An intelligent environment monitoring and automatic obstacle avoidance system for wheelchairs

Abstract

The present invention discloses an intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair, which relates to the technical field of intelligent wheelchairs and comprises a monitoring center. The monitoring center is connected with a data acquisition module, a data processing module, a data analysis module and an automatic obstacle avoidance module. The monitoring center monitors environmental data in real time, thereby generating corresponding road surface blocks in a model, and associating corresponding road surface characteristic attributes with the road surface blocks according to the environmental data, so that a user can timely understand the road conditions in the road blind spots. At the same time, according to the driving data of the wheelchair and the environmental data, it is judged whether there is a risk in the current wheelchair driving of the user. If there is a risk, a corresponding avoidance instruction is generated according to the situation, thereby reducing the risk of the user during the wheelchair driving process.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent wheelchairs, and in particular to an intelligent environment monitoring and automatic obstacle avoidance system for wheelchairs. Background Art

[0002] An electric wheelchair is a specially designed chair with wheels that can be used by the elderly or people with limited mobility. It is a medical device that uses the wheels of the electric wheelchair to replace the user's feet to walk. When facing complex driving environments, existing electric wheelchairs often require users to judge the environment by themselves. This method undoubtedly increases the burden on users who are already mobility-impaired. At the same time, it is impossible to accurately judge the blind spots on the ground. How to make the wheelchair effectively monitor the environment in which it is located so that it can automatically avoid obstacles or abnormal road surfaces is a problem we need to solve. To this end, an intelligent environment monitoring and automatic obstacle avoidance system for wheelchairs is now provided. Summary of the invention

[0003] The object of the present invention is to provide an intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair.

[0004] The object of the present invention can be achieved by the following technical solutions: An intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair, comprising a monitoring center, wherein the monitoring center is connected to a data acquisition module, a data processing module, a data analysis module, and an automatic obstacle avoidance module; The data acquisition module is used to obtain environmental data of the wheelchair's location and wheelchair travel data; The data processing module is used to process the obtained environmental data and wheelchair travel data to obtain a field trend model of the wheelchair; The data analysis module is used to analyze the obtained environmental data and wheelchair driving data to determine whether there is a driving risk; The automatic obstacle avoidance module is used to construct a corresponding obstacle avoidance route in the domain trend model when there is a risk of driving the wheelchair.

[0005] Furthermore, the process of the data acquisition module acquiring the environmental data of the wheelchair location and the wheelchair travel data includes: The data acquisition module includes an environment data acquisition unit and a driving data acquisition unit; The environmental data acquisition unit is used to acquire the environmental data of the location of the wheelchair in real time; the environmental data includes humidity data, vibration data and obstacle data; The vibration data includes vibration amplitude and vibration frequency, and the obstacle data includes the distance between the obstacle and the wheelchair and the direction of the obstacle; The wheelchair driving data during the wheelchair driving process is acquired in real time through the driving data acquisition unit, and the wheelchair driving data includes driving speed and driving direction.

[0006] Furthermore, the data processing module processes the obtained environmental data and wheelchair travel data to obtain a field trend model of the wheelchair, including: Construct a three-dimensional coordinate system with the position of the wheelchair as the origin; Setting a virtual road surface block, wherein the virtual road surface block includes a plurality of road surface characteristic attributes, wherein the road surface characteristic attributes include a flat road surface, a bumpy road surface, a sloped road surface, a horizontal road surface, a dry road surface, and a slippery road surface; Generate a corresponding virtual road surface block according to the obtained environmental data of the wheelchair location, associate the generated virtual road surface block with the corresponding road surface characteristic attribute, and map the generated virtual road surface block to the wheelchair location in the three-dimensional coordinate system; Generating a corresponding virtual obstacle plate in a three-dimensional coordinate system according to the obstacle data; Generate a predicted wheelchair trajectory in a three-dimensional coordinate system according to the obtained wheelchair travel data, and generate at least one virtual wheelchair plate on the predicted wheelchair trajectory; Integrate the generated plates in a three-dimensional coordinate system to obtain the corresponding field trend model.

[0007] Furthermore, the process of associating the generated virtual road surface slab with the corresponding road surface characteristic attribute includes: The obtained humidity data is recorded as Sd, the vibration amplitude is recorded as Zf, and the vibration frequency is recorded as Zp; The angle between the wheelchair's travel direction and the horizontal direction is recorded as SJ; Setting corresponding road surface characteristic parameter ranges for each road surface characteristic attribute; The obtained humidity data, vibration amplitude, vibration frequency and the angle between the wheelchair's travel direction and the horizontal direction are matched with the corresponding road surface characteristic parameter ranges; When the humidity data Sd∈[0, S], the dry road surface in the road surface characteristic attribute is associated with the virtual road surface block; conversely, when the humidity data Sd∉[0, S], the wet road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∈[0, F], the flat road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∉[0, F] and the vibration frequency Zp∈[0, P], the flat road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∉[0, F] and the vibration frequency Zp∉[0, P], the bumpy road surface in the road surface characteristic attribute is associated with the virtual road surface plate; When the angle between the wheelchair's driving direction and the horizontal direction is SJ∈[β1, β2], the horizontal road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the angle SJ between the wheelchair's driving direction and the horizontal direction is less than β1 or greater than β2, the sloped road surface in the road surface characteristic attribute is associated with the virtual road surface block.

[0008] Furthermore, the data analysis module analyzes the obtained environmental data and wheelchair driving data to determine whether there is a driving risk, and maps the analysis result to the domain trend model, including: Generate a predicted wheelchair trajectory according to the direction of the wheelchair, and record the length of the predicted wheelchair trajectory as L; The generated virtual wheelchair blocks are marked as sample nodes. The length between each sample node is a fixed value and is evenly distributed on the predicted wheelchair trajectory. Obtain the node risk assessment coefficient of each sample node; Set the risk threshold X0; Then the node risk assessment coefficient of each sample node obtained is compared with the set risk threshold in sequence according to the label order of the sample nodes to obtain the corresponding comparison result; When JX i When <X0, it means that there is no risk of wheelchair running; When JX i When ≥X0, it means that there is a driving risk for the wheelchair, the sample node with the corresponding label is marked as a risk node, and the corresponding avoidance instruction is generated according to the obtained risk node.

[0009] Furthermore, the process of generating corresponding avoidance instructions according to the obtained risk nodes includes: Connect the current location of the wheelchair with the risk nodes in sequence to obtain the corresponding predicted driving route, and determine whether the predicted driving risk node has an intersection with the virtual obstacle plate; When there is no intersection between the predicted driving route and the virtual obstacle plate, a deceleration avoidance instruction is generated; When there is an intersection between the predicted driving route and the virtual obstacle plate, the intersection is marked as a collision risk point and an obstacle avoidance instruction is generated.

[0010] Furthermore, the process of the automatic obstacle avoidance module constructing a corresponding obstacle avoidance route includes: When a deceleration avoidance instruction is generated, the user reduces the speed of the wheelchair and performs a driving risk analysis again during the process of reducing the speed of the wheelchair until the wheelchair no longer has any driving risk; When an obstacle avoidance instruction is generated, a virtual ray is generated that intersects with the outer contour of the virtual obstacle plate, taking the position of the wheelchair as the starting point; Obtain the number of intersections between the virtual ray and the outer contour of the virtual obstacle plate, and record the intersection of the virtual ray with the number of intersections of "1" and the outer contour of the virtual obstacle plate as the obstacle avoidance point; Obtain the distance between the obstacle avoidance point and the wheelchair's location and the obstacle avoidance deflection angle between the obstacle avoidance point and the wheelchair's current travel direction; Then obtain the corresponding obstacle avoidance cost coefficient; The obstacle avoidance point corresponding to the minimum obstacle avoidance cost coefficient is selected, and the corresponding obstacle avoidance route is generated, and the obstacle avoidance route is uploaded to the monitoring center, and the user performs corresponding operations on the wheelchair according to the generated obstacle avoidance route.

[0011] Compared with the prior art, the present invention has the following beneficial effects: By monitoring the environmental data in real time, corresponding road surface blocks are generated in the model, and the road surface characteristic attributes are associated with the road surface blocks according to the environmental data, so that the user can understand the road conditions in the blind spots in time. At the same time, according to the wheelchair driving data and environmental data, it is judged whether the user's current wheelchair driving is risky. If there is a risk, the corresponding avoidance instructions are generated according to the situation, thereby reducing the risk of the user during wheelchair driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0013] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0014] like Figure 1 As shown, an intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair includes a monitoring center, and the monitoring center is connected to a data acquisition module, a data processing module, a data analysis module, and an automatic obstacle avoidance module; The data acquisition module is used to obtain environmental data of the wheelchair's location and wheelchair travel data; The data processing module is used to process the obtained environmental data and wheelchair travel data to obtain a field trend model of the wheelchair; The data analysis module is used to analyze the obtained environmental data and wheelchair driving data to determine whether there is a driving risk; The automatic obstacle avoidance module is used to construct a corresponding obstacle avoidance route in the domain trend model when there is a risk of driving the wheelchair.

[0015] It should be further explained that, in the specific implementation process, the process of the data acquisition module acquiring the environmental data of the wheelchair location and the wheelchair driving data includes: The data acquisition module includes an environment data acquisition unit and a driving data acquisition unit; The environmental data acquisition unit is used to acquire the environmental data of the location of the wheelchair in real time; the environmental data includes humidity data, vibration data and obstacle data; The vibration data includes vibration amplitude and vibration frequency, and the obstacle data includes the distance between the obstacle and the wheelchair and the direction of the obstacle; The wheelchair driving data during the wheelchair driving process is acquired in real time through the driving data acquisition unit, and the wheelchair driving data includes driving speed and driving direction.

[0016] It should be further explained that, in the specific implementation process, the data processing module processes the obtained environmental data and wheelchair driving data to obtain the field trend model of the wheelchair, which includes: Construct a three-dimensional coordinate system with the position of the wheelchair as the origin; Setting a virtual road surface block, wherein the virtual road surface block includes a plurality of road surface characteristic attributes, wherein the road surface characteristic attributes include a flat road surface, a bumpy road surface, a sloped road surface, a horizontal road surface, a dry road surface, and a slippery road surface. It should be further explained that, in a specific implementation process, a plurality of road surface characteristic attributes may exist simultaneously according to actual conditions; Generate a corresponding virtual road surface block according to the obtained environmental data of the wheelchair location, associate the generated virtual road surface block with the corresponding road surface characteristic attribute, and map the generated virtual road surface block to the wheelchair location in the three-dimensional coordinate system; Generating a corresponding virtual obstacle plate in a three-dimensional coordinate system according to the obstacle data; Generate a predicted wheelchair trajectory in a three-dimensional coordinate system according to the obtained wheelchair travel data, and generate at least one virtual wheelchair plate on the predicted wheelchair trajectory; Integrate the generated plates in a three-dimensional coordinate system to obtain the corresponding field trend model.

[0017] It should be further explained that, in a specific implementation process, the process of associating the generated virtual pavement slab with the corresponding pavement characteristic attributes includes: The obtained humidity data is recorded as Sd, the vibration amplitude is recorded as Zf, and the vibration frequency is recorded as Zp; The angle between the wheelchair's travel direction and the horizontal direction is recorded as SJ; A corresponding road surface characteristic parameter range is set for each road surface characteristic attribute, wherein the road surface characteristic parameter range includes a humidity range, denoted as [0, S], a vibration amplitude range [0, F], a vibration frequency range [0, P], and an angle range [β1, β2], wherein β1<0, β2>0; The obtained humidity data, vibration amplitude, vibration frequency and the angle between the wheelchair's travel direction and the horizontal direction are matched with the corresponding road surface characteristic parameter ranges; When the humidity data Sd∈[0, S], the dry road surface in the road surface characteristic attribute is associated with the virtual road surface block; conversely, when the humidity data Sd∉[0, S], the wet road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∈[0, F], the flat road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∉[0, F] and the vibration frequency Zp∈[0, P], the flat road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∉[0, F] and the vibration frequency Zp∉[0, P], the bumpy road surface in the road surface characteristic attribute is associated with the virtual road surface plate; When the angle between the wheelchair's driving direction and the horizontal direction is SJ∈[β1, β2], the horizontal road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the angle SJ between the wheelchair's driving direction and the horizontal direction is less than β1 or greater than β2, the sloped road surface in the road surface characteristic attribute is associated with the virtual road surface block.

[0018] It should be further explained that, in the specific implementation process, the data analysis module analyzes the obtained environmental data and wheelchair driving data to determine whether there is a driving risk, and maps the analysis results to the domain trend model, including: According to the driving direction of the wheelchair, a predicted wheelchair trajectory is generated, and the length of the predicted wheelchair trajectory is recorded as L; it should be further explained that, in the specific implementation process, the length of the predicted wheelchair trajectory depends on the driving speed of the wheelchair, and is linearly related to the driving speed of the wheelchair. The faster the driving speed, the shorter the generated predicted wheelchair trajectory; The generated virtual wheelchair blocks are marked as sample nodes. The length between each sample node is a fixed value and is evenly distributed on the predicted wheelchair trajectory. The generated sample nodes are numbered in sequence, denoted as i, where i=1, 2, ..., n; Get the node risk assessment coefficient of each sample node, denoted as JX i ; in, ; It should be further explained that, in the specific implementation process, β is β1 or β2, when SJ < β1, β is β1, when SJ > β2, β is β1; when Sd∈[0, S], Sd=0; when Zf∈[0, F], Zf=0; when Zp∈[0, P], Zp=0; Set a risk threshold X0; It should be further explained that, in the specific implementation process, the risk threshold is set by a person skilled in the art according to actual tests. It can be seen from the above formula that the node risk assessment coefficient of each sample node will increase as the number of the sample node increases; Then the node risk assessment coefficient of each sample node obtained is compared with the set risk threshold in sequence according to the label order of the sample nodes to obtain the corresponding comparison result; When JX i When <X0, it means that there is no risk of wheelchair running; When JX i ≥X0, it means that there is a risk of wheelchair driving, then the sample node with the corresponding label is marked as a risk node, and the corresponding avoidance instruction is generated according to the obtained risk node; it should be further explained that in the specific implementation process, if the label i of the sample node is ≠n, then the sample node and other sample nodes whose labels are sorted after the sample node are also marked as risk nodes; Label the risk nodes as j, where j = 1, 2, ..., m; Connect the current location of the wheelchair with the risk node labeled j in the order of the risk node labels, obtain the corresponding predicted driving route, and determine whether the predicted driving risk node has an intersection with the virtual obstacle plate; When there is no intersection between the predicted driving route and the virtual obstacle plate, a deceleration avoidance instruction is generated; When there is an intersection between the predicted driving route and the virtual obstacle plate, the intersection is marked as a collision risk point and an obstacle avoidance instruction is generated.

[0019] It should be further explained that, in the specific implementation process, the process of the automatic obstacle avoidance module constructing the corresponding obstacle avoidance route includes: When a deceleration avoidance instruction is generated, the user reduces the speed of the wheelchair and performs a driving risk analysis again during the process of reducing the speed of the wheelchair until the wheelchair no longer has any driving risk; When an obstacle avoidance instruction is generated, a virtual ray is generated that intersects with the outer contour of the virtual obstacle plate, taking the position of the wheelchair as the starting point; Obtain the number of intersections between the virtual ray and the outer contour of the virtual obstacle plate, and record the intersection of the virtual ray with the number of intersections of "1" and the outer contour of the virtual obstacle plate as the obstacle avoidance point; Get the distance between the obstacle avoidance point and the wheelchair, recorded as JL, and record the angle between the obstacle avoidance point and the current direction of the wheelchair as the obstacle avoidance deflection angle, recorded as α; Then the corresponding obstacle avoidance cost coefficient is obtained, denoted as Bd;

[0020] Where V is the current speed of the wheelchair, a is the acceleration of the wheelchair, and Zn is the steering efficiency coefficient of the wheelchair; The obstacle avoidance point corresponding to the minimum obstacle avoidance cost coefficient is selected, and the corresponding obstacle avoidance route is generated, and the obstacle avoidance route is uploaded to the monitoring center, and the user performs corresponding operations on the wheelchair according to the generated obstacle avoidance route.

[0021] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments with equivalent changes without departing from the scope of the technical solution of the present invention. However, any modification or equivalent replacement of the above embodiments made according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. An intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair, comprising a monitoring center, characterized in that: The monitoring center is connected to a data acquisition module, a data processing module, a data analysis module and an automatic obstacle avoidance module; The data acquisition module is used to obtain environmental data of the wheelchair's location and wheelchair travel data; The data processing module is used to process the obtained environmental data and wheelchair travel data to obtain a field trend model of the wheelchair; The data analysis module is used to analyze the obtained environmental data and wheelchair driving data to determine whether there is a driving risk; The automatic obstacle avoidance module is used to construct a corresponding obstacle avoidance route in the domain trend model when there is a risk of driving the wheelchair.

2. The intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair according to claim 1, characterized in that: The process of the data acquisition module acquiring the environmental data of the wheelchair location and the wheelchair travel data includes: The data acquisition module includes an environment data acquisition unit and a driving data acquisition unit; The environmental data acquisition unit is used to obtain the environmental data of the location of the wheelchair in real time; the environmental data includes humidity data, vibration data and obstacle data; The vibration data includes vibration amplitude and vibration frequency, and the obstacle data includes the distance between the obstacle and the wheelchair and the direction of the obstacle; The wheelchair driving data during the wheelchair driving process is acquired in real time through the driving data acquisition unit, and the wheelchair driving data includes driving speed and driving direction.

3. The intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair according to claim 2, characterized in that: The data processing module processes the obtained environmental data and wheelchair travel data to obtain a field trend model of the wheelchair, including: Construct a three-dimensional coordinate system with the position of the wheelchair as the origin; Setting a virtual road surface block, wherein the virtual road surface block includes a plurality of road surface characteristic attributes, wherein the road surface characteristic attributes include a flat road surface, a bumpy road surface, a sloped road surface, a horizontal road surface, a dry road surface, and a slippery road surface; Generate a corresponding virtual road surface block according to the obtained environmental data of the wheelchair location, associate the generated virtual road surface block with the corresponding road surface characteristic attribute, and map the generated virtual road surface block to the wheelchair location in the three-dimensional coordinate system; Generating a corresponding virtual obstacle plate in a three-dimensional coordinate system according to the obstacle data; Generate a predicted wheelchair trajectory in a three-dimensional coordinate system according to the obtained wheelchair travel data, and generate at least one virtual wheelchair plate on the predicted wheelchair trajectory; Integrate the generated plates in a three-dimensional coordinate system to obtain the corresponding field trend model.

4. The intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair according to claim 3, characterized in that: The process of associating the generated virtual pavement slabs with the corresponding pavement characteristic attributes includes: The obtained humidity data is recorded as Sd, the vibration amplitude is recorded as Zf, and the vibration frequency is recorded as Zp; The angle between the wheelchair's travel direction and the horizontal direction is recorded as SJ; Setting corresponding road surface characteristic parameter ranges for each road surface characteristic attribute; The obtained humidity data, vibration amplitude, vibration frequency and the angle between the wheelchair's travel direction and the horizontal direction are matched with the corresponding road surface characteristic parameter ranges; When the humidity data Sd∈[0, S], the dry road surface in the road surface characteristic attribute is associated with the virtual road surface block; conversely, when the humidity data Sd∉[0, S], the wet road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∈[0, F], the flat road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∉[0, F] and the vibration frequency Zp∈[0, P], the flat road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the vibration amplitude Zf∉[0, F] and the vibration frequency Zp∉[0, P], the bumpy road surface in the road surface characteristic attribute is associated with the virtual road surface plate; When the angle between the wheelchair's driving direction and the horizontal direction is SJ∈[β1, β2], the horizontal road surface in the road surface characteristic attribute is associated with the virtual road surface block; When the angle SJ between the wheelchair's driving direction and the horizontal direction is less than β1 or greater than β2, the sloped road surface in the road surface characteristic attribute is associated with the virtual road surface block.

5. The intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair according to claim 4, characterized in that: The data analysis module analyzes the obtained environmental data and wheelchair driving data to determine whether there is a driving risk, and maps the analysis results to the domain trend model, including: Generate a predicted wheelchair trajectory according to the direction of the wheelchair, and record the length of the predicted wheelchair trajectory as L; The generated virtual wheelchair blocks are marked as sample nodes. The length between each sample node is a fixed value and is evenly distributed on the predicted wheelchair trajectory. Obtain the node risk assessment coefficient of each sample node; Set the risk threshold X0; Then the node risk assessment coefficient of each sample node obtained is compared with the set risk threshold in sequence according to the label order of the sample nodes to obtain the corresponding comparison result; When JX i When <X0, it means that there is no risk of wheelchair running; When JX i When ≥X0, it means that there is a driving risk for the wheelchair, the sample node with the corresponding label is marked as a risk node, and the corresponding avoidance instruction is generated according to the obtained risk node.

6. The intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair according to claim 5, characterized in that: The process of generating corresponding avoidance instructions according to the obtained risk nodes includes: Connect the current location of the wheelchair with the risk nodes in sequence to obtain the corresponding predicted driving route, and determine whether the predicted driving risk node has an intersection with the virtual obstacle plate; When there is no intersection between the predicted driving route and the virtual obstacle plate, a deceleration avoidance instruction is generated; When there is an intersection between the predicted driving route and the virtual obstacle plate, the intersection is marked as a collision risk point and an obstacle avoidance instruction is generated.

7. The intelligent environment monitoring and automatic obstacle avoidance system for a wheelchair according to claim 6, characterized in that: The process of the automatic obstacle avoidance module constructing the corresponding obstacle avoidance route includes: When a deceleration avoidance instruction is generated, the user reduces the speed of the wheelchair and performs a driving risk analysis again during the process of reducing the speed of the wheelchair until the wheelchair no longer has any driving risk; When an obstacle avoidance instruction is generated, a virtual ray is generated that intersects with the outer contour of the virtual obstacle plate, taking the position of the wheelchair as the starting point; Obtain the number of intersections between the virtual ray and the outer contour of the virtual obstacle plate, and record the intersection of the virtual ray with the number of intersections of "1" and the outer contour of the virtual obstacle plate as the obstacle avoidance point; Obtain the distance between the obstacle avoidance point and the wheelchair's location and the obstacle avoidance deflection angle between the obstacle avoidance point and the wheelchair's current travel direction; Then obtain the corresponding obstacle avoidance cost coefficient; The obstacle avoidance point corresponding to the minimum obstacle avoidance cost coefficient is selected, and the corresponding obstacle avoidance route is generated, and the obstacle avoidance route is uploaded to the monitoring center, and the user performs corresponding operations on the wheelchair according to the generated obstacle avoidance route.

Images