Barrier-free parking space navigation system and method based on path planning
By employing multi-source perception, data processing, and adaptive interaction technologies, the problems of lagging accessibility parking space information and incompatible route planning have been solved, enabling real-time navigation and personalized route planning, thus improving the user parking experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HANGZHOU YISHITONG TECH CO LTD
- Filing Date
- 2026-01-13
- Publication Date
- 2026-05-01
AI Technical Summary
Existing technologies suffer from outdated and poorly matched accessibility information for parking spaces, lack adaptability in route planning, and unsuitable interaction methods for specific user needs, resulting in a poor user parking experience.
The system employs a multi-source perception module to collect data, a data processing module to optimize the data and generate priority decision instructions, a path planning module to perform parking space selection and path planning, and an adaptive interaction module to provide personalized navigation information, including environmental perception, parking space status perception, user status and intent perception, combined with the A* algorithm and adaptive interaction technology.
It enables real-time synchronization of accessible parking space status, predicts the probability of parking space vacancy, plans suitable routes, lowers the barrier to entry, improves the accuracy of information transmission, and ensures user safety and comfort.
Smart Images
Figure CN121963524A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of accessible parking space navigation technology, specifically to an accessible parking space navigation system and method based on path planning. Background Technology
[0002] Accessible parking spaces are designated for motor vehicles driven or ridden by people with physical disabilities. These spaces are marked with a "wheelchair" symbol and are for vehicles used by people with disabilities. Vehicles for people with lower limb disabilities include rickshaws, motorcycles, and other motor vehicles. With the increasing popularity of accessible travel, various public places such as hospitals, shopping malls, and parks have standardized accessible parking spaces. These spaces must meet core requirements such as proximity to entrances / exits, spaciousness, and availability of ramps / charging ports to accommodate the parking needs of people with disabilities, the elderly, and those with strollers. However, many problems still exist when users park in accessible spaces, seriously affecting the travel experience of these users. Specific problems include: 1. Lagging and low matching accuracy of parking space information: Most existing parking lot navigation systems only synchronize the status of ordinary parking spaces. Key information such as the real-time occupancy status of accessible parking spaces, the availability of charging ports, and whether they are illegally occupied by ordinary vehicles cannot be updated in a timely manner, which often leads to users facing difficulties in finding a parking space or the parking space not matching the description after arriving at the parking lot. 2. Lack of accessibility adaptation in route planning: Conventional navigation only aims at the shortest distance and does not consider the travel obstacles of special users. For example, the planned route may contain sections of road that are impassable, such as steps, steep slopes, and narrow passages, which may cause users to find a parking space but not be able to reach it; some routes may be passable, but require multiple turns and detours on long slopes, which increases physical exertion. 3. Insufficient adaptability of interaction methods: The existing navigation interface and prompts are not optimized for special users. For example, visually impaired users have difficulty recognizing the text and graphics on the screen, and users with physical disabilities find it inconvenient to operate complex buttons. In addition, the voice prompts are mostly at a fixed speed and volume. In noisy environments such as hospital entrances with heavy traffic or in dimly lit environments such as underground parking garages, users cannot clearly receive navigation information.
[0003] In view of this, a barrier-free parking space navigation system and method based on path planning is proposed. Summary of the Invention
[0004] To address the shortcomings of existing technologies, this invention provides a path planning-based barrier-free parking space navigation system and method, which solves the problems of delayed and low matching of parking space information, lack of barrier-free adaptation in path planning, and insufficient adaptability of interaction methods when users park in barrier-free parking spaces.
[0005] To achieve the above objectives, the first aspect of the present invention provides a barrier-free parking space navigation system based on path planning, comprising: A multi-source sensing module is used to collect parking-related data, including parking lot environment data, accessible parking space status data, user status data, and user intent data. The data processing module is used to receive parking-related data, optimize the data, output standardized data, and generate priority decision instructions based on the user's real-time status and intent data. The route planning module performs qualified parking space screening and route planning based on standardized data and priority decision instructions, and outputs a qualified parking space and route combination scheme. An adaptive interaction module is used to receive a combination of qualified parking spaces and routes, and to determine the interaction method based on parking lot environment data and user status data to push navigation information.
[0006] The present invention is further configured such that: the multi-source sensing module includes an environment sensing unit, a parking space status sensing unit, and a user status and intent sensing unit; The environmental sensing unit is used to collect parking lot environmental data; the parking lot environmental data includes lane width, ramp slope, ambient noise, and light intensity. The parking space status sensing unit is used to collect accessible parking space status data; the accessible parking space status data includes parking space occupancy status and charging interface status; The user status and intent perception unit is used to collect user status data and user intent data; the user status data includes user heart rate and wheelchair movement speed; the user intent data includes charging needs, whether it is near an elevator, and whether it has a need for a ramp.
[0007] The present invention is further configured such that: the data processing module includes a data fusion unit, a user profiling and demand understanding unit, and a decision-making unit; The data fusion unit is used to correct and optimize parking-related data through Kalman filtering, and obtain standardized data after filtering valid data with confidence. The user profiling and demand understanding unit is used to binarize user intent data to obtain a comprehensive demand value and then generate user demand instructions. The decision-making unit predicts the probability of parking space vacancy based on standardized data and user demand instructions, and generates priority decision instructions. The formula for calculating the probability of parking space vacancy is: ; In the formula, This represents the probability of a parking space being vacant. This represents the number of idle times during the same historical period for the target time period. This represents the total number of occurrences in the same historical period for the target timeframe. This is a time period correction factor.
[0008] The present invention is further configured such that: the path planning module includes an adaptation evaluation unit, a multi-objective path planning unit, and an alternative scheme generation and interpretation unit; The adaptation evaluation unit is used to calculate the adaptation score of each available parking space and output a list of qualified parking spaces; The multi-objective path planning unit calculates the optimal path from the user's current location to each qualified parking space in the list of qualified parking spaces based on the A* algorithm; The alternative solution generation and interpretation unit is used to establish a mapping relationship between qualified parking spaces and corresponding optimal routes, sort qualified parking spaces in descending order according to the suitability score, filter the top three qualified parking spaces, obtain the three qualified parking spaces and route combination schemes, and mark the differences in information such as whether charging is available, whether it is near an elevator, and ramp information.
[0009] The present invention is further configured such that: the adaptive interaction module includes a multi-channel output unit, an adaptive interaction mode switching unit, and a contextualized information push unit; The multi-channel output unit is used to generate navigation information based on the qualified parking space and route combination scheme after the user selects the scheme and send it to the user terminal; the user terminal includes a mobile APP, a vehicle screen, a smart cane, and a smartwatch; the navigation information includes specific distance, turning directions, and facility prompts; The adaptive switching unit for interaction modes determines the interaction method based on parking lot environment data and user status data. When the ambient noise exceeds a preset threshold, the vibration and prompt font size control commands are triggered. When the light intensity is less than a preset threshold, the screen brightness is adjusted and the voice control command is amplified. When the user's heart rate is higher than a preset threshold and the wheelchair's movement speed is lower than a preset threshold, the voice prompt is simplified and a rest reminder is triggered. The contextualized information push unit pushes prompts based on the distance threshold of key nodes for real-time navigation; the key nodes include ramp entrances, elevator entrances, and turns.
[0010] Another aspect of the present invention provides a barrier-free parking space navigation method based on path planning, specifically including the following steps: S1. The multi-source sensing module collects parking lot environmental data, accessible parking space status data, user status data, and user intent data and transmits them to the data processing module. S2. The data processing module uses Kalman filtering to correct and optimize parking lot environment data, accessible parking space status data, user status data and user intent data. After filtering the valid data with confidence, it combines the comprehensive demand value and the probability of parking space vacancy to output standardized data and priority decision instructions and push them to the path planning module. S3. The route planning module filters qualified parking spaces through adaptability scoring, uses the A* algorithm to obtain three qualified parking space and route combination schemes and pushes them to the adaptive interaction module. S4, the adaptive interaction module is used to receive parking space and route combination schemes, and determine the interaction method based on parking lot environment data and user status data to push navigation information; S5. During navigation, if at least one of the following is detected: a sudden change in slope gradient, a change in parking space status, or an abnormal user heart rate, repeat operations S2-S4.
[0011] This invention provides a barrier-free parking space navigation system and method based on path planning. It has the following beneficial effects: This invention ensures that accessible parking spaces meet user needs while shortening the time users spend searching for spaces by real-time synchronization of accessible parking space status and facility availability, combined with parking space vacancy probability prediction and intelligent matching of user needs. It incorporates accessibility parameters into the A* algorithm to plan and obtain paths that adapt to user needs, providing support for users to easily reach accessible parking spaces. Furthermore, the adaptive interaction mode switching can accurately adapt to different users, lowering the usage threshold, improving the accuracy of information transmission, ensuring that users clearly receive navigation information, and monitoring user status and path status in real time throughout the navigation process, further ensuring travel safety and comfort. Attached Figure Description
[0012] Figure 1 This is a schematic diagram of the system architecture of the present invention; Figure 2 This is a schematic diagram of the system architecture of the multi-source sensing module and data processing module of the present invention; Figure 3 This is a schematic diagram of the system architecture of the path planning module of the present invention; Figure 4 This is a schematic diagram of the system architecture of the adaptive interaction module of the present invention. Detailed Implementation
[0013] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
[0014] Please see Figure 1-4The first aspect of this invention provides a path planning-based barrier-free parking space navigation system, comprising a multi-source sensing module, a data processing module, a path planning module, and an adaptive interaction module that are sequentially interconnected. The multi-source sensing module is used to collect parking-related data, including parking lot environment data, barrier-free parking space status data, user status data, and user intent data, wherein the user status data is also transmitted to the adaptive interaction module. The data processing module is used to receive parking-related data, optimize the data, and output standardized data, and generate priority decision instructions based on the user's real-time status and intent data. The path planning module performs parking space qualification screening and path planning based on the standardized data and priority decision instructions, and outputs a qualified parking space and path combination scheme. The adaptive interaction module is used to receive the qualified parking space and path combination scheme, and determine the interaction mode based on the parking lot environment data and user status data to push navigation information.
[0015] In an exemplary embodiment, the multi-source sensing module includes an environmental sensing unit, a parking space status sensing unit, and a user status and intent sensing unit; the environmental sensing unit is used to collect parking lot environmental data; the parking lot environmental data includes lane width, ramp slope, environmental noise, and light intensity, with a SICKTiM781 LiDAR to collect lane width data, a WDD35D4 tilt sensor to collect ramp slope data, and a noise / light sensor to collect parking lot noise and light intensity.
[0016] The parking space status sensing unit is used to collect accessible parking space status data. Accessible parking space status data includes parking space occupancy status and charging interface status. A TMR2501 geomagnetic sensor is embedded in the center of each accessible parking space to detect the parking space occupancy status, and an FSR402 contact sensor is installed at the charging gun of the parking space with the charging interface to detect the charging interface status.
[0017] The user status and intent perception unit is used to collect user status data and user intent data; user status data includes user heart rate and wheelchair movement speed; user intent data includes charging needs, whether the user is near an elevator, and whether the user needs a ramp.
[0018] In an exemplary embodiment, the data processing module includes a data fusion unit, a user profiling and demand understanding unit, and a decision-making unit. The data fusion unit is used to correct and optimize parking-related data through Kalman filtering, and after filtering valid data based on confidence level, obtain standardized data. Specifically, it calculates the confidence level using the following formula: ; In the formula, The number of times the same data is collected. For the first The second collected value, for The mean of the collected values; exist At that time, it was determined to be valid data.
[0019] The user profiling and demand understanding unit is used to binarize user intent data to obtain a comprehensive demand value, and then generate user demand instructions. Specific methods include: Binarization processing: When a user has a charging need, the value is 1, otherwise the value is 0; when a user needs to be near an elevator, the value is 1, otherwise the value is 0; when a user does not need a ramp, the value is 1, otherwise the value is 0. The comprehensive demand value is calculated using the following formula: ; In the formula, For the comprehensive demand value, Values are assigned based on charging demand. Values are taken based on the demand for elevator access. Values are taken for cases where there is no ramp requirement. All are weighting coefficients, and .
[0020] Furthermore, the higher the overall demand value, the higher the priority, meaning that accessible parking spaces are allocated to users with high overall demand values first.
[0021] The decision-making unit predicts the probability of parking space vacancy based on standardized data and user demand instructions, and generates priority decision instructions. The formula for calculating the probability of parking space vacancy is: ; In the formula, This represents the probability of a parking space being vacant. This represents the number of idle times during the same historical period for the target time period. This represents the total number of occurrences in the same historical period for the target timeframe. This is a time period correction factor.
[0022] In an exemplary embodiment, the route planning module includes an adaptation evaluation unit, a multi-objective route planning unit, and an alternative solution generation and interpretation unit; the adaptation evaluation unit is used to calculate the adaptation score for each available parking space and output a list of qualified parking spaces. The formula for calculating the adaptation score is: ; ; ; ; In the formula, For compatibility rating, This is the slope adaptation coefficient. The slope of the ramp. For channel width adaptation coefficient, The width of the channel is in meters. The obstacle point adaptation coefficient. The number of obstacle points. This is the facility integrity coefficient; a value of 1 is assigned to complete supporting facilities, and a value of 0.8 is assigned to the missing item. All are weighting coefficients, and ; when When the time is right, it is determined to be a qualified parking space and recorded in the list of qualified parking spaces.
[0023] If no suitable parking space is available, the estimated time until a barrier-free parking space becomes available will be sent to the user based on the parking space vacancy probability calculation.
[0024] The multi-objective path planning unit calculates the optimal path from the user's current location to each available parking space in the list of available parking spaces based on the A* algorithm, where the cost function of the A* algorithm is: ; ; In the formula, The nodes passed from the starting point to the end point Total cost estimate, From the starting point to the node distance, For nodes The cost of unimpeded access to the destination.
[0025] The alternative solution generation and interpretation unit is used to establish the mapping relationship between qualified parking spaces and corresponding optimal routes, sort qualified parking spaces in descending order according to the suitability score, filter the top three qualified parking spaces, obtain the three qualified parking spaces and route combination schemes, and mark the differences in information such as whether charging is available, whether it is near an elevator, and ramp information.
[0026] In an exemplary embodiment, the adaptive interaction module includes a multi-channel output unit, an adaptive interaction mode switching unit, and a contextualized information push unit; the multi-channel output unit is used to generate navigation information based on the qualified parking space and route combination scheme after the user selects the qualified parking space and route combination scheme and send it to the user terminal; the user terminal includes a mobile APP, an in-vehicle screen, a smart cane, and a smartwatch; the navigation information includes specific distance, turning directions, and facility prompts.
[0027] The interactive mode adaptive switching unit determines the interaction method based on parking lot environment data and user status data: When the ambient noise exceeds a preset threshold, such as >70dB, trigger vibration and increase the size of the prompt font control command; When the light intensity is less than a preset threshold, such as <50 lux, the screen brightness is adjusted and the voice control command is amplified. When the user's heart rate is higher than a preset threshold, such as >110 beats / min, and the wheelchair's movement speed is lower than a preset threshold, such as <0.5km / h, the voice prompt is simplified and a rest prompt is triggered.
[0028] As a detailed explanation, in scenarios where wheelchair users are in a shopping mall parking lot with noise levels of 60dB and sufficient lighting (>50lux), only voice and text reminders will be used, with the voice message played at 50% volume and the text message in 24-point font. When a wheelchair user moves to the parking lot entrance and a truck passes by, the noise level is 80dB > 70dB. Immediately increase the voice volume from 50% to 80%, and at the same time control the phone to vibrate at a frequency of 2 seconds per vibration, and enlarge the text to size 32 to ensure that the user can receive the information. After 10 minutes of navigation, the heart rate of wheelchair users rose from 80 beats per minute to 110 beats per minute. The voice was automatically simplified, such as from "Turn left 10m ahead to enter the B area passage, the passage width is 2m" to "Turn left ahead, go to the B area, no uphill", reducing the user's memory burden and prompting wheelchair users to choose the nearest rest.
[0029] The contextualized information push unit pushes prompts based on the distance threshold of key nodes for real-time navigation; key nodes include ramp entrances, elevator entrances, and turns.
[0030] Another aspect of the present invention provides a barrier-free parking space navigation method based on path planning, specifically including the following steps: S1. The multi-source sensing module collects parking lot environmental data, accessible parking space status data, user status data, and user intent data and transmits them to the data processing module. S2. The data processing module uses Kalman filtering to correct and optimize parking lot environment data, accessible parking space status data, user status data and user intent data. After filtering the valid data with confidence, it combines the comprehensive demand value and the probability of parking space vacancy to output standardized data and priority decision instructions and push them to the path planning module. S3. The route planning module filters qualified parking spaces through adaptability scoring, uses the A* algorithm to obtain three qualified parking space and route combination schemes and pushes them to the adaptive interaction module. S4, the adaptive interaction module is used to receive parking space and route combination schemes, and determine the interaction method based on parking lot environment data and user status data to push navigation information; S5. During navigation, if at least one of the following is detected: a sudden change in slope gradient, a change in parking space status, or an abnormal user heart rate, repeat operations S2-S4.
[0031] As an extension, after the user selects a suitable parking space, a parking space reservation is made: when the user passes through the parking lot gate, the target suitable parking space is automatically reserved, navigation is activated, and the parking space is locked and marked as in use. If the user does not enter the target suitable parking space within a set time period, such as 10 minutes, the reservation is canceled, the parking space is unlocked, and it is marked as available.
[0032] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A barrier-free parking space navigation system based on path planning, characterized in that, include: A multi-source sensing module is used to collect parking-related data, including parking lot environment data, accessible parking space status data, user status data, and user intent data. The data processing module is used to receive parking-related data, optimize the data, output standardized data, and generate priority decision instructions based on the user's real-time status and intent data. The route planning module performs qualified parking space screening and route planning based on standardized data and priority decision instructions, and outputs a qualified parking space and route combination scheme. An adaptive interaction module is used to receive a combination of qualified parking spaces and routes, and to determine the interaction method based on parking lot environment data and user status data to push navigation information.
2. The barrier-free parking space navigation system based on path planning according to claim 1, characterized in that, The multi-source perception module includes an environment perception unit, a parking space status perception unit, and a user status and intent perception unit. The environmental sensing unit is used to collect parking lot environmental data; the parking lot environmental data includes lane width, ramp slope, ambient noise, and light intensity. The parking space status sensing unit is used to collect accessible parking space status data; the accessible parking space status data includes parking space occupancy status and charging interface status; The user status and intent perception unit is used to collect user status data and user intent data; the user status data includes user heart rate and wheelchair movement speed; the user intent data includes charging needs, whether it is near an elevator, and whether it has a need for a ramp.
3. The barrier-free parking space navigation system based on path planning according to claim 2, characterized in that, The data processing module includes a data fusion unit, a user profiling and demand understanding unit, and a decision-making unit. The data fusion unit is used to correct and optimize parking-related data through Kalman filtering, and obtain standardized data after filtering valid data with confidence. The user profiling and demand understanding unit is used to binarize user intent data to obtain a comprehensive demand value and then generate user demand instructions. The decision-making unit predicts the probability of parking space vacancy based on standardized data and user demand instructions, and generates priority decision instructions. The formula for calculating the probability of parking space vacancy is: ； In the formula, This represents the probability of a parking space being vacant. This represents the number of idle times during the same historical period for the target time period. This represents the total number of occurrences in the same historical period for the target timeframe. This is a time period correction factor.
4. The barrier-free parking space navigation system based on path planning according to claim 3, characterized in that, The confidence level screening method includes: The confidence level is calculated using the following formula: ； In the formula, The number of times the same data is collected. For the first The second collected value, for The mean of the collected values; exist At that time, it was determined to be valid data.
5. The barrier-free parking space navigation system based on path planning according to claim 3, characterized in that, The methods for binarizing user intent data to obtain a comprehensive demand value include: Binarization processing: When a user has a charging need, the value is 1, otherwise the value is 0; when a user needs to be near an elevator, the value is 1, otherwise the value is 0; when a user does not need a ramp, the value is 1, otherwise the value is 0. The comprehensive demand value is calculated using the following formula: ； In the formula, For the comprehensive demand value, Values are assigned based on charging demand. Values are taken based on the demand for elevator access. Values are taken for cases where there is no ramp requirement. All are weighting coefficients, and .
6. The barrier-free parking space navigation system based on path planning according to claim 5, characterized in that, The path planning module includes an adaptation evaluation unit, a multi-objective path planning unit, and an alternative scheme generation and interpretation unit. The adaptation evaluation unit is used to calculate the adaptation score of each available parking space and output a list of qualified parking spaces; The multi-objective path planning unit calculates the optimal path from the user's current location to each qualified parking space in the list of qualified parking spaces based on the A* algorithm; The alternative solution generation and interpretation unit is used to establish a mapping relationship between qualified parking spaces and corresponding optimal routes, sort qualified parking spaces in descending order according to the suitability score, filter the top three qualified parking spaces, obtain the three qualified parking spaces and route combination schemes, and mark the differences in information such as whether charging is available, whether it is near an elevator, and ramp information.
7. The barrier-free parking space navigation system based on path planning according to claim 6, characterized in that, The formula for calculating the fit score is: ； In the formula, For compatibility rating, This is the slope adaptation coefficient. For channel width adaptation coefficient, The obstacle point adaptation coefficient. The facility integrity coefficient. All are weighting coefficients, and ; when When the time is right, it is determined to be a qualified parking space and recorded in the list of qualified parking spaces.
8. The barrier-free parking space navigation system based on path planning according to claim 6, characterized in that, The cost function of the A* algorithm is: ； ； In the formula, The nodes passed from the starting point to the end point Total cost estimate, From the starting point to the node distance, For nodes The cost of unimpeded access to the destination.
9. The barrier-free parking space navigation system based on path planning according to claim 2, characterized in that, The adaptive interaction module includes a multi-channel output unit, an adaptive switching unit for interaction modes, and a contextualized information push unit. The multi-channel output unit is used to generate navigation information and send it to the user terminal; the user terminal includes a mobile APP, a vehicle screen, a smart cane, and a smartwatch; the navigation information includes specific distance, turn directions, and facility prompts; The adaptive switching unit for interaction modes determines the interaction method based on parking lot environment data and user status data. When the ambient noise exceeds a preset threshold, the vibration and prompt font size control commands are triggered. When the light intensity is less than a preset threshold, the screen brightness is adjusted and the voice control command is amplified. When the user's heart rate is higher than a preset threshold and the wheelchair's movement speed is lower than a preset threshold, the voice prompt is simplified and a rest reminder is triggered. The contextualized information push unit pushes prompts based on the distance threshold of key nodes for real-time navigation; the key nodes include ramp entrances, elevator entrances, and turns.
10. A barrier-free parking space navigation method based on path planning, characterized in that, Specifically, the following steps are included: S1. The multi-source sensing module collects parking lot environmental data, accessible parking space status data, user status data, and user intent data and transmits them to the data processing module. S2. The data processing module uses Kalman filtering to correct and optimize parking lot environment data, accessible parking space status data, user status data and user intent data. After filtering the valid data with confidence, it combines the comprehensive demand value and the probability of parking space vacancy to output standardized data and priority decision instructions and push them to the path planning module. S3. The route planning module filters qualified parking spaces through adaptability scoring, uses the A* algorithm to obtain three qualified parking space and route combination schemes and pushes them to the adaptive interaction module. S4, the adaptive interaction module is used to receive parking space and route combination schemes, and determine the interaction method based on parking lot environment data and user status data to push navigation information; S5. During navigation, if at least one of the following is detected: a sudden change in slope gradient, a change in parking space status, or an abnormal user heart rate, repeat operations S2-S4.