CN115482659A - Intelligent agent autonomous decision-making method based on deep reinforcement learning - Google Patents
Intelligent agent autonomous decision-making method based on deep reinforcement learning Download PDFInfo
- Publication number
- CN115482659A CN115482659A CN202210992167.5A CN202210992167A CN115482659A CN 115482659 A CN115482659 A CN 115482659A CN 202210992167 A CN202210992167 A CN 202210992167A CN 115482659 A CN115482659 A CN 115482659A
- Authority
- CN
- China
- Prior art keywords
- time
- objects
- turning
- road
- comparison
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
-
- 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
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Abstract
The invention discloses an intelligent agent autonomous decision method based on deep reinforcement learning, which relates to the technical field of intelligent agent autonomous decision, and is characterized in that basic data is acquired aiming at intersections in a forbidden bid state to obtain license plate numbers, right turn time and vehicle identifications of all comparison objects; the comparison object is automatically deleted after being stored for T1 time; then, initially screening all potential objects, and determining all initially suspected objects and corresponding interval time thereof according to comparison among license plate numbers, entry time and vehicle identifications of real objects and license plate numbers, right turn time and vehicle identifications of comparison objects; and performing secondary audit on the first suspected object again, determining the illegal object through the secondary audit, facilitating the processing of law enforcement departments, and solving the problem that potential safety hazards are caused because the problem cannot be processed in the prior art.
Description
Technical Field
The invention belongs to the technical field of autonomous decision making, and particularly relates to an intelligent autonomous decision making method based on deep reinforcement learning.
Background
Patent No. CN111833597A discloses autonomous decision making in traffic situations with planning control. A control device for generating maneuver decisions in a traffic scenario for an autonomous vehicle is proposed. The control device comprises a first module comprising a trained self-learning model, the first module being configured to receive data comprising information about a surrounding environment of the autonomous vehicle, determine an action to be performed by the autonomous vehicle based on the received data by means of the trained self-learning model. The control device includes a second module configured to receive the determined action, receive data including information about an ambient environment of the autonomous vehicle during a limited time range, predict an environmental state of a first time period of the limited time range, determine a trajectory of the autonomous vehicle based on the received action of the limited time range and the environmental state of the first time period, transmit a signal to control the autonomous vehicle during the first time period according to the determined trajectory.
However, for the patent, an important part is still lacked for the autonomous decision of a traffic scene, in the existing road condition driving process, the red light is often avoided by a mode of turning right in advance and turning right again after turning around under the condition of straight driving of the red light, of course, under the normal condition, the driving modes are allowed, but in the existing process, the condition of turning around illegally after turning around is often existed, so that some potential safety hazards are caused, and in order to solve the problem, a solution is provided.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art; therefore, the invention provides an intelligent agent autonomous decision-making method based on deep reinforcement learning.
In order to achieve the above object, an embodiment according to a first aspect of the present invention provides an intelligent agent autonomous decision method based on deep reinforcement learning, which specifically includes the following steps:
the method comprises the following steps: the method comprises the following steps of acquiring basic data aiming at a crossing in a label forbidden state, wherein the specific mode is as follows:
all pictures of vehicles turning right are obtained and marked as comparison objects when the intersection commanded by the target object is in a target forbidding state;
the license plate numbers, right turn time and vehicle identifications of all comparison objects are synchronously and automatically acquired; the comparison object is automatically deleted after being stored for T1 time;
step two: then, initially screening all potential objects, and determining all initially suspected objects and corresponding interval time thereof according to comparison among license plate numbers, entry time and vehicle identifications of real objects and license plate numbers, right turn time and vehicle identifications of comparison objects;
step three: and (3) carrying out secondary audit on the initial suspected object, wherein the specific mode of the secondary audit is as follows:
s1: acquiring all initial suspected objects and corresponding interval time thereof;
s2: then acquiring a road before turning of the initial suspected object into the target object commanding road, wherein the road before turning is a road where the initial suspected object is located when turning right into the target object, acquiring an object lane of the road before turning, and marking the object lane as a lane inserted by the lane;
s3: acquiring the distance between the right turn of the target object command road and the intersection position of the inserted lane and the turning point position of the inserted lane, and marking the distance as the turning distance, wherein the turning point refers to the turning point where the vehicle can turn;
s4: then the distance from the turning point to the up-to-standard object command road from the road before turning is acquired, and the distance is marked as the distance in the rule;
s5: acquiring a first speed limit value of the inserted lane, and dividing the U-turn distance by the first speed limit value to obtain a U-turn list;
then acquiring a second speed limit value of the road before turning, and dividing the distance in the gauge by the second speed limit value to obtain a second turning time; adding a second turning time to the first turning time to obtain short time limit;
s6: marking the initial suspected object with the interval time exceeding the short limit as a speculative object;
s7: all the speculative objects are obtained.
Compared with the prior art, the invention has the beneficial effects that:
the invention obtains the license plate numbers, right-turn time and vehicle identifications of all comparison objects by acquiring basic data of the intersections in the state of forbidden marks; the comparison object is automatically deleted after being stored for T1 time; then, performing initial screening on all potential objects, and determining all initial suspected objects and corresponding interval time thereof according to comparison among license plate numbers, entry time and vehicle identifications of real objects and license plate numbers, right turn time and vehicle identifications of comparison objects;
and performing secondary audit on the first suspected object again, determining the illegal object through the secondary audit, facilitating the processing of law enforcement departments, and solving the problem that potential safety hazards are caused because the problem cannot be processed in the prior art.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The application provides an intelligent agent autonomous decision method based on deep reinforcement learning, which specifically comprises the following steps of:
the method comprises the following steps: synchronizing the state of the target object, starting autonomous decision-making judgment when any driving direction is in a target forbidden state, and keeping silence in other states; any driving direction is the direction of the road which is in charge of commanding the traffic light and can be driven;
the target object refers to a traffic light, and the state of the target object is the specific red, green and yellow real-time state of the traffic light; the no-marking state is a state that vehicles in the straight-going direction corresponding to the straight-going lane are in red light no-passing;
step two: basic data acquisition is carried out on the intersection in the state of forbidden marks, and the specific mode is as follows:
when the intersection instructed by the target object is in a mark forbidden state, all pictures of vehicles turning right are marked as comparison objects, and license plate numbers, right-turning time and vehicle identifications of all comparison objects are synchronously and automatically acquired; the right-turn time is the specific time point of the corresponding comparison object in the right turn; the comparison object is automatically deleted after being stored for T1 time, wherein T1 is a preset numerical value, is usually taken for fifteen minutes, and can be set to other numerical values;
the vehicle mark refers to the color of a vehicle engine hood and the brand of the vehicle, and the brand of the vehicle can be known by automatically identifying the brand through a camera;
step three: and then carrying out initial screening on all potential objects, wherein the specific mode of the initial screening is as follows:
s01: acquiring pictures of all vehicles entering a road instructed by a target object through right turning, marking the corresponding vehicles as real entering objects through image identification, and acquiring license plate numbers, entering time and vehicle identifications of all the real entering objects; the entry time is a time node for the real entry object to enter the road commanded by the target object;
s02: firstly, comparing every two real objects with a comparison object, comparing whether license plate numbers and vehicle identifications of the real objects and the comparison object are consistent or not, and if the license plate numbers and the vehicle identifications of the real objects and the comparison object are consistent, marking the consistent real objects as initial doubt objects;
s03: synchronously obtaining interval time according to the entry time of the initial suspected object and the right turn time of the comparison object, wherein the interval time is determined according to the time length of the interval from the entry time to the right turn time;
s04: obtaining all initial doubt objects and corresponding interval time thereof;
step four: and performing secondary audit on the initial suspected object, wherein the secondary audit has the specific mode that:
s1: acquiring all initial suspected objects and corresponding interval time thereof;
s2: then acquiring a road before turning of the initial suspected object into the target object commanding road, wherein the road before turning is a road where the initial suspected object is located when turning right into the target object, acquiring an object lane of the road before turning, and marking the object lane as a lane inserted by the lane; the lane crossing meets the requirement that the vehicle can enter through the right turn of the road instructed by the target object;
s3: acquiring the distance between the right turn of the target object command road and the intersection position of the inserted lane and the turning point position of the inserted lane, and marking the distance as the turning distance, wherein the turning point refers to the turning point where the vehicle can turn;
s4: then the distance from the turning point to the up-to-standard object command road from the road before turning is acquired, and the distance is marked as the distance in the rule;
s5: acquiring a first speed limit value of the inserted lane, and dividing the U-turn distance by the first speed limit value to obtain a U-turn list;
then acquiring a second speed limit value of the road before turning, and dividing the distance in the gauge by the second speed limit value to obtain a second turning time; adding a second turning time to the first turning time to obtain short time limit;
s6: marking the initial suspected object with the interval time exceeding the short limit as a speculative object;
s7: obtaining all speculative objects;
step five: all the speculative objects and pictures thereof are transmitted to the intelligent terminal ports of the corresponding supervision departments, so that the processing is convenient; the speculative object refers to the situation that a user turns around again after not waiting for turning around from a right turn road when going straight to a red light and does not turn around at a legal position so as to avoid the illegal situation of the traffic light;
as an embodiment two of the present invention, on the basis of the embodiment one, the step four of the present embodiment is slightly different from the embodiment one, and specifically includes:
step four: and performing secondary audit on the initial suspected object, wherein the secondary audit has the specific mode that:
s1: acquiring all initial suspected objects and corresponding interval time thereof;
s2: then acquiring a road before turning of the initial suspected object into the target object commanding road, wherein the road before turning is a road where the initial suspected object is located when turning right into the target object, acquiring an object lane of the road before turning, and marking the object lane as a lane inserted by the lane; the lane crossing meets the requirement that the vehicle can enter through the right turn of the road instructed by the target object;
s3: acquiring the distance between a right turn of a target object command road and an intersection position of a crossing lane and the turning point position of the crossing lane, marking the distance as the turning distance, and indicating that a vehicle can turn around at the turning point;
s4: then obtaining the distance from the turning point to the up-to-standard object command road from the front turning road, and marking the distance as an in-gauge distance;
s5: acquiring a first speed limit value of a vehicle lane which is inserted, and dividing the turning distance by the first speed limit value to obtain a turning list;
then acquiring a second speed limit value of the road before turning, and dividing the distance in the gauge by the second speed limit value to obtain a second turning time; adding a second turning time to the first turning time to obtain short time limit; if the vehicle is inserted through the lane and the turning position does not exist, marking the short time limit as 0;
the absence of the turning position is specifically indicated as follows:
the vehicle runs straight along the crossing lane, and no turning position exists before meeting the second traffic light and including the position of the second traffic light;
s6: marking the initial suspected object with the interval time exceeding the short limit as a speculative object;
s7: obtaining all speculative objects;
as an embodiment three of the present invention, on the basis of the embodiment one, after the processing of the step five, the present invention further needs to perform the following steps, specifically:
SS1: acquiring all the speculative objects and the time points marked as the speculative objects to obtain all the speculative objects and the speculative time points;
and (4) SS2: acquiring all the speculative objects at the current approaching stage from the distance and the times of marking the speculative objects as the speculative objects, and removing the times lower than X1, wherein X1 is a preset value and is generally 2; the approach stage is obtained by calculating three months from the current time;
and SS3: marking the rest speculative objects as inertial objects, and marking the times marked as the speculative objects as inertial times to obtain all the inertial objects and the inertial times;
and SS4: optionally, acquiring the interval time from the first time to the last time when the inertial object is marked as the speculative object, marking the interval time as the inter-projection period value corresponding to the marker Ji, i =1.. N, and indicating that n inter-projection period values exist, namely marking the interval time as the speculative object n +1 times;
and SS5: then, automatically calculating the average value of the Ji, marking the average value as P, and calculating the polymerization degree D of the Ji according to a formula, wherein the specific calculation formula is as follows:
and SS6: defining a doubling value according to the polymerization degree D, wherein when D is less than X2, the doubling value is equal to 2;
when X2 is more than or equal to D and less than or equal to X3, defining the doubling value to be 1.5;
when D > X3, defining the doubling value as 1;
and (7) SS: then, performing SS4-SS7 same processing on all the inertial objects to obtain doubling values of all the inertial objects;
and SS8: and calculating the weighing values of all the inertial objects by using a formula, wherein the specific formula is as follows:
the weighing value = inertia times multiplied by the doubling value;
and SS9: sorting the inertia objects according to the weighing values of the inertia objects from large to small, and marking the corresponding inertia objects which are ranked thirty-five percent first as habit objects;
and SS10: when the processing of any habit object in the third step of the embodiment is marked as an initial suspected object, the habit object is synchronously marked as a semi-speculative object, and the semi-speculative object is transmitted to an intelligent terminal port of a corresponding supervision department for processing.
As an embodiment four of the present invention, the embodiment one to the embodiment three are integrated in the concrete implementation.
Part of data in the formula is obtained by removing dimension and taking the value to calculate, and the formula is obtained by simulating a large amount of collected data through software and is closest to a real situation; the preset parameters and the preset threshold values in the formula are set by those skilled in the art according to actual conditions or obtained through simulation of a large amount of data.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (7)
1. An intelligent agent autonomous decision method based on deep reinforcement learning is characterized by specifically comprising the following steps:
the method comprises the following steps: the method comprises the following steps of acquiring basic data aiming at a crossing in a label forbidden state, wherein the specific mode is as follows:
all pictures of vehicles turning right are obtained and marked as comparison objects when the intersection commanded by the target object is in a target forbidding state;
the license plate numbers, right turn time and vehicle identifications of all comparison objects are synchronously and automatically acquired; the comparison object is automatically deleted after being stored for T1 time;
step two: then, performing initial screening on all potential objects, and determining all initial suspected objects and corresponding interval time thereof according to comparison among license plate numbers, entry time and vehicle identifications of real objects and license plate numbers, right turn time and vehicle identifications of comparison objects;
step three: and (3) carrying out secondary audit on the initial suspected object, wherein the specific mode of the secondary audit is as follows:
s1: acquiring all initial suspected objects and corresponding interval time thereof;
s2: then acquiring a road before turning of the initial suspected object into the target object commanding road, wherein the road before turning is a road where the initial suspected object is located when turning right into the target object, acquiring an object lane of the road before turning, and marking the object lane as a lane inserted by the lane;
s3: acquiring the distance between a right turn of a target object command road and an intersection position of a crossing lane and the turning point position of the crossing lane, marking the distance as the turning distance, and indicating that a vehicle can turn around at the turning point;
s4: then obtaining the distance from the turning point to the up-to-standard object command road from the front turning road, and marking the distance as an in-gauge distance;
s5: acquiring a first speed limit value of a vehicle lane which is inserted, and dividing the turning distance by the first speed limit value to obtain a turning list;
then acquiring a second speed limit value of the road before turning, and dividing the distance in the gauge by the second speed limit value to obtain a second turning time; adding a second turning time to the first turning time to obtain short time limit;
s6: marking the initial suspected object with the interval time exceeding the short limit as a speculative object;
s7: all the speculative objects are obtained.
2. The intelligent agent autonomous decision method based on deep reinforcement learning according to claim 1, characterized in that the following steps are further performed before the first step is performed, specifically:
synchronizing the state of the target object, starting autonomous decision-making judgment when the target object is in a label forbidden state, and keeping silence in other states.
3. The intelligent agent autonomous decision method based on deep reinforcement learning of claim 2, characterized in that the target object is designated as a traffic light; the no-mark state is a state that vehicles in the straight-going direction corresponding to the straight-going lane are in red light no-pass.
4. The intelligent agent autonomous decision method based on deep reinforcement learning according to claim 1, wherein the right turn time in the first step is a specific time point of the corresponding comparison object in the right turn;
vehicle identification refers to vehicle hood color and vehicle brand; and T1 is a predetermined value.
5. The intelligent agent autonomous decision method based on deep reinforcement learning according to claim 1, wherein the initial screening in the second step is specifically as follows:
s01: acquiring pictures of all vehicles entering a road instructed by the target object through right-turn, marking the pictures as real entering objects, and acquiring license plate numbers, entering time and vehicle identifications of all the real entering objects; the entry time is a time node for the real entry object to enter the road commanded by the target object;
s02: firstly, comparing the real object with the comparison object in pairs at will, comparing whether the license plate numbers and the vehicle identifications of the real object and the comparison object are consistent or not, and if so, marking the consistent real object as an initial doubt object;
s03: synchronously obtaining interval time according to the entry time of the initial suspected object and the right turn time of the comparison object, wherein the interval time is determined according to the time length of the interval from the entry time to the right turn time;
s04: all the first suspected objects and the corresponding interval time are obtained.
6. The intelligent agent autonomous decision method based on deep reinforcement learning according to claim 1, characterized in that the vehicle can enter through right turn of the road instructed by the target object by inserting the lane in step S2;
and in the step S5, if the vehicle is inserted through the lane and the U-turn position does not exist, marking the short consumed time as 0.
7. The intelligent agent autonomous decision method based on deep reinforcement learning according to claim 1, characterized in that after the processing of step three, the following steps are further performed:
and transmitting all the speculative objects to the intelligent terminal ports of the corresponding supervision departments.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210992167.5A CN115482659B (en) | 2022-08-18 | 2022-08-18 | Intelligent autonomous decision-making method based on deep reinforcement learning |
| JP2023051884A JP2024028097A (en) | 2022-08-18 | 2023-03-28 | Learning-based autonomous decision-making method based on advanced reinforcement learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210992167.5A CN115482659B (en) | 2022-08-18 | 2022-08-18 | Intelligent autonomous decision-making method based on deep reinforcement learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115482659A true CN115482659A (en) | 2022-12-16 |
| CN115482659B CN115482659B (en) | 2023-09-19 |
Family
ID=84422523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210992167.5A Active CN115482659B (en) | 2022-08-18 | 2022-08-18 | Intelligent autonomous decision-making method based on deep reinforcement learning |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP2024028097A (en) |
| CN (1) | CN115482659B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170364083A1 (en) * | 2016-06-21 | 2017-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Local trajectory planning method and apparatus for smart vehicles |
| CN108831168A (en) * | 2018-06-01 | 2018-11-16 | 江苏数翰信息科技有限公司 | A kind of method for controlling traffic signal lights and system based on association crossing visual identity |
| CN109949579A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method that makes a dash across the red light based on deep learning |
| WO2020192122A1 (en) * | 2019-03-27 | 2020-10-01 | 江苏智通交通科技有限公司 | Off-site law enforcement picture intelligent auditing method and system for vehicles running red light |
| WO2021093335A1 (en) * | 2019-11-14 | 2021-05-20 | Suzhou Zhijia Science & Technologies Co., Ltd. | Method for automatically labeling lane changing intention based on high-noise trajectory data of vehicle |
| CN113682312A (en) * | 2021-09-23 | 2021-11-23 | 中汽创智科技有限公司 | Autonomous lane changing method and system integrating deep reinforcement learning |
-
2022
- 2022-08-18 CN CN202210992167.5A patent/CN115482659B/en active Active
-
2023
- 2023-03-28 JP JP2023051884A patent/JP2024028097A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170364083A1 (en) * | 2016-06-21 | 2017-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Local trajectory planning method and apparatus for smart vehicles |
| CN108831168A (en) * | 2018-06-01 | 2018-11-16 | 江苏数翰信息科技有限公司 | A kind of method for controlling traffic signal lights and system based on association crossing visual identity |
| CN109949579A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method that makes a dash across the red light based on deep learning |
| WO2020192122A1 (en) * | 2019-03-27 | 2020-10-01 | 江苏智通交通科技有限公司 | Off-site law enforcement picture intelligent auditing method and system for vehicles running red light |
| WO2021093335A1 (en) * | 2019-11-14 | 2021-05-20 | Suzhou Zhijia Science & Technologies Co., Ltd. | Method for automatically labeling lane changing intention based on high-noise trajectory data of vehicle |
| CN113682312A (en) * | 2021-09-23 | 2021-11-23 | 中汽创智科技有限公司 | Autonomous lane changing method and system integrating deep reinforcement learning |
Non-Patent Citations (1)
| Title |
|---|
| 刘庆杰;林友勇;李少利;: "面向智能避障场景的深度强化学习研究", 智能物联技术, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115482659B (en) | 2023-09-19 |
| JP2024028097A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647839B (en) | Method and device for generating automatic driving strategy and computer readable storage medium | |
| CN110675656B (en) | Intelligent vehicle lane change early warning method based on instantaneous risk identification | |
| CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
| CN110077397B (en) | Intelligent vehicle obstacle avoidance trajectory planning method and device | |
| US8160811B2 (en) | Method and system to estimate driving risk based on a hierarchical index of driving | |
| JP6916552B2 (en) | A method and device for detecting a driving scenario that occurs during driving and providing information for evaluating a driver's driving habits. | |
| CN111212772A (en) | Method and device for determining a driving strategy of a vehicle | |
| CN112644498B (en) | Intelligent vehicle safety decision-making method based on driving safety field | |
| CN113212454B (en) | Method and device for adjusting running state of vehicle, computer equipment and storage medium | |
| CN107077606A (en) | For the method and apparatus for the travel situations for determining there is currently | |
| CN108665556B (en) | Road indication display method based on mixed reality and storage medium | |
| CN113851017A (en) | Pedestrian and vehicle identification and early warning multifunctional system based on road side RSU | |
| CN113674523A (en) | Traffic accident analysis method, device and equipment | |
| CN111063192A (en) | Operating area compliance judgment method and system | |
| CN111422202B (en) | Intelligent driving test judging method | |
| CN111539268A (en) | Road condition early warning method and device during vehicle running and electronic equipment | |
| CN112071066A (en) | Automatic driving vehicle testing method, judging method and device | |
| CN115482659A (en) | Intelligent agent autonomous decision-making method based on deep reinforcement learning | |
| JP2020149574A (en) | Compartment line deterioration specification system and compartment line deterioration specification method | |
| CN114998863B (en) | Target road identification method, device, electronic equipment and storage medium | |
| CN116128360A (en) | Road traffic congestion level evaluation method and device, electronic equipment and storage medium | |
| CN113593253A (en) | Method and device for monitoring red light running of vehicle | |
| CN110634120A (en) | Vehicle damage judgment method and device | |
| KR102187441B1 (en) | Distinguishable drone for abnormal driving | |
| CN116109711A (en) | Driving assistance method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |