Method and apparatus for controlling vehicle based on UWB
A method and apparatus of controlling a vehicle based on UWB includes receiving from at least one UWB tag, tag data which is data about a target object carrying the UWB tag; positioning for extracting dynamic information of the UWB tag using location information of a subject vehicle and the tag data; determining a collision risk of the subject vehicle with the target object based on the extracted dynamic information; and controlling, at least one electronic control unit (ECU) included in the subject vehicle depending on the collision risk.
1 . A method of controlling a vehicle based on ultra-wideband (UWB) performed by a vehicle control apparatus, the method comprising:
receiving from at least one UWB tag, tag data which is data about a target object carrying the at least one UWB tag;
extracting dynamic information of the at least one UWB tag using location information of a subject vehicle and the tag data;
determining a collision risk of the subject vehicle with the target object based on the extracted dynamic information; and
controlling at least one electronic control unit (ECU) included in the subject vehicle based on comparing the collision risk with a preset first probability and a preset second probability,
wherein the controlling includes determining whether collision of the subject vehicle with the target object is avoidable when the collision risk is greater than or equal to the preset second probability and less than or equal to the preset first probability,
wherein the extracting includes:
searching for shortest paths between pairs of nodes on a data structure having recognized UWB tags and a plurality of UWB modules of the subject vehicle as nodes;
determining weights for distances between the nodes corresponding to the shortest paths; and
estimating 3D coordinates of the at least one UWB tag based on the distances between the nodes and the weights,
wherein the plurality of UWB modules are adjacent to the recognized UWB tags, and
wherein the pairs of nodes are determined as pairs corresponding to shortest paths between the recognized UWB tags and the plurality of UWB modules, and between the plurality of UWB modules.
2 . The method of claim 1 , wherein the controlling includes:
determining whether an instantaneous change rate of estimated acceleration of the at least one UWB tag during a preset tracking time is equal to or greater than a predetermined reference change rate when the collision risk is less than the preset second probability.
3 . The method of claim 1 , wherein the controlling includes:
controlling a display to provide a warning notification to a driver of the subject vehicle when the collision risk is greater than or equal to the preset first probability;
controlling an electronic control suspension and an electronic brake until the subject vehicle stops; and
turning off an automatic control function of an electronic power steering.
4 . The method of claim 3 , wherein the determining the collision risk of the subject vehicle further includes:
detecting the target object using a plurality of sensors included in the subject vehicle; and
determining the collision risk based on a distance between the subject vehicle and the target object.
5 . The method of claim 1 , wherein, when the collision with the target object is unavoidable, the controlling includes:
detecting an object existing in an area adjacent to the target object using a camera included in the subject vehicle;
controlling steering of the subject vehicle toward a safe area in which no object is detected in the area adjacent to the target object; and
controlling an electronic control suspension and an electronic brake until the subject vehicle stops.
6 . The method of claim 1 , wherein when the collision with the target object is avoidable, the controlling includes:
controlling at least one of an engine control unit, an electronic power steering, an electronic control suspension, an electronic brake, or a display.
7 . The method of claim 1 , further including:
generating an input dataset including tag information and sensor information of the subject vehicle; and
estimating the collision risk by inputting the input dataset into a pre-trained collision risk estimation model.
8 . A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the method of claim 1 .
9 . An apparatus for controlling a vehicle based on ultra-wideband (UWB), the apparatus comprising:
a memory; and
a plurality of processors,
wherein at least one processor of the plurality of processors is configured to:
receive, from at least one UWB tag, tag data which is data about a target object carrying the at least one UWB tag;
extract dynamic information of the at least one UWB tag using location information of a subject vehicle and the tag data;
determine a collision risk of the subject vehicle with the target object based on the extracted dynamic information; and
control at least one electronic control unit (ECU) included in the subject vehicle based on comparing the collision risk with a preset first probability and a preset second probability,
wherein the at least one processor is further configured to determine whether collision of the subject vehicle with the target object is avoidable when the collision risk is greater than or equal to the preset second probability and less than or equal to the preset first probability,
wherein the at least one processor is further configured to:
search for shortest paths between pairs of nodes on a data structure having recognized UWB tags and a plurality of UWB modules of the subject vehicle as nodes;
determine weights for distances between the nodes corresponding to the shortest paths; and
estimate 3D coordinates of the at least one UWB tag based on the distances between the nodes and the weights,
wherein the plurality of UWB modules are adjacent to the recognized UWB tags, and
wherein the pairs of nodes are determined as pairs corresponding to shortest paths between the recognized UWB tags and the plurality of UWB modules, and between the plurality of UWB modules.
10 . The apparatus of claim 9 , wherein the at least one processor is further configured to:
determine whether an instantaneous change rate of estimated acceleration of the at least one UWB tag during a preset tracking time is equal to or greater than a predetermined reference change rate when the collision risk is less than the preset second probability.
11 . The apparatus of claim 9 , wherein the at least one processor is further configured to:
control a display to provide a warning notification to a driver of the subject vehicle when the collision risk is greater than or equal to the preset first probability;
control an electronic control suspension and an electronic brake until the subject vehicle stops; and
turn off an automatic control function of an electronic power steering.
12 . The apparatus of claim 11 , wherein at least one processor is further configured to:
detect the target object using a plurality of sensors included in the subject vehicle; and
determine the collision risk based on a distance between the subject vehicle and the target object.
13 . The apparatus of claim 9 , wherein, when the collision with the target object is unavoidable, the at least one processor is further configured to:
detect an object existing in an area adjacent to the target object using a camera included in the subject vehicle;
control steering of the subject vehicle toward a safe area in which no object is detected in the area adjacent to the target object; and
control an electronic control suspension and an electronic brake until the subject vehicle stops.
14 . The apparatus of claim 9 , wherein when the collision with the target object is avoidable, the at least one processor is further configured to:
control at least one of an engine control unit, an electronic power steering, an electronic control suspension, an electronic brake, or a display.
15 . The apparatus of claim 9 , wherein the at least one processor is further configured to:
generate an input dataset including tag information and sensor information of the subject vehicle; and
estimate the collision risk by inputting the input dataset into a pre-trained collision risk estimation model.