Classifications

• • G—PHYSICS
  • G08—SIGNALLING
  • G08G—TRAFFIC CONTROL SYSTEMS
  • G08G1/00—Traffic control systems for road vehicles
  • G08G1/16—Anti-collision systems
  • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
• • G—PHYSICS
  • G08—SIGNALLING
  • G08G—TRAFFIC CONTROL SYSTEMS
  • G08G1/00—Traffic control systems for road vehicles
  • G08G1/16—Anti-collision systems
  • G08G1/164—Centralised systems, e.g. external to vehicles
• • G—PHYSICS
  • G01—MEASURING; TESTING
  • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
  • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
  • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
  • G01C21/3804—Creation or updating of map data
  • G01C21/3807—Creation or updating of map data characterised by the type of data
  • G01C21/3815—Road data
• • G—PHYSICS
  • G08—SIGNALLING
  • G08G—TRAFFIC CONTROL SYSTEMS
  • G08G1/00—Traffic control systems for road vehicles
  • G08G1/01—Detecting movement of traffic to be counted or controlled
  • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
  • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
  • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
• • G—PHYSICS
  • G08—SIGNALLING
  • G08G—TRAFFIC CONTROL SYSTEMS
  • G08G1/00—Traffic control systems for road vehicles
  • G08G1/01—Detecting movement of traffic to be counted or controlled
  • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
  • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
  • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
• • G—PHYSICS
  • G08—SIGNALLING
  • G08G—TRAFFIC CONTROL SYSTEMS
  • G08G1/00—Traffic control systems for road vehicles
  • G08G1/01—Detecting movement of traffic to be counted or controlled
  • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
  • G08G1/0125—Traffic data processing
  • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
• • G—PHYSICS
  • G08—SIGNALLING
  • G08G—TRAFFIC CONTROL SYSTEMS
  • G08G1/00—Traffic control systems for road vehicles
  • G08G1/01—Detecting movement of traffic to be counted or controlled
  • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
  • G08G1/0125—Traffic data processing
  • G08G1/0133—Traffic data processing for classifying traffic situation
• • G—PHYSICS
  • G08—SIGNALLING
  • G08G—TRAFFIC CONTROL SYSTEMS
  • G08G1/00—Traffic control systems for road vehicles
  • G08G1/09—Arrangements for giving variable traffic instructions
  • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
  • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
  • G08G1/0969—Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map

Definitions

• the invention relates to a method for creating a map with collision probabilities for an area.
• the invention relates to a method for creating a map with collision probabilities for an area, the method having the following steps:
• Collision probabilities are created, which is based on actually recorded movement data and which can also be based on calculation models, which are used anyway for vehicle control, for example.
• calculation models are typically not executed by the respective vehicles, but by an infrastructure which, for example, can be specially designed to create such maps with collision probabilities.
• Vehicles can be detected and movement data can be determined, for example, using suitable sensors such as cameras or movement sensors, but it can also take place, for example, using data obtained as part of vehicle-to-X communication.
• suitable sensors such as cameras or movement sensors
• models based on deterministic algorithms and/or statistical methods and/or artificial intelligence can be used for the prediction.
• Collision probabilities can be calculated, for example, by checking the probability with which trajectories overlap or areas around trajectories overlap.
• the card can be an electronically stored card, for example, which can be stored in a central unit, for example. It can then be used, for example, to evaluate accident black spots and identify opportunities to improve road safety.
• Movement data can be determined multiple times, for example, while the respective vehicle is driving through the area, and based on this, at least one trajectory can be predicted. As a result, the map can be improved, since a more extensive potential of data can be accessed. However, corresponding data can also be used for separate maps. Movement data can be determined in particular at predetermined time intervals. This allows for easy implementation.
• a plurality of trajectories with respective associated probabilities are always or at least partially predicted. This applies in particular to a respective vehicle. As a result, it is possible to calculate in advance how the vehicle will continue to move and with what probability, and in particular a probability can be assigned to each possible course of movement. This facilitates the calculation of collision probabilities.
• the detection and/or the determination of movement data can take place in particular by means of information received from the vehicles via radio.
• Vehicle-to-X communication for example, can be used for this purpose.
• roadside sensors such as cameras, radars, lidar sensors, etc. is also possible.
• the area can contain an intersection, junction, curve or junction. Such places are typically accident black spots. However, other areas can also be used.
• the collision probabilities can be normalized to a reference value.
• the map can then be designed to give a relative probability compared to a reference value rather than an absolute probability.
• the collision probabilities can, for example, be stored in aggregated form in predefined subdivisions of the area. This allows the map to be appropriately partitioned to avoid overly fine-grained execution. This allows certain evaluations in aggregated form.
• a prediction uncertainty and/or error limits can occur Determine movement data are taken into account. This can further improve the calculation.
• a number of trajectories with respective probabilities can be calculated on the basis of the uncertainty and/or the error limits.
• the collision probabilities of multiple pairings of vehicles can be stored in an aggregated form.
• a pairing can in particular be understood to mean that two vehicles come so close that there is at least a certain probability of collision.
• Aggregated storage can also result in an aggregated evaluation.
• collision probability for a collision with a fixed Flindernis can be considered.
• a trajectory or trajectories originating from the single vehicle is typically sufficient.
• the collision probabilities can be stored in the map in such a way that the map only takes into account collision probabilities from a predetermined time window.
• the map can be created in such a way that it enables an evaluation with regard to an improvement in traffic safety at specific times, with different traffic volumes typically prevailing at different times.
• a sliding window functionality may also be implemented so that the map is always generated for a predetermined period of time in the past.
• one or more maps are generated, with only collision probabilities that meet one or more predetermined conditions being considered for each map.
• maps with different characteristics can be generated, for example. Below are some examples, especially for conditions:
• Map differs depending on the prediction horizon, for example one map each for a prediction time of 1 s, 2 s, 3 s etc., Tickets for different times, for example one ticket each for 6 a.m. to 10 a.m., 10 a.m. to 3 p.m., 3 p.m. to 7 p.m., 7 p.m. to 10 p.m., etc. and/or for certain days of the week,
• Map only for certain combinations of objects for example a map for vehicle-vehicle, vehicle-pedestrian, bicycle-pedestrian, bicycle-car, truck-VRU, etc.,
• Map that does not show the collision probabilities but the locations of the objects involved if the collision probability exceeds a certain threshold. This can be particularly advantageous if it is to be determined where the objects involved come from or where there could be structural reasons for the risk of collision.
• Map depending on object density i.e. for example a map for a few, normally many, very many and overcrowded many objects in the observation area, possibly differentiated according to object types, for example "very many pedestrians", etc.,
• Map as a deviation from the norm. For this purpose, for example, a map can first be created that describes the basic state, and from then on further maps can be created that show the difference to this basic state. This can be particularly helpful when the result of a change is to be shown.
• the method can be carried out in such a way that one or more near-collision events are determined based on the fact that no collision of the vehicles took place at a location with a high probability of a collision between two vehicles.
• Such near-collision events are particularly valuable for improving accident black spots with regard to road safety, since, in contrast to actual accidents, they cannot be determined using real events.
• each collision probability to be read out can be one of can be assigned to a plurality of predetermined areas, and this area can be output in each case. In particular, this can mean that the reading is more coarse than the map would actually allow, which allows for an aggregated view and a simplification of the evaluation.
• the invention further relates to a calculation module configured to carry out a method as described herein.
• the invention further relates to a non-transitory computer-readable storage medium on which program code is stored, during the execution of which a processor executes a method described herein. With regard to the method, all of the versions and variants described herein can be used.
• an infrastructure installation that has at least one environment sensor (for example radar, camera, lidar, ultrasound, etc.) and/or a vehicle-to-X communication module can be regarded as the basis.
• a motion prediction can be created for each detected object. It is then checked whether the motion predictions of two or more objects overlap and there is therefore a risk of collision. Ideally, but not necessarily, both the motion prediction and the detection of the risk of collision take place with implicit consideration of the detection error and the prediction inaccuracy.
• a vehicle is detected and its position is detected with an accuracy of ⁇ 0.5 m, its speed is detected with an accuracy of ⁇ 1 m/s and its direction of movement with an accuracy of ⁇ 1 °.
• the prediction is now created as a kind of movement fan, with a most probable path in the middle (assuming no errors) and outer limits assuming detection errors and changes in vehicle dynamics during the prediction time.
• the collision risks determined in this way can be recorded on a map, which can be designed, for example, in the form of a “fleat map”. For that can for each location and for each object combination, the collision risk in the range from 0% to 100% can be added to the other collision risks.
• a grid can be used as the location for the evaluation, i.e. the collision probability is only added up for positions at a distance of e.g. 10 cm or another distance.
• a normalization can also take place for the map or fleet map if the absolute collision probability is not important, but only the relative one, i.e. when the question is asked where an accident is most likely to occur. To do this, the collision probabilities added up are divided by the greatest collision probability in the given observation area.
• the collision probabilities can also be added as a sliding window. Only the collision probabilities of the last x seconds or minutes or hours are added up.
• the consideration can be simplified in particular if only clusters of collision probabilities are considered instead of the collision probabilities.
• the collision probabilities could thus be divided into clusters, for example ⁇ 50%, 50% to 75%, 75% to 90%, >90%. Then, for example, it can be counted how often each cluster is reached (dedicated fleetmaps per cluster), or each cluster gets a rating number and these are summed up (for the example above, this could be 1, 3, 7, 15, for example).
• near misses can also be recognized from a map or fleet map, especially if high collision probabilities are determined with short prediction times, but no collision takes place.
• a minimum space-time distance distance of the four-dimensional space-time vectors
• This space-time can then, for example, be weighted with the probability of the pair of trajectories and summed up.
• this weighted space-time distance is evaluated as a near miss and can be re-entered in a fleet map at the position of the smallest distance.
• the advantage of this second approach is, in particular, that even close passes with very well-defined speeds and directions are recognized as near misses, which did not have a high probability of collision.
• the collision probability can also be made available as a further function to functions or devices of the system. This can be done, for example, in the form of raw data or as a trigger if a collision probability exceeds a specific value. On the basis of relatively well-known methods, danger spots and near misses can be identified.
• FIG. 1 shows a situation with two vehicles in front of an intersection.
• the first vehicle 10 is moving on a first road S1 and the second vehicle 20 is moving on a second road S2. Both vehicles 10, 20 are moving on the streets S1, S2 towards an intersection K, at which the two streets S1, S2 intersect.
• the first vehicle 10 instructs Vehicle-to-X communication module 15 having an antenna 17 attached thereto.
• the second vehicle 20 has a vehicle-to-X communication module 25 with an antenna 27 attached thereto. This enables the two vehicles 10, 20 to participate in the vehicle-to-X communication.
• Vehicle-to-X communication module 45 with an antenna 47 is arranged.
• the vehicles 10, 20 can also communicate with the roadside infrastructure.
• a computing unit 30, which can be used to create a map, is arranged next to the streets S1, S2.
• a camera 50 is arranged next to the roads S1, S2, which is shown here schematically and which can capture the two vehicles 10, 20.
• the camera 50 represents an infrastructure-side environment sensor.
• the computing unit 30 is designed to create a respective prediction of trajectories and associated probabilities at a number of times when the vehicles 10, 20 approach the intersection K.
• the computing unit 30 calculates a number of trajectories for each vehicle starting from each point in time at which a corresponding measurement was made, with each trajectory being assigned a certain probability. Based on these trajectories, collision probabilities at the intersection K are then calculated, ie it is calculated at what point and with what probability a collision can occur.
• a fleet map can be generated from this, ie an electronic map which indicates a respective collision probability for specific points of the intersection K. If required, the map can be normalized or it can be created based only on specific data, for example only based on data recorded at specific points in time. Such maps can help planners help to identify accident blackspots and to optimize them in such a way that road safety is increased.
• vehicle-to-X communication means, in particular, direct communication between vehicles and/or between vehicles and infrastructure devices.
• it can be vehicle-to-vehicle communication or vehicle-to-infrastructure communication. If reference is made to communication between vehicles in the context of this application, this can in principle take place, for example, in the context of vehicle-to-vehicle communication, which typically takes place without mediation through a mobile network or a similar external infrastructure and which is therefore different from other solutions , which are based, for example, on a cellular network.
• vehicle-to-X communication can be accomplished using the IEEE 802.11p or IEEE 1609.4 standards.
• Vehicle-to-X communication can also be referred to as C2X communication.
• the sub-areas can be referred to as C2C (Car-to-Car) or C2I (Car-to-Infrastructure).
• C2C Car-to-Car
• C2I Car-to-Infrastructure
• the invention does not explicitly exclude vehicle-to-X communication with switching, for example via a mobile radio network.

Landscapes

• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Chemical & Material Sciences (AREA)
• Analytical Chemistry (AREA)
• Engineering & Computer Science (AREA)
• Radar, Positioning & Navigation (AREA)
• Remote Sensing (AREA)
• Automation & Control Theory (AREA)
• Traffic Control Systems (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=80952170

Family Applications (1)

Country Status (8)

Families Citing this family (4)

Family Cites Families (6)

• 2021
  • 2021-04-23 DE DE102021204067.5A patent/DE102021204067A1/de active Pending
• 2022
  • 2022-03-16 CA CA3216842A patent/CA3216842A1/en active Pending
  • 2022-03-16 CN CN202280029298.1A patent/CN117178309A/zh active Pending
  • 2022-03-16 WO PCT/DE2022/200042 patent/WO2022223080A1/de active Application Filing
  • 2022-03-16 EP EP22712800.6A patent/EP4327314A1/de active Pending
  • 2022-03-16 JP JP2023562778A patent/JP2024517394A/ja active Pending
  • 2022-03-16 MX MX2023012505A patent/MX2023012505A/es unknown
  • 2022-03-16 KR KR1020237035198A patent/KR20230156414A/ko unknown

Also Published As

Similar Documents

Legal Events