CN-122009075-A - Emergency escape method, device, equipment and medium for vehicle

CN122009075ACN 122009075 ACN122009075 ACN 122009075ACN-122009075-A

Abstract

The embodiment of the application provides a vehicle emergency escape method, device, equipment and medium, wherein the method comprises the steps of determining a dangerous source existing in a vehicle, dangerous information of the dangerous source and safety scores of various initial escape exits of the vehicle according to the current vehicle internal environment information; and determining a target escape outlet according to the accumulated passing cost and the safety score, and sending multi-mode guiding information to the passengers. According to the embodiment of the application, the environment in the vehicle and the state of the passengers are perceived in real time, so that the personalized escape exits of the passengers are dynamically planned according to the environment information and the state of the passengers, the method is suitable for complex dangerous situations and individual differences, and the passengers are guided to escape through multi-mode guiding information, so that the escape success rate is effectively improved.

Inventors

DAI YU
CHEN XIAOJIE
PANG JING
WANG YUE
MIAO CHENGSHENG
LIU GUOZHI

Assignees

广州汽车集团股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260210

Claims (10)

1. An emergency escape method of a vehicle, comprising: Acquiring current environment information in a vehicle and passenger state information of passengers; Determining a dangerous source existing in the vehicle, dangerous information of the dangerous source, at least two initial escape exits of the vehicle and safety scores of the initial escape exits according to the environmental information; Determining the accumulated passing cost of the passengers from the current carriage position to each initial escape exit according to the passenger state information and the dangerous information; Selecting a target escape outlet from the initial escape outlets according to the accumulated passing cost and the safety score; And sending multi-mode guiding information to the passengers based on the target escape exits.
2. The method of claim 1, wherein the occupant status information includes occupant position, occupant age category, occupant pose, and occupant capacity coefficient, the method comprising: Collecting image data of the interior of the vehicle; Performing target recognition and gesture estimation on the image data to obtain the passenger position, the passenger age category and the passenger gesture of the passenger; and carrying out capability assessment on the passengers by adopting the passenger age categories and the passenger postures to obtain passenger capability coefficients of the passengers.
3. The method of claim 2, wherein said determining an accumulated traffic cost of the occupant from the current cabin location to each of the initial escape exits based on the occupant status information and the hazard information comprises: Calculating the passing cost of each carriage position of the vehicle based on the dangerous information; acquiring a personalized path planning algorithm; carrying out path planning on each initial escape exit by utilizing the personalized path planning algorithm based on the passenger position, the passenger capacity coefficient and the passing cost of each carriage position, and obtaining candidate paths of each initial escape exit; And calculating the accumulated passing cost of the initial escape exit based on the candidate path and the passing cost.
4. A method according to claim 3, wherein the hazard information includes a hazard intensity per unit distance of the hazard source, and the calculating a traffic cost for each compartment position of the vehicle based on the hazard information includes: calculating a dangerous distance between the carriage position and the dangerous source; Calculating a risk index of the carriage position based on the unit distance risk intensity and the risk distance; judging the position category of the carriage position, and acquiring the basic passing cost corresponding to the position category; and calculating the passing cost of the carriage position based on the basic passing cost and the danger index.
5. The method according to claim 4, wherein the method further comprises: acquiring characteristic information of the dangerous source, wherein the characteristic information at least comprises a highest temperature, smoke concentration, toxic gas concentration, an open flame mark and a battery fault level; And carrying out weighted fusion on the highest temperature, the smoke concentration, the toxic gas concentration, the open flame mark and the battery fault level to obtain the unit distance dangerous intensity of the dangerous source.
6. The method of claim 5, wherein the environmental information includes at least a temperature, a smoke concentration, and a toxic gas concentration, and wherein the determining a hazard source present inside the vehicle, hazard information for the hazard source, an initial escape exit of at least two of the vehicles, and a safety score for each of the initial escape exits based on the environmental information includes: performing risk assessment on each compartment position of the vehicle based on the temperature, the smoke concentration and the toxic gas concentration to obtain a comprehensive risk index of each compartment position; If the comprehensive risk index is larger than a preset risk threshold, marking the carriage position as a risk source, and acquiring coordinate information, the comprehensive risk index and the unit distance risk intensity of the risk source; Acquiring an initial escape outlet of the vehicle, and calculating a first distance between the initial escape outlet and the dangerous source; And calculating the safety score of the initial escape exit based on the first distance and the unit distance dangerous intensity of the dangerous source.
7. The method of claim 3, wherein the issuing of multi-modal guidance information to the occupant based on the target escape exit comprises: And sending out multi-mode guiding information to the passengers based on the escape route corresponding to the target escape exit, wherein the multi-mode guiding information comprises at least one of voice prompt information, light prompt information and text prompt information.
8. The method of claim 7, wherein the method further comprises: Detecting the passing cost of the carriage position, the safety score of the target escape exit and the passenger state information of the passenger in real time to obtain real-time detection information; judging whether to reprogram the escape route or not based on the real-time detection information and a preset reprogram condition; If yes, correcting the escape path to obtain a target escape path.
9. An electronic device comprising a processor and a memory, wherein A memory for storing a computer program; a processor for executing a program stored on a memory, implementing the method of any one of claims 1-8.
10. A vehicle comprising the electronic device of claim 9.

Description

Emergency escape method, device, equipment and medium for vehicle Technical Field The embodiment of the application relates to the technical field of emergency escape, in particular to an emergency escape method, device, equipment and medium for a vehicle. Background With the popularity of automobiles, vehicular fires have become an important safety hazard. Unlike traditional fire disaster, the vehicle has airtight internal space, concentrated combustible matters, limited escape outlet, and extremely short escape time of passengers, and can be accompanied by composite hazards such as toxic gas (such as carbon monoxide) and battery explosion. The existing vehicle fire emergency escape method generally controls the unlocking of a vehicle door according to a fixed physical threshold value, such as a specific temperature, gas concentration and the like, has delayed response, cannot cope with complex situations of changeable fire source positions and different passenger states, has uniform response modes, such as simultaneous unlocking of all vehicle doors, cannot provide differentiated escape guidance for passengers at different positions, can possibly guide the passengers into more dangerous areas, and can not adjust the guiding direction according to the dynamic spreading dangerous situations by normally-bright emergency lamps or uniform audible and visual alarms to further consider individual differences of the passengers. Disclosure of Invention The embodiment of the application provides an emergency escape method, device, equipment and medium for a vehicle, which aim to solve the problems that the existing emergency escape method cannot cope with complex and changeable dangerous situations and the state of passengers is not considered. In order to solve the above problems, an embodiment of the present application discloses an emergency escape method for a vehicle, the method comprising: Acquiring current environment information in a vehicle and passenger state information of passengers; Determining a dangerous source existing in the vehicle, dangerous information of the dangerous source, at least two initial escape exits of the vehicle and safety scores of the initial escape exits according to the environmental information; Determining the accumulated passing cost of the passengers from the current carriage position to each initial escape exit according to the passenger state information and the dangerous information; Selecting a target escape outlet from the initial escape outlets according to the accumulated passing cost and the safety score; And sending multi-mode guiding information to the passengers based on the target escape exits. In some possible implementations, the occupant state information includes occupant position, occupant age category, occupant posture, and occupant capacity coefficient, the method comprising: Collecting image data of the interior of the vehicle; Performing target recognition and gesture estimation on the image data to obtain the passenger position, the passenger age category and the passenger gesture of the passenger; and carrying out capability assessment on the passengers by adopting the passenger age categories and the passenger postures to obtain passenger capability coefficients of the passengers. In some possible implementations, the determining, according to the occupant status information and the danger information, an accumulated passing cost of the occupant from a current car position to each of the initial escape exits includes: Calculating the passing cost of each carriage position of the vehicle based on the dangerous information; acquiring a personalized path planning algorithm; carrying out path planning on each initial escape exit by utilizing the personalized path planning algorithm based on the passenger position, the passenger capacity coefficient and the passing cost of each carriage position, and obtaining candidate paths of each initial escape exit; And calculating the accumulated passing cost of the initial escape exit based on the candidate path and the passing cost. In some possible implementations, the hazard information includes a unit distance hazard intensity of the hazard source, and the calculating, based on the hazard information, a passing cost of each compartment position of the vehicle includes: calculating a dangerous distance between the carriage position and the dangerous source; Calculating a risk index of the carriage position based on the unit distance risk intensity and the risk distance; judging the position category of the carriage position, and acquiring the basic passing cost corresponding to the position category; and calculating the passing cost of the carriage position based on the basic passing cost and the danger index. In some possible implementations, the method further includes: acquiring characteristic information of the dangerous source, wherein the characteristic information at least comprises a highest temperature,