Method for determining a collision risk of a vehicle, method for preventing a collision and a driving assistance device

Abstract

A collision risk of a vehicle 102 with a traffic participant appearing from a blind zone 204 is determined using an area of overlap 208 between the blind zone and collision zone(s) 206. Each (e.g. cir

Description

TECHNICAL FIELD

[0001] Various embodiments relate to methods for determining a collision risk of a vehicle, methods for preventing a collision, and a driving assistance device. BACKGROUND

[0002] As cities become increasingly congested, urban driving scenarios can be complex and stressful to drivers. Advanced Driver Assistance Systems (ADAS) technologies play an important role in enhancing road safety in these urban driving scenarios, through improved perception capabilities and a reduction in the cognitive load of drivers. A challenge in urban driving scenarios, is to avoid accidents w ith pedestrians who unexpectedly appear, for example, by dashing out from a blind zone of a vehicle. SUMMARY

[0003] According to various embodiments, there is provided a computer-implemented method for determining a collision risk of a vehicle. The method includes determining a driving path that the vehicle is moving towards, determining a blind zone of the vehicle and determining at least one collision zone based on a current velocity of the vehicle. Each collision zone corresponds to a respective position of at least one position on a route that the vehicle is moving towards. Each collision zone is bounded by a locus where an object that travels therefrom at a predefined speed towards the respective position will arrive at the respective position at a same time as the vehicle. The method further includes determining the collision risk with traffic participants appearing from the blind zone, based on an area of overlap between the blind zone and the plurality of collision zones.

[0004] According to various embodiments, there is provided a method for preventing a collision of a vehicle. The method includes performing the abovementioned method for determining a collision risk of a vehicle. The method further includes generating an alert signal in the vehicle based on the determined collision risk.

[0005] According to various embodiments, there is provided a driving assistance device. The driving assistance device includes a processor. The processor is configured to perform at least one of: (i) the abovementioned method for determining a collision risk of a vehicle, and (ii) the abovementioned method for preventing collision of a vehicle.

[0006] Additional features for advantageous embodiments are provided in the dependent claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] hi the drawings, like reference characters generally refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the invention. In the following description, various embodiments are described with reference to the following drawings, in which:

[0008] FIG. 1A and IB show examples of urban traffic scenarios.

[0009] FIG. 2 shows an urban traffic scenario represented in a graph.

[0010] FIG. 3 shows a collision risk of a vehicle, as represented in a graph.

[0011] FIG. 4 is a flowchart of a method for preventing a collision according to various embodiments.

[0012] FIG. 5a shows an assumption of traffic participants velocity.

[0013] FIG. 5b shows a block diagram of a vehicle according to various embodiments.

[0014] FIG. 6 includes three graphs that show the effects of the method for an example traffic scenario.

[0015] FIG. 7 is a three-dimensional graph showing the predicted collision risk.

[0016] FIG. 8 shows a flow diagram of a computer-implemented method for determining a collision risk of a vehicle, according to various embodiments.

[0017] FIG. 9 shows a flow diagram of a computer-implemented method for determining a collision risk of a vehicle, according to various embodiments.

[0018] FIG. 10 shows a simplified block diagram of a driving assistance device according to various embodiments. DESCRIPTION

[0019] Embodiments described below in context of the devices are analogously valid for the respective methods, and vice versa. Furthermore, it will be understood that the embodiments described below may be combined, for example, a part of one embodiment may be combined with a part of another embodiment.

[0020] It will be understood that any property described herein for a specific device may also hold for any device described herein. It will be understood that any property described herein for a specific method may also hold for any method described herein. Furthermore, it will be understood that for any device or method described herein, not necessarily all the components or steps described must be enclosed in the device or method, but only some (but not all) components or steps may be enclosed.

[0021] In this context, the device as described in this description may include a memory which is for example used in the processing carried out in the device. A memory used in the embodiments may be a volatile memory, for example a DRAM (Dynamic Random Access Memory) or a non-volatile memory, for example a PROM (Programmable Read Only Memory), an EPROM (Erasable PROM), EEPROM (Electrically Erasable PROM), or a flash memory, e.g., a floating gate memory, a charge trapping memory, an MRAM (Magnetoresistive Random Access Memory) or a PCRAM (Phase Change Random Access Memory).

[0022] In order that the invention may be readily understood and put into practical effect, various embodiments will now be described by way of examples and not limitations, and with reference to the figures.

[0023] FIG. 1A shows an example of an urban traffic scenario 100A. In this urban traffic scenario 100A, a vehicle 102 is approaching a crosswalk 110, in other words, a pedestrian crossing. The vehicle 102 is travelling along a driving direction 120. A pedestrian 108 is beginning to cross the road, walking along a crossing direction 122. There may be an obstruction 150 which partially occludes the field of view (FOV) of the vehicle 102, thereby resulting in a blind zone for the vehicle 102. The obstruction 150 may be one of other vehicles 104 near to the vehicle 102. The obstruction 150 may also be any other object, such as a building structure, a wall, a post box, or others. The blind zone may refer to an area around the vehicle 102 that cannot be seen by the driver while the driver is at the driver’s seat. The blind zone may also refer to an area around the vehicle 102 that cannot be captured by perception sensors onboard the vehicle 102. The perception sensors may include, for example, cameras, radar, LiDAR, and ultrasonic sensors. The boundary of the blind zone is indicated in FIG. 1A by the dashed line 106. When the pedestrian is beginning to cross the road from the sidewalk 112, the pedestrian 108 is positioned within the blind zone of the vehicle 102. The sidewalk 112 may also be referred to as a pavement, in other words, it is a path for pedestrians to walk on. As such, the driver of the vehicle 102 may be unaware of the presence of the pedestrian 108. If both the vehicle 102 and the pedestrian 108 were to continue on their paths without decelerating, they may collide at collision point 124.

[0024] FIG. IB shows another example of an urban traffic scenario 100B. In this urban traffic scenario 100B, the vehicle 102 is travelling along a road that is adjacent to sidewalks 112a, 112b. The vehicle 102 is travelling along a driving direction 120. A pedestrian 108 is beginning to jaywalk across the road, along a crossing direction 122. As the pedestrian 108 is positioned within the blind zone of the vehicle 102, the driver of the vehicle 102 may be unaware of the presence of the pedestrian 108. If the vehicle 102 continues at its current velocity in the driving direction 120, and if the pedestrian 108 continues walking in die crossing direction 122, the vehicle 102 may knock down the pedestrian 108 at collision point 124.

[0025] To address the urban traffic scenarios 100A and 100B, the vehicle 102 may be equipped with a driving assistance device 1000 (shown in FIG. 10) that performs a method 800 for determining a collision risk (shown in FIG. 8). The method 800 may include calculating a quantitative risk of potential collision when the field of view of the vehicle 102 is curtailed by an obstruction 150, such as one of the odier vehicles 104. The vehicle 102 may generate a warning message to alert its driver to die potential collision based on the calculated risk. The vehicle 102 may also adjust its heading or speed based on the calculated risk. The mediod 800 for determining a collision risk will be described further with respect to at least FIGS. 2 and 3.

[0026] According to various embodiments, the driving assistance device 1000 may be an ADAS system.

[0027] According to various embodiments, the driving assistance device 1000 may be integrated into an automated driving control unit (ADCU) of a vehicle. The vehicle may be a self-driving vehicle.

[0028] FIG. 2 shows an urban traffic scenario, such as the urban traffic scenario 100A or the urban traffic scenario 100B, represented in a graph 200. The graph 200 includes a horizontal axis 220 and a vertical axis 222. The present position, in other words, the current position, of the vehicle 102, is represented by the origin of the graph 200 where tire horizontal axis 220 and vertical axis 222 intersect. The horizontal axis 220 represents distance from the vehicle 102, along a direction parallel to the driving direction 120 of the ego vehicle. The vertical axis 222 represents distance from the vehicle 102, along a direction parallel to the crossing direction 122 ofthe pedestrian. The obstruction 150 may at least partially obstruct the FOV ofthe vehicle 102, causing a blind zone 204. A position on the driving path of the vehicle 102 marked as Ox, may be referred to as a potential collisional point 202. The driving path may also be referred herein as a route ahead of the vehicle 102 according to a driving direction of the vehicle 102. The driving assistance device 1000 may calculate a driving time required for the vehicle 102 to travel from its current position (at the origin of the graph 200), to the potential collisional point 202. The driving time may be calculated based on the current velocity of the vehicle 102, and further based on the displacement between the current position of the vehicle 102 and Ox. The driving time may be calculated according to the following equation: Dx =

[0029] where t(x) is the driving time required for the vehicle 102 to reach 0x, vegois the current velocity of the vehicle 102 and Dx is the displacement along the x-axis 220, between the current position of the vehicle 102 and Ox. The driving assistance device 1000 may further compute a collision zone 206 associated with Ox. The driving assistance device 1000 may determine the collision zone 206 associated with Ox, based on tx and further based on a predefined speed of another traffic participant. The collision zone 206 is a region where another traffic participant may travel from and meet the ego vehicle 202 at the potential collisional point 202. The traffic participant may be for example, a pedestrian 108, a cyclist, or another vehicle 104. The predefined speed may be an estimated maximum speed of the traffic participant. For example, the predefined speed for a walking pedestrian may be up to 1,5m / s. The collision zone 206 associated with Ox may be a circle centred around Ox, and having a radius rx. The radius may be calculated according to the following equation: = vtpt(x) where vtp is the predefined speed of the traffic participant.

[0030] The area of the collision zone 206, Cx, may be calculated according to the following equation: Cx = nrx 2

[0031] The driving assistance device 1000 may further determine an overlapping area between the blind zone 204 and the collision zone 206. The overlapping area may be referred herein as the risk area 208, Ax. The size of the risk area 208, after being multiplied with density of other traffic participants in the collision zone 206, may be indicative of the expectation of a collision with a traffic participant. If the density of other traffic participants in the collision zone 206 is assumed to be unity, the risk of collision with the traffic participant may increase according to an increase in the risk area 208.

[0032] The risk area may be expressed as follows: Ax = B n Cx where B is the blind zone 204, and Cx is the collision zone 206 associated with Ox.

[0033] The driving assistance device 1000 may further determine a risk value associated with Ox based on the risk area 208 and potential density of other traffic participants in the risk area 208. The risk value, So, may be expressed as follows: 50 = ^X*^ where d denotes the potential density' of other traffic participants per unit area, in the risk area 208. The other traffic participants may be assumed to move to Ox from the edge of the collision zone 206 at a predefined constant velocity. Accordingly, the potential density, d may increase as the other traffic participants approach Ox.

[0034] According to various embodiments, the number of traffic participants in the risk area may be assumed to be the same, regardless of the size of the risk area. Accordingly, the potential density may decrease with an increase in the risk area, in other words with an increase of distance from Ox.

[0035] The collision risk may be determined based on an integral of the risk value from a start point OXstart, to an end point OXgnd, according to the following equation: f f X CTltl Collisionrisk = I S0(x)dx = I S0(x)dx $ Oxstart

[0036] The end point, OXgnd may be selected based on a time duration required for the vehicle 102 to avoid the collision. The time duration may be determined based on the distance at which the vehicle 102can stop with a relatively mild deceleration, for example, -0.1G. The end point, Oxgnd may ^8° determined based on a predefined reaction time, for example, 3 seconds, multiplied by the speed of the vehicle 102.

[0037] The start point, OXstart may be selected based on size and position of the obstruction 150. For example, OXstart may be a position where a line drawn perpendicularly from the driving direction of the vehicle 102 meets a rearmost end of the obstruction 150. The rearmost end of the obstruction may be the end of the obstruction 150 that is furthest away from the origin, i.e., initial position of the vehicle 102.

[0038] According to various embodiments, d may be assumed to be a constant value, for example, d = 1 person per m2, to simplify the calculation of collision risk.

[0039] FIG. 3 shows a collision risk of the vehicle 102, as represented in a graph 300. Different future positions of the vehicle 102 along a route of the vehicle 102 may be referred herein as potential collisional points 202. A method for determining collision risk of the vehicle 102 may include setting potential collisional points 202. The method may further include computing a respective collision zone 206 for each potential collisional point 202 of a plurality of potential collisional points 202. The method may further include calculating a respective estimated driving time for the vehicle 102 to reach each of the potential collisional points 202 from its current position. The method may further include calculating an expectation of traffic participants appearing from the risk area 208. The calculation of the expectation may include making assumptions, such as assuming that the traffic participants travel in a linear motion with constant velocity, for example, an assumption that a pedestrian travels at a velocity of up to 1.5m / s. Another assumption may be that the potential density is a constant value of 1 person per m2 The expectation of potential collision with objects, i.e. other traffic participants, appearing from the risk area 208. The collision risk may be determined based on an integral of the expectation from a first potential collisional point to the last potential collision point.

[0040] According to various embodiments, the method for determining the collision risk may include assuming a finite number of potential collision points to simplify the calculation. In the example shown in FIG. 3, there may be n+1 number of potential collisional points 202 that are taken into consideration for the computation. The value of n may be a timing parameter that is predefined or chosen by the driver. The value of n may depend on a time frame to be considered. For example, the driver of the vehicle 102 may request the driving assistance device 1000 to estimate the collision risk for a 10-second future time frame, and n may be defined based on 10 seconds.

[0041] Alternatively, n may be determined based on fulfilling the following: where vc is the current velocity of the vehicle 102, and ac is a predefined deceleration of the vehicle 102. This means the calculation estimates the risk till the time when the vehicle 102 can stop with the predefined declaration value. Using this criteria, the collision risk is estimated for a longer time frame when the vehicle 102 is travelling at a high velocity so that there is sufficient time for the vehicle 102 to come to a stop for potential collision points that are at a greater distance away.

[0042] For simplicity of the illustration, only 3 potential collisional points 202 (Oo, On) and their associated collision zones 206 (Co, Cy, Cn) are shown in the figure. The risk area 208 associated with each potential collision point 202 is denoted as s, where i is the index of the potential collision point 202, for example, i = 0, i = 1, i = •••, i = n.

[0043] The computation of the collision zones 206 and the risk areas 208 may be performed as described with respect to FIG. 2. The collision risk may be determined based on a sum of the risk areas 208, as follows: A = 8 O Co + 8 O + + 8 O Cn where A is the risk area. The collision risk may be a multiplication of A and the potential density. The traffic participants may be assumed to exist uniformly and move in all directions, 360°, on a same probability with having velocity up to the predefined value. One participant on the edge of Ci with max value as the predefined velocity, can reach Oi with the velocity in ti. Other participants moving at a lower velocity than the predefined velocity and / or does not move towards Oi will not reach Oi. As the traffic participant that can reach Oi within ti is unlikely to reach O2 within t2, the calculation of collision risk does not need to consider any overlaps of risk areas 208.

[0044] FIG. 4 is a flowchart of a method 400 for avoiding a collision according to various embodiments. The method 400 may be performed by the driving assistance device 1000. The method 400 may include the method 800 for determining a collision risk. The method 400 may include a plurality of steps. Step 402 may include obtaining the velocity and planned route of the ego car, also referred herein as the vehicle 102. The method 400 may further include determining if any object is detected, in step 404. If there is no object detected in step 404, the method 400 may return 420 to start 410. If an object is detected in step 404, the method 400 may proceed to step 406 to obtain the positions, velocity and heading angle of the object which yields the blind spot, i.e., blind zone 204, for the vehicle’s driver or perception sensors. The object which yields the blind spot is also referred herein as the obstruction 150. It should be understood that the step 404 may be performed before, after, or concurrently to the step 402. The method 400 may further include calculating blind area D, in step 408. The blind area D may refer to the area of the blind zone 204. In step 408, the blind area D may be calculated, based on information obtained in the step 404. Referring to FIG. 2, the blind area D may be calculated based on positions of a leftmost comer 250 and a rightmost comer 252 of the object, from the perspective of the vehicle 102.

[0045] Next, step 410 may include calculating the collision circle C. The collision circle C may refer to the collision zone 206. In step 410, the collision circle C may be calculated based on the velocity and planned route of the vehicle 102 obtained from the step 402. Next, step 412 may include calculating the risk area 208 based on the collision circle C calculated in the step 410 and further based on the blind area D calculated in the step 408. The method 400 may further include step 414, where the risk area 208 is compared against a risk threshold. If the risk area 208 is equal to, or larger than, the risk threshold, the method 400 may further include generating a warning signal to warn the driver of the vehicle 102, in step 416. If the risk area 208 is smaller than the risk threshold, the method 400 may return 420 to the start 410.

[0046] According to various embodiments, the calculations carried out in the method 400 may involve one or more assumptions about the behavior of other traffic participants in the collision zones 206. The assumption(s) is explained with reference to FIG. 5A.

[0047] FIG. 5A is a graph 500A representing velocities of other traffic participants in a collision zone 206. The graph 500A has a vertical axis 554 representing velocity of the traffic participants. The graph 500A has an x-axis 550 representing distance from the vehicle 102 along a driving direction of the vehicle 102. The graph 5 00A also has ay-axis 552 that represent distance from the vehicle 102 along another direction that is orthogonal to the driving direction of the vehicle 102. The graph 500A also includes vectors 556, each vector 556 representing velocity of a respective traffic participant.

[0048] The assumptions may include at least one of: (a) the traffic participants exist uniformly on the x-y plane defined by the x-axis 550 and they-axis 552; (b) the movement directions of the traffic participants are equally distributed in different directions, as represented by the vectors 556; and (c) the traffic participants’ velocities range from 0 to a predefined maximum velocity, as represented by V1. V2. V3, V4, V5 and V6. In each collision zone, only the vector 556 that points towards the potential collision point Ox may reach the potential collision point Ox, if it is travelling at the right speed to reach Ox at the same time as the vehicle 102.

[0049] By applying the above assumptions, possible positions of traffic participants that may reach the collision point Ox may be observed as a circle like Cn in FIG.3. Uris also means if Cn partially overlaps with adjacent collision zones, for example, Cn+1 or Cn-i, the overlapping areas need not be subtracted from the risk calculation as there is only one vector 556 in each collision zone that reaches the collision point Ox. According to various embodiments, a traffic participant may have a high velocity in the driving direction of the vehicle 102, i.e. parallel to the road on which the vehicle 102 is travelling on, and a low velocity in an orthogonal direction, for example in the direction of a crosswalk. In such cases, the collision zone 206 may be elliptical in shape, instead of being circular.

[0050] This assumption may be reasonable if the traffic participant that may appear from the blind zone 206 is a pedestrian. However, if the traffic participant is faster moving, for example isa motorbike, and / or if the traffic participant travels in a direction that is not parallel to the lane on which the vehicle 102 travels on, the collision zone 204 may be elliptical in shape.

[0051] FIG. 5B shows a block diagram of a vehicle 102 according to various embodiments. The vehicle 102 may include a controller 502. The controller 502 may include the driving assistance device 1000. The vehicle 102 may further include at least one of: a Global Positioning System (GPS) 504, at least one wheel speed sensor (WSS) 506, a supplemental restraint system (SRS) sensor 508, an electric power steering (EPS) sensor 510, a front camera 512, a radar 514, a LiDAR 516, an electric power steering (EPS) system 518, a power plant (PP) system 520, a brake system 522, and an acoustic alert system 524. The SRS sensor 508 may include yaw rate and lateral G sensors. The PP system 520 may include for example, an engine or in the case of an electric vehicle, a propulsion control system. The controller 502 may be configured to receive inputs from a sensor, wherein the sensor includes at least one of: the GPS 504, the WSS 506, the SRS sensor 508, the EPS sensor 510, the front camera 512, the radar 514, and the LiDAR 516. The controller 502 may be configured to send output to at least one of: the EPS system 518, the PP system 520, the brake system 522, and the acoustic alert system 524. The controller 502 may generate the output based on inputs received from the sensor.

[0052] For example, referring back to the flow chart 400, the step 402 may include receiving in the controller 502, the ego vehicle’s velocity from the WSS 506 and the planned route from the GPS 504. The step 406 may include detecting objects by the controller 502, based on inputs from the front camera 512 and / or the LiDAR 516. The step 416 may include the controller 502 sending a command to the acoustic alert system 524, such that the acoustic alert system 524 generates an acoustic warning to the driver.

[0053] FIG. 6 includes three graphs 610, 620 and 630 that show the effects of the method 400 for an example traffic scenario. In this example traffic scenario, the vehicle 102 is assumed to be driving on a straight road and going to pass by a parked car. The parked car is an obstruction 150 to the ego vehicle's FOV. Each of the graphs 610, 620 and 630 include a common horizontal axis 602 representing time.

[0054] The first graph 610 shows the vehicle 102 approaching the parked car as time increases. The vertical axis 604 of the first graph 610 represents distance between the vehicle 102 and the parked car.

[0055] The second graph 620 shows how the velocity of the vehicle 102 changes with time, depending on how the vehicle 102 is controlled. A dashed line 622 represents the velocity of the vehicle 102 as controlled by ACC. A solid line 624 represents the velocity of the vehicle 102 as controlled by a driver assisted by the driving assistance device 1000, or an autonomous vehicle controlled by the driving assistance device 1000. A dotted line 626 represents the velocity of the vehicle 102 as controlled by an expert driver. The solid line 624 closely follows the dotted line 626, indicating that the driving assistance device 1000 may aid the driver such that the driver maneuvers the vehicle 102 like an expert driver.

[0056] The vertical axis 608 of the third graph 630 represents the risk of the vehicle 102 colliding into a traffic participant, in other words, the collision risk. The third graph 630 includes a dashed line 632 that indicates a predetermined risk threshold. The risk increases as the vehicle 102 accelerates, until the risk reaches the risk threshold. The method 400 may generate a warning to the driver of the vehicle 102, or may decelerate the vehicle 102, such that the vehicle 102 slows down and reduces the risk of collision.

[0057] FIG. 7 is a three-dimensional graph 700 showing the predicted collision risk calculated in the step 412. The graph 700 includes an x-axis 702, ay-axis 704 and az-axis 706. The x-axis 702 represents the lateral distance between the middle of the obstruction 150, for example a parked car, and the middle of the vehicle 102. The y-axis 704 represents the velocity of the vehicle 102. The z-axis 706 represents the predicted collision risk calculated the step 412. The graph 700 shows that the predicted collision risk depends on the lateral distance between the obstruction 150 and the vehicle 102, and also depends on the velocity of the vehicle 102. The collision risk increases as the lateral distance decreases, and as the velocity increases.

[0058] FIG. 8 shows a flow diagram of a computer-implemented method 800 for determining a collision risk of a vehicle 102, according to various embodiments. The method 800 may include processes 802, 804, and 806. The process 802 may include determining a blind zone 204 of the vehicle 102. The process 804 may include determining at least one collision zone 206 based on a current velocity of the vehicle 102. Each collision zone 206 may correspond to a respective position of at least one position on a route that the vehicle 102 is moving towards. Each collision zone 206 may be bounded by a locus where a traffic participant that travels therefrom at a predefined speed towards the respective position will arrive at the respective position at a same time as the vehicle 102. The traffic participant may be for example, a pedestrian, a bicycle, a personal mobility device or any other vehicle. The process 808 may include determining the collision risk based on an area of overlap between the blind zone 204 and the plurality of collision zones 206. For example, with reference to FIG. 4, the process 802 may include the step 408, the process 804 may include the step 410, and the process 806 may include the step 412.

[0059] The method 800 determines the collision risk, which is a probability value rather than a binary flag. This provides more information to the ADAS system, as compared to a binary flag. This may be useful, for example, in an automatic driving system, to adjust the speed of the vehicle based on analog value of the collision risk, such that the risk is reduced to a predefined acceptable level. This may reduce the rates of false alarm or sudden braking of tire vehicle. Further, the method 800 is able to determine the collision risk using only a small number of parameters that are easily obtained from the vehicle 102.

[0060] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, the collision risk may be increased according to the area of overlap between the blind zone 204 and the plurality of collision zones 206.

[0061] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, determining the plurality of collision zones 206 may include determining a current position of the vehicle 102. Determining the plurality of collision zones 206 may further include, for each position on the route ahead of the vehicle 102, determining a respective driving time required for the vehicle 102 to travel from the current position to the position, determining a respective distance that can be travelled at the predefined speed, in the respective driving time, and determining the respective collision zone 206 based on the respective distance and further based on the current position. For example, with reference to FIG. 4, determining the current position of the vehicle 102 may include the step 402. The current position of the vehicle 102 may be provided by the GPS 504.

[0062] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, determining the blind zone 204 may include receiving sensor data from a sensor onboard the vehicle 102, and detecting an obstruction 150 in the sensor FOV, based on the sensor data. Determining the blind zone 204 may further include determining at least one of size and position of the obstruction 150, and determining the blind zone 204 based on the at least one of size and position of the obstruction 150. For example, with reference to FIG. 4, determining at least one of size and position of the obstruction 150 may include the step 404. The sensor data may be provided, for example, by at least one of the front camera 512, the radar 514 and the LiDAR 516.

[0063] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, the obstruction 150 may lie outside of the route ahead of the vehicle 102. For example, like in FIGS. 1A and IB, the obstruction 150 may be offset from the route of the vehicle 102.

[0064] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, each collision zone 206 may be a circular area centred around the respective position. For example, with reference to FIG. 3, the collision zones 206 may be circles with respective centre points at Oo, Oi, ... , On.

[0065] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, the vehicle 102 may be travelling beside a sidewalk 112.

[0066] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, the vehicle 102 may be approaching at least one of a crosswalk 110 and a road intersection.

[0067] FIG. 9 shows a flow diagram of a computer-implemented method 900 for determining a collision risk of a vehicle 102, according to various embodiments. Ure method 900 may include, or may be part of, the method 400. The method 900 may include processes 902 and 904. The process 902 may include performing the method 800 to result in a determined collision risk. The process 904 may include generating an alert signal in the vehicle 102 based on the determined collision risk.

[0068] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, generating the alert signal may include comparing the determined collision risk to a risk threshold, and generating the alert signal based on determining that the determined collision risk exceeds the risk threshold. Hie determined collision risk being larger than the risk threshold may indicate that there might be an imminent collision of the vehicle 102 with a pedestrian, or another vehicle, that appears from the blind zone 204 unless the vehicle 102 decelerates. The alert signal may be used to trigger a deceleration of the vehicle 102, so as to avoid the collision. For example, with reference to FIG. 4, comparing the determined collision risk to a risk threshold may include the step 414.

[0069] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, the method 900 may further include decelerating the vehicle 102 based on the alert signal. For example, the alert signal may be sent to the brake system 522 or the EPS 518 of the vehicle 102 to slow down the vehicle 102.

[0070] According to an embodiment which may be combined with any above-described embodiment or with any below described further embodiment, the method 900 may further include generating a warning message for a driver of the vehicle 102 based on the determined collision risk. The w arning message may include at least one of a visual message and an audio message. Generating the warning message may include, for example, the step 416 of the method 400. The warning message may trigger the driver to decelerate the vehicle 102 in time to prevent a collision.

[0071] FIG. 10 shows a simplified block diagram of a driving assistance device 1000 according to various embodiments. The driving assistance device 1000 may include a processor 1002. The processor 1002 may include the controller 502. The processor 1002 may be configured to perform the method 800. Alternatively, or additionally, the processor 1002 may be configured to perform the method 900 or 400.

[0072] While embodiments of the invention have been particularly shown and described with reference to specific embodiments, it should be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. The scope of the invention is thus indicated by the appended claims and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced. It will be appreciated that common numerals, used in the relevant drawings, refer to components that serve a similar or the same purpose.

[0073] It will be appreciated to a person skilled in the art that the terminology used herein is for the purpose of describing various embodiments only and is not intended to be limiting of the present invention. As used herein, the singular forms ‘"a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0074] It is understood that the specific order or hierarchy of blocks in the processes / flowcharts disclosed is an illustration of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of blocks in the processes / flowcharts may be rearranged. Further, some blocks may be combined or omitted. The accompanying method claims present elements of the various blocks in a sample order, and are not meant to be limited to the specific order or hierarchy presented.

[0075] The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not intended to be limited to the aspects shown herein, but is to be accorded the full scope consistent with the language claims, wherein reference to an element in the singular is not intended to mean “one and only one” unless specifically so stated, but rather “one or more.” The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects. Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ include any combination of A, B, and / or C, and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, where any such combinations may contain one or more member or members of A, B, or C. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims.

Claims

1. A computer-implemented method (800) for determining a collision risk of a vehicle, the method comprising:determining a blind zone (204) of the vehicle (102);detennining at least one collision zone (206) based on a current velocity of the vehicle (102), each collision zone (206) of the at least one collision zone (206) corresponding to a respective position of at least one position on a route that the vehicle (102) is moving towards,wherein each collision zone (206) is bounded by a locus where a traffic participant that travels therefrom at a predefined speed towards the respective position will arrive at the respective position at a same time as the vehicle (102); anddetermining the collision risk with a traffic participant appearing from the blind zone (204), based on an area of overlap between the blind zone (204) and at least one collision zone (206).

2. The method (800) of any preceding claim, wherein determining the at least one collision zone (206) comprises,determining a current position of the vehicle (102), andfor each position on the route ahead of the vehicle (102),determining a respective driving time required for the vehicle (102) to travel from the current position to the position,determining a respective distance that can be travelled at the predefined speed, in the respective driving time, anddetennining the respective collision zone (206) based on the respective distance and further based on the current position.

3. The method (800) of any preceding claim, wherein detennining the blind zone (204) comprisesreceiving sensor data from a sensor onboard the vehicle (102),detecting an obstniction (150) in the sensor field of view, based on the sensor data, detennining position of the obstruction (150), anddetermining the blind zone (204) based on the at least one of size and position of the obstruction (150).

4. The method (800) of claim 5, wherein the obstruction (150) lies outside of the route that the vehicle (102) is heading towards.

5. The method (800) of any preceding claim, wherein each collision zone (206) is a circular area centred around the respective position.

6. The method (800) of any preceding claim, wherein the vehicle (102) is travelling beside a sidewalk (112).

7. The method (800) of any preceding claim, wherein the vehicle (102) is approaching at least one of a crosswalk (110) and a road intersection.

8. The method (800) of any preceding claim, wherein determining the collision risk comprises determining, for each collision zone,a risk value based on the area of overlap between the blind zone (204) and the collision zone (206) and further based on a predefined density of other traffic participants in the collision zone (206).

9. The method (800) of claim 8, wherein determining the collision risk further comprises integrating the risk value from a start point to an end point, wherein the start point is a position where a line drawn perpendicularly from a driving direction of the vehicle (102) meets a rearmost end of the obstruction 150, the rearmost end of the obstruction (150) being an end of the obstruction (150) that is furthest away from a current position of the vehicle (102), and wherein the end point is determined based on a distance at which the vehicle (102) is able to stop when a predefined deceleration is applied.

10. A method (400, 900) for preventing a collision of a vehicle (102), the method comprising:performing the method of any preceding claim to result in a determined collision risk; andgenerating an alert signal in the vehicle (102) based on the determined collision risk.

11. The method (400, 900) of claim 10, wherein generating the alert signal comprises comparing the determined collision risk to a risk threshold, and generating the alert signal based on determining that the determined collision risk exceeds the risk threshold.

12. The method (400, 900) of any one of claims 10 to 11, further comprising: decelerating the vehicle (102) based on the alert signal.

13. The method (400, 900) of any one of claims 10 to 12, further comprising: generating a warning message for a driver of the vehicle (102) based on the determined collision risk, wherein the warning message comprises at least one of a visual message and an audio message.

14. A driving assistance device (1000) comprising:a processor (1002) configured to perform at least one of:the method (800) for determining a collision risk of a vehicle (102) according to any one of claims 1 to 9, andthe method (400, 900) for preventing a collision of a vehicle (102) according to any one of claims 10 to 13.

Images