A vehicle configured to operate in an autonomous mode can obtain sensor data from one or more sensors observing one or more aspects of an environment of the vehicle. At least one aspect of the environment of the vehicle that is not observed by the one or more sensors could be inferred based on the sensor data. The vehicle could be controlled in the autonomous mode based on the at least one inferred aspect of the environment of the vehicle.

A vehicle configured to operate in an autonomous mode can obtain sensor data from one or more sensors observing one or more aspects of an environment of the vehicle. At least one aspect of the environment of the vehicle that is not observed by the one or more sensors could be inferred based on the sensor data. The vehicle could be controlled in the autonomous mode based on the at least one inferred aspect of the environment of the vehicle.

A computer-implemented method and a system are provided for, in turn, providing driver assistance for a vehicle. The method includes forming, by a processor, a deep High-Order Long Short-Term Memory (HOLSTM)-based model by applying, to a HOLSTM, high-order interactions captured between global pattern distribution probabilities and local feature representations of an input sensor signal vector at each of a plurality of time steps. The input sensor signal vector is formed from multiple time series. Each of the multiple time series corresponds to a different one of a plurality of driving related sensors. The method further includes generating, by the processor, one or more predictions of impending dangerous conditions related to driving the vehicle based on the deep HOLSTM-based model. The method also includes informing, by an operator-perceptable warning device, an operator of the vehicle of the one or more predictions of impending dangerous conditions.

An action probability factor is developed based at least in part on a plurality of probability arrays predicting one or more probabilities of a deviation from at least one of a planned vehicle direction, position, speed, and acceleration. Levels of autonomous control are transitioned based at least in part on the action probability factor.

Methods and devices for using a relationship between activities of different traffic signals in a network to improve traffic signal state estimation are disclosed. An example method includes determining that a vehicle is approaching an upcoming traffic signal. The method may further include determining a state of one or more traffic signals other than the upcoming traffic signal. Additionally, the method may also include determining an estimate of a state of the upcoming traffic signal based on a relationship between the state of the one or more traffic signals other than the upcoming traffic signal and the state of the upcoming traffic signal.

Methods and devices for using a relationship between activities of different traffic signals in a network to improve traffic signal state estimation are disclosed. An example method includes determining that a vehicle is approaching an upcoming traffic signal. The method may further include determining a state of one or more traffic signals other than the upcoming traffic signal. Additionally, the method may also include determining an estimate of a state of the upcoming traffic signal based on a relationship between the state of the one or more traffic signals other than the upcoming traffic signal and the state of the upcoming traffic signal.

A method for detecting a situation of loss of grip of a vehicle provided with a steering system operated by a steering wheel, said method being in that it comprises a step (a) of evaluating a first indicator of loss of grip (P1) comprising calculating, as the first indicator of loss of grip (P1), the partial derivative

[00001]$\left(P.Math..Math.1=\frac{\partial \stackrel{.}{\psi }}{\partial \alpha }\right),$

relative to a variable (α) representative of the angular position of the steering wheel, of a driving parameter which is representative of the yaw rate ({dot over (ψ)}) of the vehicle.

Methods and systems are provided for controlling a component of a vehicle. In one embodiment, a method includes: receiving sensor data sensed from the vehicle; processing the sensor data to determine an ideal state of the vehicle; processing the sensor data and the ideal state of the vehicle to determine a feasible state of the vehicle; and selectively controlling at least one component associated with at least one of an active safety system and a chassis system of the vehicle based on the at least one feasible state.

There are provided an apparatus, a method, and an autonomous moving body which allow a recognition target to be notified with certainty that the recognition target is recognized by an autonomous moving body. A recognition result presenting apparatus according to an embodiment of the present disclosure detects a recognition target (person) present within a predetermined range from an automatic driving vehicle and presents, to the detected recognition target (person), the result of recognition indicating that the automatic driving vehicle recognizes the recognition target (person).

A hybrid vehicle includes an electronic control unit that executes first discharge control in a state where an engine is stopped in the case where a collision detector detects a collision of the hybrid vehicle. The first discharge control includes bringing all switching elements on either one of an upper arm side and a lower arm side of either one of a first inverter and a second inverter into ON states; bringing another inverter into a gate blocking state; and discharging electric charges of a capacitor by using a discharge device until a voltage of the capacitor becomes lower than a threshold.