# US 2022/0036735 A1 · Real-time driving risk assessment method employing equivalent force and device thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0036735 A1
- Document ID: US20220036735A1
- Status: Published application
- Kind: A1
- Application number: 16/755,891
- Filed: 2018-05-14
- Published: 2022-02-03
- Earliest claimed: 2018-05-08
- Assignees: Tsinghua University
- Applicants: Tsinghua University
- Inventors: Jianqiang WANG; Xunjia ZHENG; Heye HUANG
- Web page: https://patentgrep.com/patent/US20220036735A1

## CPC

- G08G 1/16: Anti-collision systems (road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08)
- B60W 30/0953: {the prediction being responsive to vehicle dynamic parameters}
- B60W 30/0956: {the prediction being responsive to traffic or environmental parameters}
- B60W 50/0098: {Details of control systems ensuring comfort, safety or stability not otherwise provided for}
- G06Q 50/265: {Personal security, identity or safety}
- B60W 2050/0031: {Mathematical model of the vehicle}
- B60W 2520/06: Direction of travel
- B60W 2520/10: Longitudinal speed
- B60W 2520/12: Lateral speed
- B60W 2530/10: Weight
- B60W 2554/4042: Longitudinal speed
- B60W 2554/4045: Intention, e.g. lane change or imminent movement
- B60W 2554/80: Spatial relation or speed relative to objects
- B60W 2554/801: Lateral distance
- B60W 2554/802: Longitudinal distance
- B60W 2554/804: Relative longitudinal speed
- B60W 2554/805: Azimuth angle
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A real-time assessment method of driving risk based on equivalent force includes: S1, collecting traffic environment information and various types of traffic environment use object information in a road environment in an area to be assessed; S2, inputting, into an electronic control unit of a vehicle, the traffic environment use object information and the environment information acquired in S1, wherein a road risk assessment model based on the equivalent force distribution is preset in the electronic control unit; S3, using the road risk assessment model, so as to acquire road traffic risk E of the vehicle i and equivalent force distribution Fij between the vehicle i and the object j in different traffic environments, wherein the object j represents any traffic element other than vehicle i in various traffic environment use object information. A real-time assessment device of driving risk based on equivalent force is further provided.

## Claims

### Claim 1

A real-time assessment method of driving risk based on equivalent force, comprising:
S1, collecting traffic environment information and various types of traffic environment use object information in a road environment in an area to be assessed;
S2, inputting, into an electronic control unit of a vehicle, the various types of traffic environment use object information and the traffic environment information acquired in S1, wherein a road risk assessment model based on an equivalent force distribution is preset in the electronic control unit;
S3, using the road risk assessment model to acquire a road traffic risk E of a vehicle i and an equivalent force distribution Fij between the vehicle i and an object j in different traffic environments, wherein the object j represents any traffic element other than the vehicle i in the various types of traffic environment use object information, the road traffic risk E is expressed as a sum of kinetic energy Ei of the vehicle i, kinetic energy Ej of the object j, and relative kinetic energy Eij between the vehicle i and the object j.

### Claim 2 (depends on 1)

The real-time assessment method according to claim 1, wherein Eij and Fij in S3 are defined as follows:
E
ij
=
1
2
⁢
m
i
⁢
v
i
·
v
ij
⁡
(
cos
⁢
⁢
θ
ij
*
-
tan
⁢
⁢
θ
ij
⁢
sin
⁢
⁢
θ
ij
*
)
;
F
ij
=
1
2
⁢
w
ki
⁢
w
kj
⁢
F
ij
,
max
;
wherein, Fij,max represents a maximum equivalent force on the object j loaded by the vehicle i, and is expressed as:
F
ij
,
max
=
1
2
⁢
m
i
⁢
v
i
·
v
ij
⁡
(
cos
⁢
⁢
θ
ij
*
-
tan
⁢
⁢
θ
ij
⁢
sin
⁢
⁢
θ
ij
*
)
d
ij
;
wherein, mi represents a mass of the vehicle i; vi represents a speed of the vehicle i; vij represents a relative speed between the vehicle i and the object j; dij represents a relative distance between the vehicle i and the object j; vi, vij, dij each is a vector, θij is an angle from dij to vij, θij* is an angle from dij to vi, a counterclockwise direction is defined as positive; wki is a probability weight of the vehicle i to maintain a current wheel angle and to change the current wheel angle; wkj is a probability weight of the object j to maintain an angle of a current state and to change the angle of the current state.

### Claim 3 (depends on 2)

The real-time assessment method according to claim 2, wherein
w
ki
=
p
ki
⁡
(
δ
ki
)
p
0
⁡
(
δ
0
)
;
w
kj
=
p
kj
⁡
(
δ
kj
)
p
0
⁡
(
δ
0
)
;
the object j is defined as a vehicle, wij represents a probability weight of a vehicle j to maintain the current wheel angle and to change the current wheel angle; pki (δki) represents a steering probability of the vehicle i at a next moment steering angle along a steering angle δki; pkj(δkj) represents a steering probability of the vehicle j at the next moment steering angle along a steering angle δkj; δ0=0 indicates straight-line driving, p0 (δ0) indicates a probability that the vehicle i and the vehicle j go straight;
pki(δki), pkj(δkj), p0(δ0) are obtained by the following calculation expression:
p
k
⁡
(
δ
k
)
=
1
3.7704
*
2
⁢
π
⁢
e
-
δ
k
2
28.4318
,
⁢
δ
k
=
k
*
Δδ
,
k
∈
[
-
n
,
n
]
,
wherein k, n∈Z; Δδ represents an increment of a steering angle; when k is a positive integer, δk means turning to left; when k is a negative integer, δk means turning to right.

### Claim 4 (depends on 1)

The real-time assessment method according to claim 1, further comprising:
S4, based on the equivalent force distribution Fij obtained in S3, verifying a rationality of steering probability of the vehicle according to distribution law of a possible trajectory of a driver.

### Claim 5 (depends on 4)

The real-time assessment method according to claim 4, wherein the S4 comprises the following steps:
S41, taking a target weight distance ds of n feasible expected trajectory decisions s of the driver, s=1 . . . n, and forming a set D to be determined,
D={d1,d2,d3, . . . dn};
S42, forming an evaluation index set by a security e1, an efficiency e2, a maneuverability e3 and a regularity e4 as follows:
E{e1,e2,e3,e4};
through the security e1, the efficiency e2, the maneuverability e3 and the regularity e4, evaluating the n feasible expected trajectory decisions s in S41 using a relative membership matrix with evaluation indicators as follows:
M
t
=
[
m
11
m
12
⋯
m
1
⁢
n
m
21
m
22
⋯
m
2
⁢
n
m
31
m
32
⋯
m
3
⁢
n
m
41
m
42
⋯
m
4
⁢
n
]
=
(
m
su
)
4
*
n
;
S43, defining an appropriate expected trajectory decision s having a greatest relative membership, in a form of:
Am=(A1,A2,A3A4)T=(1,1,1,1)T;
S44, defining an inappropriate expected trajectory decision s having a smallest relative membership, in a form of:
Bm(B1,B2B3)T=(0,0,0,0)T;
S45, expressing an evaluation indicator membership function of an expected trajectory decision s in vector form as:
ms(m1s,m2s,m3s,m4s)T
S46, representing a difference between an actual trajectory decision u and the appropriate expected trajectory decision s by a generalized superior target weight distance dsA as follows:
d
s
A
=
∑
i
=
1
4
⁢
⁢
[
w
s
⁡
(
A
s
-
m
su
)
]
p
p
;
wherein msu represents one of m1s,m2s,m3s,m4s;
S47, expressing a difference between the actual trajectory decision u and the inappropriate expected trajectory decision by a generalized poor target weight distance dsB as follows:
d
s
B
=
∑
s
=
1
4
⁢
[
w
s
⁡
(
B
s
-
m
s
⁢
u
)
]
p
p
⁢
⁢
wherein
,
⁢
w
=
(
w
1
,
w
2
,
w
3
,
w
4
)
T
,
∑
s
=
1
4
⁢
w
s
=
1
;
p is a distance parameter, wherein p is called Hamming distance when p=1; p is called Euclidean distance when p=2;
ws represents a weight for the security e1, the efficiency e2, the maneuverability e3 and the regularity e4;
S48, according to formulas in S46 and S47, obtaining the generalized superior target weight distance dsA and the generalized poor target weight distance dsB of all decisions in the set D, and calculating a relative proximity index Cs of the appropriate expected trajectory decision for each expected trajectory decision according to the following formula:
C
s
=
d
s
B
d
s
A
+
d
s
B
,
comparing a difference between an actual driving route and an optimal centerline path in a multi-objective decision process of the driver by using the following optimization objective function:
f=max(Cs),
wherein when the difference is small, an actual trajectory distribution approaches a road centerline, indicating that a convergence of the road risk assessment model based on the equivalent force distribution is good.

### Claim 6

A real-time assessment device of driving risk based on equivalent force, comprising:
an information collecting unit, wherein the information collecting unit is configured to collect traffic environment information and various types of traffic environment use object information in a road environment in an area to be assessed; and
an electronic control unit, wherein electronic control unit is preset with a road risk assessment model based on an equivalent force distribution, the electronic control unit is configured to receive the traffic environment information and the various types of traffic environment use object information collected by the information collection unit;
wherein the road risk assessment model is used to acquire a road traffic risk E of a vehicle i and an equivalent force distribution Fij between the vehicle i and an object j in different traffic environments, and the object j represents any traffic element other than the vehicle i in the various types of traffic environment use object information, the road traffic risk E is expressed as a sum of kinetic energy Ei of the vehicle i, kinetic energy Ej of the object j, and relative kinetic energy Eij between the vehicle i and the object j.

### Claim 7 (depends on 6)

The real-time assessment device according to claim 6, wherein Eij and Fij in S3 are defined as follows:
E
ij
=
1
2
⁢
m
i
⁢
v
i
·
v
ij
⁡
(
cos
⁢
θ
ij
*
-
tan
⁢
θ
ij
⁢
sin
⁢
⁢
θ
ij
*
)
;
F
ij
=
1
2
⁢
w
ki
⁢
w
kj
⁢
F
ij
,
max
;
wherein Fij,max represents a maximum equivalent force on the object j loaded by the vehicle i, and is expressed as:
F
ij
,
max
=
1
2
⁢
m
i
⁢
v
i
·
v
ij
⁡
(
cos
⁢
⁢
θ
ij
*
-
tan
⁢
⁢
θ
ij
⁢
sin
⁢
⁢
θ
ij
*
)
d
ij
;
wherein, mi represents a mass of the vehicle i; vi represents a speed of the vehicle i; vij represents a relative speed between the vehicle i and the object j; dij represents a relative distance between the vehicle i and the object j; vi, vij, dij each is a vector, θij is an angle from dij to vij, θij* is an angle from dij to vi, a counterclockwise direction is defined as positive; wki is a probability weight of the vehicle i to maintain a current wheel angle and to change the current wheel angle; wkj is a probability weight of the object j to maintain an angle of a current state and to change the angle of the current state.

### Claim 8 (depends on 7)

The real-time assessment device according to claim 7, wherein
w
ki
=
p
ki
⁡
(
δ
ki
)
p
0
⁡
(
δ
0
)
;
w
kj
=
p
kj
⁡
(
δ
kj
)
p
0
⁡
(
δ
0
)
;
the object j is defined as a vehicle, wkj represents a probability weight of a vehicle j to maintain the current wheel angle and to change the current wheel angle; pki(δki) represents a steering probability of the vehicle i at a next moment steering angle along a steering angle δki; pkj(δkj) represents a steering probability of the vehicle j at the next moment steering angle along a steering angle δkj; δ0=0 indicates straight-line driving, p0(δ0) indicates a probability that the vehicle i and the vehicle j go straight;
pki(δki), pkj(δkj), p0(δ0) are obtained by the following calculation expression:
p
k
⁡
(
δ
k
)
=
1
3
.
7
⁢
7
⁢
0
⁢
4
*
⁢
2
⁢
π
⁢
e
-
δ
k
2
28.431
⁢
8
,
⁢
δ
k
=
k
*
Δδ
,
k
∈
[
-
n
,
n
]
,
wherein k, n∈Z; Δδ represents an increment of a steering angle; when k is a positive integer, δk means turning to left; when k is a negative integer, δk means turning to right.

### Claim 9 (depends on 6)

The real-time assessment device according to claim 6, further comprising:
a verification module, wherein the verification module is used for verifying a rationality of steering probability of the vehicle according to distribution law of a possible trajectory of a driver, based on the equivalent force distribution Fij.

### Claim 10 (depends on 9)

The real-time assessment device according to claim 9, wherein a specific work of the verification module comprises:
taking a target weight distance ds of n feasible expected trajectory decisions s of the driver, s=1 . . . n, and forming a set D to be determined,
D={d1,d2,d3, . . . dn};
forming an evaluation index set by a security e1, an efficiency e2, a maneuverability e3 and a regularity e4 as follows:
E={e1,e2,e3,e4};
through the security e1, the efficiency e2, the maneuverability e3 and the regularity e4, using a relative membership matrix with evaluation indicators as follows to evaluate the n feasible expected trajectory decisions s,
M
t
=
[
m
11
m
12
…
m
1
⁢
n
m
21
m
2
⁢
2
…
m
2
⁢
n
m
31
m
3
⁢
2
…
m
3
⁢
n
m
41
m
4
⁢
2
…
m
4
⁢
n
]
=
(
m
s
⁢
u
)
4
*
n
;
defining an appropriate expected trajectory decision s having a greatest relative membership, in a form of:
Am=(A1,A2,A3,A4)T=(1,1,1,1)T;
defining an inappropriate expected trajectory decision s having a smallest relative membership, in a form of:
Bm=(B1,B2,B3,B4)T=(0,0,0,0)T;
expressing an evaluation indicator membership function of an expected trajectory decision s in vector form as:
ms=(m1s,m2s,m3s,m4s)T
representing a difference between an actual trajectory decision u and the appropriate expected trajectory decision s by a generalized superior target weight distance dsA as follows:
d
s
A
=
∑
i
=
1
4
⁢
[
w
s
⁡
(
A
s
-
m
s
⁢
u
)
]
p
p
;
wherein msu represents one of m1s,m2s,m3s,m4s;
expressing a difference between the actual trajectory decision u and the inappropriate expected trajectory decision by a generalized poor target weight distance dsB as follows:
d
s
B
=
∑
s
=
1
4
⁢
[
w
s
⁡
(
B
s
-
m
s
⁢
u
)
]
p
p
⁢
⁢
wherein
,
⁢
w
=
(
w
1
,
w
2
,
w
3
,
w
4
)
T
,
∑
s
=
1
4
⁢
w
s
=
1
;
p is a distance parameter, wherein p is called Hamming distance when p=1; p is called Euclidean distance when p=2;
ws represents a weight for the security e1, the efficiency e2, the maneuverability e3 and the regularity e4;
according to formulas as above, obtaining the generalized superior target weight distance dsA and the generalized poor target weight distance dsB of all the decisions in the set D,
and calculating a relative proximity index Cs of the appropriate expected trajectory decision for each expected trajectory decision according to the following formula:
C
s
=
d
s
B
d
s
A
+
d
s
B
,
comparing a difference between an actual driving route and an optimal centerline path a multi-objective decision process of the driver, is compared by using the following optimization objective function:
f=max(Cs),
wherein when the difference is small, an actual trajectory distribution approaches a road centerline, indicating that a convergence of the road risk assessment model based on the equivalent force distribution is good.

### Claim 11 (depends on 2)

The real-time assessment method according to claim 2, further comprising:
S4, based on the equivalent force distribution Fij obtained in S3, verifying a rationality of steering probability of the vehicle according to distribution law of a possible trajectory of a driver.

### Claim 12 (depends on 3)

The real-time assessment method according to claim 3, further comprising:
S4, based on the equivalent force distribution Fij obtained in S3, verifying a rationality of steering probability of the vehicle according to distribution law of a possible trajectory of a driver.

### Claim 13 (depends on 7)

The real-time assessment device according to claim 7, further comprising:
a verification module, wherein the verification module is used for verifying a rationality of steering probability of the vehicle according to distribution law of a possible trajectory of a driver, based on the equivalent force distribution Fij.

### Claim 14 (depends on 8)

The real-time assessment device according to claim 8, further comprising:
a verification module, wherein the verification module is used for verifying a rationality of steering probability of the vehicle according to distribution law of a possible trajectory of a driver, based on the equivalent force distribution Fij.
