This application is directed to on-vehicle behavior modeling of vehicles. A vehicle has one or more processors, memory, a plurality of sensors, and a vehicle control system. The vehicle collects training data via the plurality of sensors, and the training data include data for one or more vehicles during a collection period. The vehicle locally applies machine learning to train a vehicle driving behavior model using the collected training data. The vehicle driving behavior model is configured to predict a behavior of one or more vehicles. The vehicle subsequently collecting sensor data from the plurality of sensors and drives the vehicle by applying the vehicle driving behavior model to predict vehicle behavior based on the collected sensor data. The vehicle driving behavior model is configured to predict behavior of an ego vehicle and/or a distinct vehicle that appears near the ego vehicle.

A method of generating an output trajectory of an ego vehicle includes recording trajectory data of the ego vehicle and pedestrian agents from a scene of a training environment of the ego vehicle. The method includes identifying at least one pedestrian agent from the pedestrian agents within the scene of the training environment of the ego vehicle causing a prediction-discrepancy by the ego vehicle greater than the pedestrian agents within the scene. The method includes updating parameters of a motion prediction model of the ego vehicle based on a magnitude of the prediction-discrepancy caused by the at least one pedestrian agent on the ego vehicle to form a trained, control-aware prediction objective model. The method includes selecting a vehicle control action of the ego vehicle in response to a predicted motion from the trained, control-aware prediction objective model regarding detected pedestrian agents within a traffic environment of the ego vehicle.

A system for estimating the friction between a road surface and a tire of a vehicle includes at least one first sensor and at least one vehicle processing device containing a friction estimation algorithm which is arranged to estimate the friction between the road surface and the tire of the vehicle based on friction related measurements is provided. The vehicle processing device is arranged to: receive an estimate of the expected friction between the road surface and the tire of the vehicle from a central processing device, from a storage device in the vehicle, or from at least one second sensor in the vehicle; adapt the friction estimation algorithm based on said received estimate of the expected friction; receive at least one friction related measurement from the at least one first sensor in the vehicle; and use the adapted friction estimation algorithm to perform an estimation of the friction between the road surface and the tire of the vehicle based on the at least one friction related measurement.

Aspects of the disclosure provide for reducing inconvenience to other road users caused by stopped autonomous vehicles. As an example, a vehicle having an autonomous driving mode may be stopped at a first location. While the vehicle is stopped, sensor data is received from a perception system of the vehicle. The sensor data may identify a road user. Using the sensor data, a value indicative of a level of inconvenience to the road user caused by stopping the vehicle at the first location may be determined. The vehicle is controlled in the autonomous driving mode to cause the vehicle to move from the first location and in order to reduce the value.

Provided herein is a system of a vehicle that comprises one or more sensors, one or more processors, and memory storing instructions that, when executed by the one or more processors, causes the system to perform: selecting a trajectory along a route of the vehicle; predicting a trajectory of another object along the route; adjusting the selected trajectory based on a predicted change, in response to adjusting the selected trajectory, to the predicted trajectory of the another object, the predicted change to the predicted trajectory of the another object being stored in a model; determining an actual change, in response to adjusting the selected trajectory, to a trajectory of the another object, in response to an interaction between the vehicle and the another object; updating the model based on the determined actual change to the trajectory of the another object; and selecting a future trajectory based on the updated model.

Method for updating at least one vehicle model parameter and at least one tire parameter in at least one chassis control unit of a vehicle, based on tire sensor information collected by a tire sensor placed on a tire. The method includes the steps of: collecting tire sensor information; updating the at least one vehicle model parameter based on updating at least one tire parameter, updating one tire parameter being based on the tire sensor information.

Systems, methods, and devices are disclosed for predicting behaviors of objects (vehicles, bicycles, pedestrians, etc.) at a location. A model descriptive of a possible object behavior can be received by an autonomous vehicle, where the model provides conditional predictions about a future behavior of an object based on a position of the object in a lane. The autonomous vehicle can detect the position of a specific object in the lane, and the model can then be applied to determine probabilities of a future behavior of the specific object.

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 disclosure provides a hybrid decision-making method for autonomous driving, including the following steps: acquiring real-time traffic environment information of an autonomous vehicle during the running at a current moment; establishing a local decision-making model for autonomous driving based on the traffic environment information; based on the local decision-making model for autonomous driving, learning, by using a method based on deep reinforcement learning, a driving behavior of the autonomous vehicle, and extracting driving rules; sharing the driving rules; augmenting an existing expert system knowledge base; and determining whether there is an emergency: if yes, making a decision by using a machine learning model; and if not, adjusting the machine learning model based on the augmented existing expert system knowledge base, and making a decision by the machine learning model. The decision-making method uses two existing policies to complement each other to overcome the shortcomings of a single policy, thereby making decisions effectively for different driving scenarios.

The information processing server includes an unstable behavior position recognition unit configured to recognize an unstable behavior position being a position on a map, at which the target vehicle has performed an unstable behavior, based on the target vehicle data, a support target vehicle determination unit configured to, when the unstable behavior position recognition unit recognizes the unstable behavior position, determine whether or not there is a support target vehicle, based on the unstable behavior position and the target vehicle data, the support target vehicle being the target vehicle estimated to perform the unstable behavior at the unstable behavior position within a predetermined time, and a vehicle support unit configured to, when the support target vehicle determination unit determines that there is the support target vehicle, perform, on the support target vehicle, a vehicle support for suppressing performing of the unstable behavior at the unstable behavior position.