Techniques and methods for performing collision monitoring using error models. For instance, a vehicle may generate sensor data using one or more sensors. The vehicle may then analyze the sensor data using systems in order to determine parameters associated with the vehicle and parameters associated with another object. Additionally, the vehicle may process the parameters associated with the vehicle using error models associated with the systems in order to determine a distribution of estimated locations associated with the vehicle. The vehicle may also process the parameters associated with the object using the error models in order to determine a distribution of estimated locations associated with the object. Using the distributions of estimated locations, the vehicle may determine the probability of collision between the vehicle and the object.

A vehicle, system and method for operating the vehicle is disclose. The system includes a radar system and a processor. The radar system locates a gap between targets in a second lane adjoining a first lane, with the host vehicle residing in the first lane. The processor is configured to determine a viability value of the gap for a lane change, select the gap based on the viability value, align the host vehicle with the selected gap, and merge the host vehicle from the first lane into the selected gap in the second lane.

Behavior information input unit receives stop-behavior information about vehicle from automatic-driving control device. Image-and-sound output unit outputs inquiry information for inquiring of an occupant whether a possibility of collision between an obstacle and vehicle is to be excluded from a determination object in automatic-driving control device to notification device, when a distance from one point on a predictive movement route of the obstacle to the obstacle is greater than or equal to a first threshold, and a speed of the obstacle is less than or equal to a second threshold. Operation signal input unit receives a response signal for excluding the collision possibility from the determination object. Command output unit outputs a command to exclude the collision possibility from the determination object to automatic-driving control device.

A control method for an autonomous vehicle is used in an autonomous vehicle including an engine, and a controller that controls an operation of the engine. In the control method, required driving force is set in accordance with an intervehicular distance between an own vehicle and a preceding vehicle when there is the preceding vehicle in front of the own vehicle. Also, when there is the preceding vehicle, a behavior of the preceding vehicle is predicted from a situation in front of the preceding vehicle. Further, when there is the preceding vehicle, sailing stop is executed based on the required driving force and the predicted behavior of the preceding vehicle. The sailing stop causes the engine to stop automatically while the own vehicle is traveling at vehicle speed equal to or higher than given vehicle speed.

Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.

A method for training a machine learning algorithm for predicting an intent parameter of an object in proximity to a self-driving vehicle on a terrain are provided. The method includes generating a training dataset having assessor-less labels, based on data collected by a training vehicle. The data collected by the training vehicle include data on the state of the training vehicle, the state of a training object, and a training terrain at a target moment in time and at a time after the target moment in time. The training data is based, at least in part, on the data for the target moment in time, and the assessor-less label is based, at least in part, on the data for a time after the target moment in time. A method for operating a self-driving vehicle and a self-driving vehicle are also disclosed.

An autonomous vehicle uses machine learning based models to predict hidden context attributes associated with traffic entities. The system uses the hidden context to predict behavior of people near a vehicle in a way that more closely resembles how human drivers would judge the behavior. The system determines an activation threshold value for a braking system of the autonomous vehicle based on the hidden context. The system modifies a world model based on the hidden context predicted by the machine learning based model. The autonomous vehicle is safely navigated, such that the vehicle stays at least a threshold distance away from traffic entities.

An automotive electronic dynamics control system for an automated motor-vehicle. The electronic dynamics control system is designed to implement two distinct Model Predictive Control (MPC)-based Trajectory Planners comprising a Longitudinal Trajectory Planner designed to compute a planned longitudinal trajectory for the automated motor-vehicle; and a Lateral Trajectory Planner designed to compute a planned lateral trajectory for the automated motor-vehicle. The electronic dynamics control system is further designed to cause the planned longitudinal trajectory to be computed before the planned lateral trajectory.

In one embodiment, a method, apparatus, and system for planning the trajectory of an autonomous driving vehicle (ADV) in view of an object within a buffer area in front of the ADV is disclosed. A buffer area in front of an ADV is identified. A first object of one or more objects that have entered the buffer area is identified. A first distance cost and a first relative speed cost associated with the first object are determined. A first object cost associated with the first object is determined based on a combination of the first distance cost and the first relative speed cost. A trajectory for the ADV is planned based at least in part on a cost function comprising the first object cost, where the cost function is minimized in the planning. Control signals are generated to drive the ADV based on the planned trajectory.

An autonomous vehicle uses machine learning based models such as neural networks to predict hidden context attributes associated with traffic entities. The hidden context represents behavior of the traffic entities in the traffic. The machine learning based model is configured to receive a video frame as input and output likelihoods of receiving user responses having particular ordinal values. The system uses a loss function based on cumulative histogram of user responses corresponding to various ordinal values. The system identifies user responses that are unlikely to be valid user responses to generate training data for training the machine learning mode. The system identifies invalid user responses based on response time of the user responses.