Systems and methods of determining a risk distribution associated with a multiplicity of coverage zones covered by a multiplicity of sensors of an autonomous driving vehicle (ADV) are disclosed. The method includes for each coverage zone covered by at least one sensor of the ADV, obtaining MTBF data of the sensor(s) covering the coverage zone. The method further includes determining a mean time between failure (MTBF) of the coverage zone based on the MTBF data of the sensor(s). The method further includes computing a performance risk associated with the coverage zone based on the determined MTBF of the coverage zone. The method further includes determining a risk distribution based on the computed performance risks associated with the multiplicity of coverage zones.

A computer implemented method for scenario generation for autonomous vehicle navigation that can include defining a cellular automaton layer that defines a road network level behavior with at least one rule directed to pathways by vehicles on a passageway for travel. The method may further include defining an active matter layer that defines a vehicle level behavior with at least one rule directed to movement of the vehicles on an ideal route for the pathways; and defining a driver agent layer that defines driving nature with at least one rule that impacts changes in the vehicle level behavior dependent upon a characterization of driver behavior. The method may further include combining outputs from the different layer to provide scenario generations for autonomous vehicle navigation. The combining of the outputs can utilize a pseudo random value to determine at an order in the execution and duration of execution for the layers.

A method is disclosed for evaluating a classifier used to determine a traffic light signal state in images. The method includes, by a computer vision system of a vehicle, receiving at least one image of a traffic signal device of an imminent intersection. The traffic signal device includes a traffic signal face including one or more traffic signal elements. The method includes classifying, by a traffic light classifier (TLC), a classification state of the traffic signal face using labeled images correlated to the received at least one image. The classification state controls an operation of the vehicle at the intersection. The method includes evaluating a performance of the classifying of the classification state generated by the TLC. The evaluation is a label-free performance evaluation based on unlabeled images. The method includes training the TLC based on the evaluated performance.

An autonomous vehicle (AV) includes features that allows the AV to comply with applicable regulations and statues for performing safe driving operation. Example embodiments disclosed herein provide enhanced high-precision operation of an AV in low-speed environments, such as a toll booth facility or heavy traffic. One example method disclosed herein includes a control computer identifying a starting point of the toll booth facility on the roadway and a plurality of toll lanes associated with the toll booth facility; selecting a particular toll lane; determining a trajectory for the AV that extends through the particular toll lane; and in response to the autonomous vehicle arriving at the starting point for the toll booth facility, transmitting, over a subsystem interface to one or more drive subsystems of the AV, instructions configured to cause the drive subsystems to operate together to cause the AV to travel according to the trajectory.

A method, device, and system for managing a micro mobility device are disclosed. The method includes obtaining access location information of a movable carrier for returning the micro mobility device and checking whether or not it is possible to return the micro mobility device to the movable carrier, based on use information of the micro mobility device and the access location information The method includes performing maintenance for the micro mobility device that is returned, when it is possible to return the micro mobility device to the movable carrier and it is confirmed, based on the use information and maintenance support information of the movable carrier, that maintenance of the micro mobility device is capable of being performed by the movable carrier.

A location of a first object can be determined in an image. A line can be drawn on the first image based on the location of the first object. A deep neural network can be trained to determine a relative location between the first object in the image and a second object in the image based on the line. The deep neural network can be optimized by determining a fitness score that divides a number of deep neural network parameters by a performance score. The deep neural network can be output.

A vehicle transport planning device includes a transport proposal unit that proposes, to an occupant of a vehicle equipped with an internal combustion engine, transport of the vehicle in a predetermined area where driving of the internal combustion engine is prohibited or restricted, and a transport arrangement unit that requests arrangement of a vehicle transport device for transporting the vehicle when the occupant desires the transport of the vehicle.

Systems and methods are directed to an autonomy computing system of an autonomous vehicle. The autonomy computing system can include first functional circuitry configured to generate a first output associated with a first autonomous compute function of the autonomous vehicle based on sensor data using first neural networks. The autonomy computing system can include second functional circuitry configured to generate a second output associated with the first autonomous compute function of the autonomous vehicle based on the sensor data and neural networks. The autonomy computing system can include monitoring circuitry configured to determine a difference between the first output of the first functional circuitry and the second output of the second functional circuitry. The autonomy computing system can include a vehicle control system configured to generate vehicle control signals for the autonomous vehicle based on the outputs.

Disclosed here are methods and systems for automatically operating automated vehicles moving through vegetation obstacles with minimal damage, comprising receiving image(s) depicting vegetation obstacle(s) blocking at least partially a path of an automated vehicle executing a mission, analyzing the image(s) to extract one or more obstacle attributes of the vegetation obstacle(s), computing a plurality of movement patterns for operating the automated to cross the vegetation obstacle(s) based on one or more vehicle attributes of the automated vehicle with respect to one or more of the obstacle attributes where each movement pattern defines one or more movement parameters of the automated vehicle, selecting one of the movement patterns estimated to reduce a cost of damage to the automated vehicle and/or to the one or more vegetation obstacles, and outputting instructions for operating the automated vehicle to move through the vegetation obstacle(s) according to the selected movement pattern.

An automatic parking system instructs a plurality of autonomous driving vehicles in a parking lot such that each autonomous driving vehicle parks in a target parking space within the parking lot, and includes an instruction change target vehicle specifying unit configured to, in a case where the autonomous driving vehicle becomes a failed vehicle due to abnormality or communication interruption during automatic driving according to instruction, specify an instruction change target vehicle from normal autonomous driving vehicles based on parking lot map information, a location of the failed vehicle, and a location of the normal autonomous driving vehicles, and a vehicle instruction unit configured to, in a case where the instruction change target vehicle is specified, issue a route change instruction, an evacuation instruction, or a stop instruction to the instruction change target vehicle, such that the instruction change target vehicle gets away from the failed vehicle.