A master control device is communicatively coupled to a first slave control device and a second slave control device via a first network and a second network, respectively. The master control device provides output data to the first slave control device based on input data received from the second slave control device. A monitoring apparatus which monitors an operation of the master control device stores determination data indicating a correspondence relationship between the input data and the output data, obtains the input data provided to the second network by the second slave control device and the output data provided to the first slave control device via the first network, and determines a presence or an absence of an anomaly in the operation of the master control device by determining whether the input data and the output data correspond to the determination data.

A controller causes a calculation device to perform calculation that determines an operation of a moving object and generates digital signals that define the operations of actuators. The generated digital signals are output to a digital signal transmission path by a signal bus control IC. ICs attached to the actuators obtain digital signals that define the operations of the actuators from the digital signal transmission path and generate control signals for the actuators based on the operations defined by the digital signals.

An example operation includes one or more of determining, by a server, an event associated with a transport, receiving, by the server, atypical data related to the transport from a plurality of devices over various times prior to the event, analyzing, by the server, the atypical data, forming, by the server, a consensus based on the analyzed atypical data to determine a severity of the event, and determining, by the server, an action to take based on the severity.

Embodiments herein can determine an optimal route for an autonomous electric vehicle. The system may score viable routes between the start and end locations of a trip using a numeric or other scale that denotes how viable the route is for autonomy. The score is adjusted using a variety of factors where a learning process leverages both offline and online data. The scored routes are not based simply on the shortest distance between the start and end points but determine the best route based on the driving context for the vehicle and the user.

Embodiments herein relate to an autonomous vehicle or self-driving vehicle. The system can determine a collision avoidance path by: 1) predicting the behavior/trajectory of other moving objects (and identifying stationary objects); 2) given the driving trajectory (issued by autonomous driving system) or predicted driving trajectory (human), establishing the probability for a collision that can be calculated between the vehicle and one or more objects; and 3) finding a path to minimize the collision probability.

A method for controlling a longitudinal position of a vehicle involves a longitudinal positioning control system generating a longitudinal acceleration control signal from a longitudinal dynamic feedforward set point and from longitudinal dynamic control error quantities for a subordinate acceleration control unit acting on a drive device and braking device of the vehicle. A current control reference point corresponding to a current time point and at least one forward control reference point corresponding to a presettable look-ahead time point are determined as control-relevant time points, current or predicted actual/required deviations of a longitudinal position, of a driving speed and of acceleration are determined for each of the control reference points and provide the basis for forming the longitudinal dynamic control error quantities, and required values of an acceleration are determined for each of the control reference points and provide the basis for forming the longitudinal dynamic feedforward set point.

Embodiments herein can determine an optimal route for an autonomous electric vehicle. The system may score viable routes between the start and end locations of a trip using a numeric or other scale that denotes how viable the route is for autonomy. The score is adjusted using a variety of factors where a learning process leverages both offline and online data. The scored routes are not based simply on the shortest distance between the start and end points but determine the best route based on the driving context for the vehicle and the user.

In one embodiment, a system determines a difference in time between a local time source and a time of a GPS sensor. The system determines a max limit in difference and a max recovery increment or max recovery time interval for a smooth time source recovery. The system determines that the difference between the local time source and a time of the GPS sensor to be less than the max limit. The system plans a smooth recovery of the time source to converge the local time source to a time of the GPS sensor within the max recovery time interval. The system generates a timestamp based on the recovered time source to timestamp sensor data for a sensor unit of the ADV.

A method for providing a dynamic adaptive deep learning model other than a fixed deep learning model, to thereby support at least one specific autonomous vehicle to perform a proper autonomous driving according to surrounding circumstances is provided. And the method includes steps of: (a) a managing device which interworks with autonomous vehicles instructing a fine-tuning system to acquire a specific deep learning model to be updated; (b) the managing device inputting video data and its corresponding labeled data to the fine-tuning system as training data, to thereby update the specific deep learning model; and (c) the managing device instructing an automatic updating system to transmit the updated specific deep learning model to the specific autonomous vehicle, to thereby support the specific autonomous vehicle to perform the autonomous driving by using the updated specific deep learning model other than a legacy deep learning model.

A learning method for supporting a safer autonomous driving through a fusion of information acquired from images and communications is provided. And the method includes steps of: (a) a learning device instructing a first neural network and a second neural network to generate an image-based feature map and a communication-based feature map by using a circumstance image and circumstance communication information; (b) the learning device instructing a third neural network to apply a third neural network operation to the image-based feature map and the communication-based feature map to generate an integrated feature map; (c) the learning device instructing a fourth neural network to apply a fourth neural network operation to the integrated feature map to generate estimated surrounding motion information; and (d) the learning device instructing a first loss layer to train parameters of the first to the fourth neural networks.