A determining method for determining a state of a road surface includes: sequentially acquiring a rotational speed of tires mounted on the vehicle, sequentially acquiring a driving force of the vehicle, calculating a slip ratio based on the sequentially acquired rotational speed of the tires, calculating a regression equation and a confidence interval width for a relationship between the slip ratio and the driving force, based on data sets of the slip ratio and the driving force in a predetermined zone, and determining a state of the road surface on which the vehicle travels, based on the confidence interval width calculated for the predetermined zone.

The systems and methods described herein disclose detecting obstacles in a vehicular environment using host vehicle input and associated trust levels. As described here, measured vehicles, either manual or autonomous, that detect an obstacle in the environment will operate to respond to the obstacle. As such, those movements can be used to determine if an obstacle exists in the environment, even if the obstacle cannot be detected directly. The systems and methods can include a host vehicle receiving prediction data about an evasive behavior from one or more measured vehicles in a vehicular environment. A trust level can then be established for the measured vehicles. An obscured obstacle can be determined using the evasive behavior and the trust level which can then be mapped in the vehicular environment. A guidance input can then be created for the host vehicle using the obscured obstacle and the trust level.

Methods relating to the control of autonomous vehicles using a reinforcement learning agent include a plurality of training sessions, in which the agent interacts with an environment, each having a different initial value and yielding a state-action quantile function dependent on state and action. The methods further include a first uncertainty estimation on the basis of a variability measure, relating to a variability with respect to quantile τ, of an average of the plurality of state-action quantile functions evaluated for a state-action pair; and a second uncertainty estimation on the basis of a variability measure, relating to an ensemble variability, for the plurality of state-action quantile functions evaluated for a state-action pair.

Disclosed are methods, systems, and non-transitory computer readable media that control an autonomous vehicle via at least two sensors. One aspect includes capturing an image of a scene ahead of the vehicle with a first sensor, identifying an object in the scene at a confidence level based on the image, determining the confidence level of the identifying is below a threshold, in response to the confidence level being below the threshold, directing a second sensor having a field of view smaller than the first sensor to generate a second image including a location of the identified object, further identifying the object in the scene based on the second image, controlling the vehicle based on the further identification of the object.

Provided is a preceding vehicle determining device including: a signal acquisition unit configured to acquire a signal from an object detection device; a border setting unit configured to set a border of a lane on which the own vehicle is traveling; a determination area setting unit configured to set a preceding vehicle determination area being an area forward of the own vehicle based on at least one piece of information out of vehicle type information, device type information, detection state information, or preceding vehicle information being information on a vehicle set as a preceding vehicle in previous processing, and based on the border set by the border setting unit; and a preceding vehicle determining unit configured to determine whether the another vehicle is to be set as the preceding vehicle based on a position of the another vehicle with respect to the preceding vehicle determination area.

A vehicle may determine that erratic vehicle behavior has been sensed, based on comparison of a sensed vehicle behavioral characteristic at a given location compared to a predefined expected value of the characteristic. The vehicle may further determine whether an environmental anomaly has been detected in association with the given location and classify the sensed erratic behavior based on whether the environmental anomaly was detected. Responsive to classifying the behavior as erratic based on determining no environmental anomaly was detected, the vehicle may report the erratic behavior to a remote server, along with the given location. The remote server may receive a plurality of such reports for a given location and update a classification of the behavior based on data indicated in the plurality of reports.

A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.

The techniques discussed herein may comprise an autonomous vehicle guidance system that generates a path for controlling an autonomous vehicle based at least in part on a static object map and/or one or more dynamic object maps. The guidance system may identify a path based at least in part on determining set of nodes and a cost map associated with the static and/or dynamic object, among other costs, pruning the set of nodes, and creating further nodes from the remaining nodes until a computational or other limit is reached. The path output by the techniques may be associated with a cheapest node of the sets of nodes that were generated.

A method for preventing a collision between a motor vehicle and at least one target object, the motor vehicle includes a detection system capable of detecting the target object and a warning system including at least one light module. The method includes detecting the target object and determining a position and a speed of the target object using the detection system. The method further includes estimating a critical trajectory likely to be followed by the target object in order to collide with the vehicle depending on the position and the speed of the target object, the critical trajectory being associated with a collision risk/collision time relationship. The method additional includes transmitting at least one light warning to the driver of the vehicle using the light module of the warning system.

Techniques relating to monitoring map consistency are described. In an example, a monitoring component associated with a vehicle can receive sensor data associated with an environment in which the vehicle is positioned. The monitoring component can generate, based at least in part on the sensor data, an estimated map of the environment, wherein the estimated map is encoded with policy information for driving within the environment. The monitoring component can then compare first information associated with a stored map of the environment with second information associated with the estimated map to determine whether the estimated map and the stored map are consistent. Component(s) associated with the vehicle can then control the object based at least in part on results of the comparing.