Method and system for narrow passage path sampling based on levy flight is disclosed. The disclosed technique is an improvisation of Random Walk to Surface (RWS), wherein, instead of performing a random walk, the disclosed technique utilizes levy flight mechanism to identify samples in narrow passages (on the obstacle boundaries). The disclosed technique for identification of narrow passages sampling points in the narrow passage is based on several techniques that include random uniform sampling technique, a levy flight function (step size) and a collision detection technique. Moreover, in addition to identification of narrow passages sampling points, the disclosed technique also performs an additional check to ensure that the identified narrow passages sampling points are present in the narrow passage based on a levy flight bridge sampler technique.

An apparatus and method for a mobile transport for delivering temperature-controlled contents includes a plurality of compartments coupled to a vehicle body where each compartment includes an interior space and a front panel defining a wall of the interior space. Each front panel is operable to open and reveal the interior space of its compartment in response to a predetermined condition. A temperature controller is configured to individually control a temperature setting within at least one of the plurality of compartments, and a germicidal controller is configured to provide a germicide to the interior space of each of the plurality of compartments. In operation, the mobile transport receives an order signal to pick up an item from a source, the order signal including the pickup location information, customer identification information, and delivery location information. After the item has been placed in the interior space of a compartment, the temperature controller sets the temperature setting for that compartment according to a type of the item. After arriving at the delivery location, the front panel of the compartment is opened in response to receiving an open request signal satisfying the predetermined condition, the open request signal including information relating to the customer identification information.

The present invention relates to a computer-implemented method and a system for testing the output of a neural network (1) having a plurality of layers (11), which detects or classifies objects. The method comprises the step (S1) of reading at least one result from at least one first layer (11) and the confidence value thereof, which is generated in the first layer (11) of a neural network (1), and the step (S2) of checking a plausibility of the result by taking into consideration the confidence value thereof so as to conclude whether the object detection by the neural network (1) is correct or false. The step (S2) of checking comprises comparing the confidence value for the result with a predefined threshold value. In the event that it is concluded in the checking step (S2) that the object detection is false, output of the object falsely detected by the neural network is prevented.

Provided is a determination device capable of safely and reliably causing a vehicle on a side road to enter and merge into a main road when merging into the main road. Information is acquired that indicates the vehicle status of vehicles CA, etc., and vehicles Ca, etc., that are traveling on a side road SR that merges with a main road MR on which the vehicles CA, etc., are traveling. When, on the basis of said information, an intervehicular space is to be formed between the vehicles CA, etc., that will make it possible for a vehicle Ca, etc., to enter, the vehicles CA, etc., are caused to form an interval on the basis of the acceleration applied to each of the vehicles CA, etc., and the entering vehicle Ca, etc., is allowed to move to a position in the intervehicular space.

A route guidance apparatus includes: a reservation information communications unit to receive reservation information which includes at least one of a parking-reserved space of the parking lot, a vehicle type, a vehicle number, and a parking time; a reserved vehicle recognition unit to recognize a vehicle number of a reserved vehicle and determine whether the reserved vehicle enters or exits the parking lot; a traffic flow determination unit that divides an area of each floor of the parking lot into a plurality of unit areas and calculates density within the parking lot based on the number of vehicles within each divided unit area; and a parking route generation unit and an exit route generation unit that respectively generate an optimal parking route and an optimal exit route based on the calculated density; and a route guidance unit to provide the user with the generated optimal parking and exit routes.

A method is for training an object detector configured to detect objects in sensor data of a sensor. The method includes providing first sensor data of the sensor, providing an object representation assigned to the first sensor data, and transmitting the object representation to a sensor model. The method further includes imaging object representations onto the first sensor data of the sensor with the sensor model, assigning the object representation to second sensor data with the sensor model, and training the object detector based on the second sensor data.

Path generation apparatus configured to generate target path of own vehicle traveling in own lane, includes: sensor configured to detect objects in surrounding area of own vehicle; and electronic control unit including processor and memory. Electronic control unit is configured to perform: recognizing adjacent vehicle traveling in adjacent lane adjacent to own lane from among detected objects; determining whether own lane is congested based on travel speed of own vehicle and determining whether adjacent lane is congested based on recognition result of adjacent lane; and generating target path of own vehicle. Generating target path includes generating target path on side away from adjacent lane with respect to that of case where own lane is determined to be congested and adjacent lane is determined to be congested, in case where own lane is determined to be congested and adjacent lane is determined not to be congested.

Path generation apparatus configured to generate target path of own vehicle, includes: sensor configured to detect objects in forward area of own vehicle; and electronic control unit including processor and memory coupled to processor. Electronic control unit is configured to perform: recognizing adjacent vehicle traveling in adjacent lane adjacent to travel lane in which own vehicle travels from among objects detected by sensor; generating reference path of own vehicle in travel lane; setting safe area from side end portion of adjacent vehicle toward travel lane; and generating target path of own vehicle based on reference path. Generating target path includes: setting reference path to target path in predetermined section on forward side of own vehicle; and modifying reference path to ensure safe area between own vehicle and adjacent vehicle on forward side of predetermined section to generate target path.

A control device mounted on a mobile object acquires surrounding situation information indicating a surrounding situation of a mobile object recognized by an object recognition device mounted on the mobile object, detects a predetermined reference object present in a traveling direction of the mobile object on the basis of the surrounding situation information, identifies a travelable area of the mobile object on the basis of the surrounding situation information, controls traveling of the mobile object such that the mobile object travels in the travelable area, causes the mobile object to move closer to the reference object when the reference object is detected, and detects an accompanying object accompanying the reference object on the basis of the surrounding situation information recognized by the object recognition device after the mobile object moves closer to the reference object, and identifying the travelable area by excluding the reference object and the accompanying object.

A driving assist method minimizes an incidence of lane changing within a circulatory roadway. In this driving assist method, a recognition assessment processor assesses the travel of a host vehicle, calculates a travel route over which the host vehicle is to travel, and executes a driving assist control based on the travel route. The recognition assessment processor further assesses whether the host vehicle has arrived at a roundabout having a circulatory roadway to which three or more radial roadways are connected. When an assessment has been made that the host vehicle has arrived at the roundabout, a position of a host vehicle entrance and a position of a host vehicle exit are specified. Furthermore, an entrance position is set based on a positional relationship between the host vehicle entrance and the host vehicle exit.