turn of the vehicle; determining, given an expected trajectory of the vehicle during the turn and the expected movement patterns of the objects, whether at least one of the objects is expected to cross the trajectory of the vehicle during the turn; and responding to an outcome of the determining.

Systems and methods for obstacle detection are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having obstacles. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

The present disclosure relates to control performed in a case where a vehicle is to turn right or left at an intersection. A control device causes the vehicle to carry out a right turn or left turn when a travel start button for starting travel from a stopped state is manipulated while the vehicle is in a stopped state due to presence of a target to be paid attention to during travel, such as a vehicle in an opposite lane or a pedestrian.

A driving assist device for a vehicle sets a a roadway area ahead of the vehicle, detects an avoidance target existing ahead of the vehicle, and executes collision avoidance control that avoids a collision between the vehicle and the avoidance target. The collision avoidance control is more likely to be executed when the avoidance target is within the roadway area than when the avoidance target is outside the roadway area. The driving assist device detects a roadway end object and a first lane marking of a first lane in which the vehicle exists. An imaginary position is a position apart from the detected position of the roadway end object toward the first lane by a constant distance. The driving assist device sets the imaginary position or the detected position of the the first lane marking as a boundary position of the roadway area based on a predetermined condition.

A navigation system for a host vehicle is provided. The system may comprise at least one processing device comprising circuitry and a memory. The memory includes instructions that when executed by the circuitry cause the at least one processing device to: receive a plurality of images acquired by a camera, the plurality of images being representative of an environment of the host vehicle; analyze the plurality of images to identify a presence in the environment of the host vehicle a navigation rule suspension condition; temporarily suspend at least one navigational rule in response to identification of the navigation rule suspension condition; and cause at least one navigational change of the host vehicle unconstrained by the temporarily suspended at least one navigational rule.