8results about "Traffic control systems" patented technology

The invention relates to air route quantitative evaluation, in particular to an unmanned aerial vehicle air route dynamic quantitative evaluation method based on comprehensive risk avoidance, and the method comprises the steps: constructing a multi-dimensional air route risk quantitative evaluation system, and enabling each dimension to comprise a plurality of specific and quantifiable risk evaluation factors; mapping the observation value of each risk assessment factor into a standardized risk score; determining the weight of each risk assessment factor according to a dynamic weight adjustment strategy, and calculating a route comprehensive risk score by combining the standardized risk score of each risk assessment factor; executing the evaluation process on all the candidate paths, calculating an air route comprehensive risk score for each candidate path, preferentially recommending the candidate path with the highest air route comprehensive risk score, and generating an air route risk evaluation report at the same time; according to the technical scheme provided by the invention, the defect that accurate dynamic quantitative evaluation of the route of the unmanned aerial vehicle is difficult in the prior art can be effectively overcome.

The invention discloses a space target long-time-sequence intelligent collision early warning method, and belongs to the technical field of space. The implementation method comprises the steps of constructing a double-branch multi-scale time convolution network long-time-sequence orbit forecasting model, and on the basis of a traditional time convolution network, establishing a relation between the model and perturbation of different time scales by establishing two branch expansion convolution structures and setting different expansion coefficients, so that the forecasting precision of the model is improved. On the basis, a voxel hash mapping rapid screening method is established, a Gaussian negative logarithm likelihood loss function is introduced, statistical characteristics of forecast errors are utilized, a voxel cube is constructed, only voxels where satellites are located and the distance between targets in neighborhoods of the voxels and the satellites need to be calculated during screening, the screening calculation scale is greatly reduced, and the screening speed is increased. The method does not depend on a high-precision dynamic model, can sense and extract the features of different time scales, improves the track forecasting precision and the collision risk screening efficiency, and accelerates the collision early warning speed.

A method includes identifying a route for passengers seeking to enter a building. The route includes at least one section of road for automobiles to access a building; or at least one access point inside the building for pedestrians to pass through. The method includes receiving traffic flow information corresponding to the route. The method includes determining whether the received traffic flow information corresponds to a condition that impedes the route, from among a set of pre-trained conditions. The method includes identifying and displaying a list of user-selectable state alternatives related to the condition that impedes the route, based on a determination that the received traffic flow information corresponds to the condition.

A vehicle control system and method may receive state information from a vehicle group having one or more vehicles. The state information may indicate an operational parameter of one of the vehicles. The controller may direct a display device to present one or more statuses of the one or more vehicles based at least in part on the state information that is received by the controller. This state information may be used to notify an operator of a potential component fault before continued operation of the vehicle group further damages the component or a vehicle. In another example, the state information may be used to control or change operation of one vehicle based on the state or status of another vehicle, such as by changing movement of one or more drones in a swarm responsive to a lower state of charge of another drone in the same swarm.

This invention discloses a large-scale space target collision early warning combination screening method, belonging to the field of space situational awareness. The implementation method is as follows: Preliminary screening of similar targets is performed based on the distance between intersection points on the orbital plane intersection line to quickly reduce the number of satellite combinations to be analyzed; by decomposing the analytical solution considering the minimum relative distance between satellites under J2 perturbation, it is divided into long-term terms and exact solutions; based on the evolution characteristics of the long-term terms, a second screening is performed using the trend characteristics of the long-term terms; a third screening is performed using the analytical exact solution considering the relative distance between satellites under J2 perturbation; based on the results of the third screening, satellite combinations with collision risk are determined, realizing large-scale space target collision early warning combination screening, thereby protecting the safety of space assets. This invention fully considers the long-term evolution characteristics of orbits under perturbation, significantly reducing the calculation time for early warning, and is suitable for rapid screening of long-term collision early warnings for large-scale space targets.

To provide a group control system and a group control method that allow machine learning by taking acceleration and deceleration data into account and group controlling based on correct position information.SOLUTION: A group control system controls a plurality of moving objects 10 that are capable of traveling autonomously within a predetermined area. The group control system includes a position information estimation unit 101 that estimates position information of each moving object, a route planning unit 102 that creates a route plan for each moving object based on the estimated position information, an acceleration data acquisition unit that acquires acceleration data acquired from an acceleration sensor 11, and a moving object position acquisition unit that acquires an actual position of each moving object using a position sensor. A deep reinforcement learning model is trained so as to correct the amount of deviation between the actual position of the moving body obtained using the position sensor and the estimated position of the moving body based on the obtained acceleration data.SELECTED DRAWING: Figure 4

Method for detecting track anomalies and associated device This method (100) includes, in configuration, the steps of: training a neural network (110) on training tracks to predict a log-likelihood value of a data track; calculation (120) of an average log-likelihood value for validation tracks and calculation (125) of a median; calculation (130) of a score on the average log-likelihood value of test tracks with respect to the median and calculation (135) of a statistical coefficient; definition (140) of an anomaly threshold from the median and the statistical coefficient.The process includes, in inference, the steps of: acquiring (150) at least one lead of interest; processing (160) the lead of interest by: calculating a mean log-likelihood value of the lead of interest; calculating a score of the mean log-likelihood value of the lead of interest relative to the median; and comparing the score of the mean log-likelihood value of the lead of interest to the abnormality threshold, the lead of interest being "abnormal" when the score of the mean log-likelihood value of the lead of interest is greater than the abnormality threshold, and "normal" otherwise. Figure for the abstract: Figure 3.

An emergency driving situation control apparatus using a brain wave signal includes a sensor configured to collect a brain wave signal for at least one passenger of a mobility in a predetermined channel region, an analyzer configured to determine, by analyzing the brain wave signal collected in the predetermined region, whether or not an emergency situation has occurred to the mobility, and a controller configured to control an operation of the mobility based on a result of the determination.