WO2018133805A1 - 路径规划方法和装置 - Google Patents

路径规划方法和装置 Download PDF

Info

Publication number
WO2018133805A1
WO2018133805A1 PCT/CN2018/073114 CN2018073114W WO2018133805A1 WO 2018133805 A1 WO2018133805 A1 WO 2018133805A1 CN 2018073114 W CN2018073114 W CN 2018073114W WO 2018133805 A1 WO2018133805 A1 WO 2018133805A1
Authority
WO
WIPO (PCT)
Prior art keywords
regions
pass cost
environmental
pass
task
Prior art date
Application number
PCT/CN2018/073114
Other languages
English (en)
French (fr)
Inventor
包鼎华
张志军
Original Assignee
华为技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP18741121.0A priority Critical patent/EP3564624A4/en
Publication of WO2018133805A1 publication Critical patent/WO2018133805A1/zh
Priority to US16/515,502 priority patent/US20190339703A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3484—Personalized, e.g. from learned user behaviour or user-defined profiles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3691—Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device

Definitions

  • Embodiments of the present invention relate to the field of intelligent control, and more particularly, to a path planning method and apparatus.
  • Path planning is an important branch in the field of intelligent control research. Using good path planning technology can save the working time of intelligent executing devices (for example, robots), improve the efficiency of executing tasks, and improve the quality of executing tasks.
  • intelligent executing devices for example, robots
  • a map may be adopted to implement path planning.
  • the map includes location information and information of obstacles, so that the smart executing device can find a path capable of bypassing the obstacle based on the map.
  • the embodiment of the invention provides a path planning method and device, which can implement a more optimized path planning.
  • a path planning method including: obtaining, according to a transit distance of each of the plurality of first regions, and a representation value of an environmental feature of each of the first regions, Passing cost of the first area; obtaining a starting position and a target position; determining a path to the target position from the starting position according to the path planning by the pass cost of each of the first areas,
  • the pass path includes an area that passes from the starting position to the target position.
  • a pass cost through each of the first regions is obtained, and according to the pass cost, Path planning is performed, so that when the path planning is performed, not only the traffic distance of the area but also the characterization value of the environmental features at the area can be considered, and a more optimized path planning can be realized, and the traffic distance and the characterization value are uniformly quantized.
  • the intelligent execution device can obtain the traffic path based on the traffic cost when performing path planning, which can save the working time of the intelligent execution device and improve the efficiency of executing the task.
  • the pass path may be the path with the least cost.
  • the method further includes: generating an environment map according to a pass cost through each of the first regions, the environment map including a pass cost through each of the first regions, for indicating the plurality of Determining values of each of the first regions within the coverage of the first region; determining, by the path planning through the pass-through cost of each of the first regions, from the starting location to the target location
  • the pass path includes: determining the pass path based on a pass cost of each of the areas within the coverage of the plurality of areas based on the environment map.
  • the environment map may be a pass cost list or a global peer cost topology map.
  • the obtaining, by the transit distance of each of the plurality of first regions, and the characterization value of the environmental features of each of the first regions, obtaining a pass cost through each of the first regions includes: determining, according to the transit distance of each of the first regions, a first pass cost component corresponding to the pass distance of each of the first regions; according to a representation value of an environmental feature of each of the first regions, Determining a second pass cost component corresponding to the characterization value of the environmental feature of each of the first regions; calculating, according to the first pass cost component and the second pass cost component of each of the first regions Through the pass cost of each of the first regions.
  • the traffic cost of the task type in each region is separately calculated, so that when the path planning of a certain task type is performed, the traffic cost of each region for the task type can be directly obtained, thereby A more optimized path planning can be achieved.
  • the method further includes: acquiring at least one type of task to be executed when passing the path; acquiring the first first according to the characterization value of the environmental feature of each of the first regions a second pass cost component corresponding to the pass distance of the region, comprising: obtaining, according to the characterization value of the at least one environment feature available in each of the at least one task type at each of the first regions a second pass cost component corresponding to each of the first types of the task types; the first pass cost component and the second pass cost component according to the each first region, Calculating a pass cost through each of the first regions, including: according to the first pass cost component of each of the first regions, and corresponding to each of the first regions in each of the task types a two-pass cost component, calculating a pass cost through each of the first regions when performing each of the task types; the path planning according to the pass cost through each of the first regions, : The execution of the task for each type by the cost of each of the first passage region for performing the determining the travel paths of each type of task.
  • the at least one task type includes a first task type
  • the obtaining performs the second pass cost component corresponding to each task type at each of the first regions, including: according to Determining, in each of the first regions, a representation value of the at least one environmental feature that satisfies a predetermined condition among the environmental features available in the first task type, determining that the first task type is in each of the first regions The corresponding second pass cost component.
  • the first area is an area that satisfies the following condition: at the first area, a feature value of an environmental feature that is available for the first task type satisfies a requirement of the first task type for an environmental feature.
  • the method further includes: determining at least one second region, wherein, at the second region, a representation value of an environmental feature available to the first task type does not satisfy the first task type to an environment a requirement of a feature; each of the at least one second region is considered an obstacle when performing path planning.
  • the method further includes: acquiring a plurality of task types to be executed when passing the transit path; and acquiring, according to the characterization value of the environmental features of each of the first regions, each of the first regions
  • the second pass cost component corresponding to the characterization value of the environment feature comprising: obtaining the plurality of task types as a whole according to a characterization value of at least one environmental feature available for each of the plurality of task types a second pass cost component corresponding to each of the first regions; the first pass cost component and the second pass cost component according to each of the first regions are calculated by each of the
  • the pass cost of the first area includes: a second pass cost component corresponding to each of the plurality of task types as a whole at each of the first areas, according to the first pass cost component of each of the first areas, Calculating a corresponding pass cost of the plurality of task types as a whole at each of the first regions; the path planning according to the pass cost through each of the first regions, Included: determining the pass path for executing the plurality of task
  • the plurality of task types can be used as a traffic cost at each region as a whole, thereby directly acquiring each region for the plurality of tasks when performing multiple path planning needs to be performed.
  • the overall cost of the operation can save the processing time of the intelligent execution device and improve the processing efficiency.
  • the acquiring the plurality of task types as a whole corresponding to the second pass cost component at each of the first regions including: according to each of the first regions, the multiple task types a characterization value of at least one environmental feature available for each task type, obtaining a second pass cost component corresponding to each of the task types at each of the first regions; A plurality of corresponding second pass cost components at each of the first regions are weighted to obtain the second pass cost component corresponding to the plurality of task types as a whole at the first region.
  • the first area is an area that satisfies the following conditions: at the first area, a representation value of an environmental feature available for each of the plurality of task types meets each of the task type pairs Environmental characteristics requirements.
  • the method further includes: determining at least one third region, wherein, at the third region, a representation value of an environmental feature corresponding to at least one of the plurality of task types does not satisfy Determining a requirement for a feature value by at least one task type; and when performing path planning, treating each third region of the at least one third region as an obstacle.
  • determining, according to the characterization value of the environmental feature of each of the first regions, a second pass cost component corresponding to the characterization value of the environmental feature of each of the first regions including: according to environmental characteristics Determining the correspondence between the characterization value interval and the pass cost component, and the characterization value of the environmental feature of each of the regions, determining the acquiring the second pass cost component of each of the first regions.
  • the obtaining, by the transit distance of each of the plurality of first regions, and the characterization value of the environmental features of each of the first regions, obtaining a pass cost through each of the first regions includes: obtaining a traffic cost through each of the first regions in a statistical manner according to the passing distance of each of the first regions and the characterization value of the environmental features of each of the first regions acquired; Or acquiring the transit cost through each of the first regions in real time according to the passing distance of each of the first regions and the characterization value of the environmental features of each of the first regions acquired in real time; or, according to A transit distance of each of the first regions, and a predicted value of the environmental features of each of the first regions are predicted, and a pass cost through each of the first regions is obtained.
  • the traversing distance according to each of the first regions, and the characterization value of the environmental features of each of the first regions acquired multiple times are obtained in a statistical manner by each of the first regions.
  • the pass cost includes: in the case where the rate of change of the environmental features of each of the first regions is less than or equal to a first threshold, according to the pass distance of each of the first regions, and each of the plurality of acquisitions A characterization value of the environmental characteristics of the first region, the transit cost through each of the first regions is obtained in a statistical manner.
  • the passing distance of each of the first regions is obtained according to the passing distance of each of the first regions, and the passing values of the environmental features of each of the first regions are acquired in real time
  • the method includes: in a case where the rate of change of the environmental features of each of the first regions is greater than a second threshold, according to the transit distance of each of the first regions, and the manner of the first region of the first region acquired in real time
  • the characterization value of the environmental feature obtains the transit cost through each of the first regions in real time.
  • the environmental feature includes a visual signal, and determining, according to the characterization value of the environmental feature of each of the first regions, a second pass corresponding to the characterization value of the environmental feature of each of the first regions
  • the cost component includes: obtaining a second pass cost corresponding to each direction of each of the first locations according to a characterization value of the visual signal in each of the plurality of directions through each of the first locations a component; calculating, according to the first pass cost component and the second pass cost component of each of the first regions, a pass cost through each of the first regions, including: according to each of the The first pass cost component of an area, and a second pass cost component corresponding to each direction of each of the first areas, determine a pass cost in each of the directions through each of the first areas .
  • the environmental characteristic comprises at least one of a visual signal, a sound signal, and a contact surface state.
  • the environmental feature comprises a visual signal, the representative value of the visual signal comprising a light intensity and/or a number of visual features.
  • the environmental feature comprises a sound signal, the representative value of the sound signal comprising an intensity of the sound signal.
  • the environmental feature comprises a contact surface state, the characterization value of the contact surface state comprising a slope of the contact surface at the location, a rate of change in height, and/or a degree of friction.
  • a path planning apparatus in a second aspect, can include means for performing the method of the first aspect or any alternative implementation thereof.
  • a path planning apparatus may include a memory and a processor, wherein the memory may store program code, and the processor and the memory communicate with each other through an internal connection path, and the processor may call The program code stored in the memory performs the method of the first aspect or any alternative implementation thereof.
  • a storage medium is provided, the storage medium being operative to store program code, the program code stored in the memory being operative by a processor to perform the method of the first aspect or any alternative implementation thereof.
  • FIG. 1 is a schematic diagram of a system for path planning in accordance with an embodiment of the present invention.
  • FIG. 2 is a schematic flowchart of a path planning method according to an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of path planning according to a pass cost, in accordance with an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of path planning according to a pass cost, in accordance with an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of path planning according to a pass cost according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of path planning according to a transit cost, in accordance with an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of path planning according to a pass cost, in accordance with an embodiment of the present invention.
  • FIG. 8 is a schematic flowchart of a map generation method according to an embodiment of the present invention.
  • FIG. 9 is a schematic flowchart of a path planning method according to an embodiment of the present invention.
  • FIG. 10 is a schematic block diagram of a path planning apparatus according to an embodiment of the present invention.
  • FIG. 11 is a schematic block diagram of a map generation device in accordance with an embodiment of the present invention.
  • Figure 12 is a schematic block diagram of a path planning apparatus in accordance with an embodiment of the present invention.
  • Figure 13 is a schematic block diagram of a processing device in accordance with an embodiment of the present invention.
  • FIG. 1 is a schematic diagram of a system for path planning in accordance with an embodiment of the present invention. As described in FIG. 1, in the system, an environment system 110 and an intelligent execution device 120 can be included.
  • the environmental system 110 can generate environmental features, wherein the environmental features can include at least one of a visual signal, a sound signal, and a contact surface state.
  • the environmental features may also include other features, which are not specifically limited herein.
  • the intelligent execution device 120 can perform path planning based on the characterization values of the environmental features generated by the environmental system 110.
  • the smart execution device 120 may generate an environment map based on the representation value of the environmental feature, and perform path planning based on the environment map.
  • system can also include an intelligent execution device 130.
  • the smart execution device 120 can also send the generated environment map to the smart execution device 130.
  • the intelligent execution device 130 may perform path planning based on the environment map transmitted by the smart execution device 120.
  • the smart execution device mentioned in the embodiment of the present invention may refer to a machine device that automatically performs work, for example, may be a robot, a driverless car, or a drone.
  • the intelligent actuators 120 and 130 shown in FIG. 1 are robots, they are merely for the reader's understanding and are not intended to limit the scope of the invention.
  • the manner in which the environmental system 110 is illustrated should not be construed as limiting the scope of the embodiments of the invention.
  • the candidate area When performing path planning, the candidate area can be divided into multiple areas, and the traffic cost through the area is marked in all or part of the area.
  • the greater the cost of the passage means the higher the cost to be paid through the area, in the path planning process.
  • the probability of being selected is smaller.
  • the pass cost may be a value, and all regions may obtain a unitless value corresponding to each region based on the same criterion.
  • the following describes in detail how to obtain the traffic cost through multiple regions, and generates an environmental map according to the traffic cost of multiple regions, and describes how to perform path planning according to the traffic cost of multiple regions.
  • FIG. 2 is a schematic flowchart of a path planning method 200 according to an embodiment of the present invention.
  • the method 200 can be applied to the system shown in FIG.
  • the method can optionally be performed by the smart executive device 120 shown in FIG. It should be understood that the method 200 can be performed by other devices, and the embodiment of the present invention is only described by taking an intelligent execution device as an example.
  • the method 200 includes the following.
  • a transit cost through each of the first regions is obtained according to a transit distance of each of the plurality of first regions and a characterization value of environmental features of each of the first regions.
  • the smart execution device may directly detect the characterization value of the environmental feature at each area, or may also receive the characterization value of the environmental feature sent by the other device, or may also receive the characterization value of the manually input environmental feature.
  • the characterization values of the environmental features may be traversed through the respective regions for calculating the traffic cost.
  • the area mentioned in the embodiment of the present invention may be referred to as a node, and the area may be a square structure, or may be a rectangle, a hexagon or any other shape.
  • the travel distances of all the areas in a map may be the same or different.
  • the transit distance of the first area refers to a length between any two points of the first area.
  • the area division is performed in a grid manner, and the length between any two points may be a straight-through distance or The distance through which the oblique line passes.
  • the environmental features mentioned in the embodiments of the present invention may include at least one of a visual signal, a sound signal, and a contact surface state.
  • the representation value of the visual signal comprises a light intensity and/or a number of visual features.
  • the visual signal can be used for positioning, for example, by visual features. Therefore, if the number of visible features is large, it is considered to be easier to locate, and when positioning is performed, the light intensity also affects the positioning, for example, The light intensity is in line with the visual requirements of the smart actuator itself, making it easier to locate.
  • the environmental feature comprises a sound signal, the representative value of the sound signal comprising an intensity of the sound signal.
  • the sound signal can be divided into a noise and a beneficial sound signal
  • the beneficial sound signal can include an ultrasonic signal through which positioning can be performed.
  • the intensity of noise in each area can be recorded, and if the noise intensity at a certain location is small or no noise, the position is more accessible.
  • the characterization value of the contact surface state includes a slope of the contact surface at the location, a rate of change in height, and/or a degree of friction.
  • the representation value of the road surface may be that the road surface is difficult or bumpy, whether it is muddy, slipping, and the inclination angle of the road surface.
  • the state of the contact surface can be obtained manually, or the device self-exploration can be used to identify the state of the contact surface at different positions.
  • manual scoring can be performed based on road conditions. For example, if the road surface with water is recorded as 0, the road surface is recorded as 10 points, the road inclination angle is greater than 5 degrees and recorded as 0 points, the degree of slip or bump is more than a certain threshold is recorded as 10 points, and other cases are recorded as 100 points.
  • the pass cost is determined according to the score. For example, the higher the score, the lower the pass cost.
  • visual recognition can be used to estimate the pavement material. If the ground has wires, thresholds, stairs, and other visually identifiable objects, this can be quantified to obtain a characterization value.
  • the degree of slip can be estimated by a variety of positioning methods and robot odometer information comparison methods, and the difficulty of the corresponding road section can be estimated by recording the motor output power.
  • the inclination of the road surface can be calculated by the robot with a sensor such as a gravimeter or a camera.
  • the first area mentioned in the embodiment of the present invention may be any area in the candidate area, or may be an area that satisfies certain conditions, for example, an area where the characteristic value of the environmental feature satisfies certain conditions, and the area may be Calculate the pass cost. For areas that do not meet the conditions, you can directly treat the area as an obstacle.
  • the pass cost through the first region in embodiments of the present invention may sometimes also be referred to as the pass cost of the first region or the pass cost at the first region.
  • the smart execution device may generate an environment map according to a pass cost through each of the first regions, where the environment map includes a pass cost through each of the first regions, And indicating a representation value of each of the first regions within the coverage of the plurality of first regions, the environment map may perform path planning.
  • the environment map may be a pass cost list or a global peer cost topology map.
  • the environment map may mark the characterization value of the environmental feature, but does not mean that the transit cost of each region in the map is only related to the characterization value of the environmental feature, and also to the regional characterization value.
  • the travel distance is related. For example, if the travel distance is inconsistent, the same pass cost may have different representation values of the environmental characteristics.
  • the smart execution device may not generate a map, but directly perform path planning according to the transit cost of the plurality of first regions.
  • the smart execution device may adopt the characterization value of the acquired environmental feature multiple times, and obtain the traffic cost at the corresponding region obtained by means of statistics or voting; or, may also use the characterization value of the real-time acquired environmental feature to obtain the real-time The traffic cost at the corresponding area; or the predicted cost of the corresponding area obtained by the characterization value of the environmental feature.
  • the characterization value of the acquired environmental feature may be used to generate the environmental map by using the traffic cost at the corresponding region obtained by statistics or voting; or, the characterization value of the environmental feature obtained in real time may also be used.
  • the environmental map is updated in real time according to the traffic cost at the corresponding area; or the environmental cost map may be generated by predicting the traffic cost of the corresponding area obtained by the characterization value of the environmental feature.
  • the statistical method refers to uniformly processing the characterization values of the environmental features acquired multiple times, for example, weighting processing, etc., to obtain the traffic cost at the corresponding region.
  • the voting method is to select the characterization value of the environmental feature obtained from the partial acquisition from the characterization values of the multiple acquired environmental features to obtain the traffic cost of the corresponding region.
  • the use of statistics or voting to obtain the pass cost, or to obtain the pass cost in real time, or to obtain the pass cost in a predictive manner, or a combination of the two ways to obtain the pass cost may be determined in conjunction with the actual situation.
  • the traffic cost of the corresponding region may be obtained in a statistical manner; when the stability of the characterization value of the environmental feature is poor, the corresponding wireless pass cost may be obtained in real time. .
  • the environmental feature is a visual signal
  • the lighting conditions of different time periods are different, and the map may be updated by the time period.
  • the lighting conditions of the same time period are substantially the same, and the map can be generated in a statistical manner.
  • the stability of the characterization value of the environmental feature may refer to the rate of change of the environmental feature. For example, if the rate of change of the intensity of the environmental feature is less than or equal to a predetermined value or the rate of change of the direction is less than or equal to a predetermined value, the stability is considered to be good.
  • the characterization value of the environmental feature at another time and/or another region may be predicted by a characterization value of the environmental feature at a certain time and/or a certain region
  • the environmental feature can be considered to be a predictable environmental feature.
  • the lighting conditions and the like of other time periods can be predicted according to the lighting conditions of a certain period of time.
  • the environmental feature is a sound signal
  • the sound signal of other time periods can be predicted according to the sound signal of a certain time period.
  • the road surface state can be predicted according to the weather prediction situation.
  • the environment map in the embodiment of the present invention may include a pass cost for each area at multiple regions, where the pass cost of each region may include multiple pass charges, for example, may include predicted at various moments The cost of the passage, so that when the path planning is carried out, the traffic cost at each moment in a certain area and the time at which it is run can be combined to obtain the corresponding path planning at the area, so that a better path can be selected.
  • the map in the embodiment of the present invention may include a pass cost in each of a plurality of regions in a plurality of directions, wherein the pass cost in each direction refers to the pass cost when passing the region in the direction.
  • the pass cost in each direction refers to the pass cost when passing the region in the direction.
  • different directions may have different characterization values, for example, the characterization value when carrying the sun is different from the characterization value along the sun.
  • the traffic direction may include 0 degrees, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees, 315 degrees, eight directions, according to the direction of the area in eight directions
  • the lighting conditions captured by the camera determine the pass cost.
  • the traffic cost at each of the first regions is obtained according to the traffic distance of each of the plurality of first regions and the characterization value of the environmental features of each of the first regions Therefore, when generating the environment map, the traffic cost at each of the regions is identified in each of the regions, so that when the environment map is generated, not only the traffic distance of the region but also the environmental characteristics at the region may be considered.
  • the characterization value, the passing distance and the characterization value of the environmental characteristics are quantified to obtain the pass cost, and a better environment map can be obtained, so that the application scope of the environment map is wider, and a better path planning can be realized, and the distance is adopted.
  • the characterization value of the environmental feature is uniformly quantified as the pass cost, which enables the robot to acquire the transit path based on the pass cost when performing path planning, which can save the robot working time and improve the efficiency of executing the task.
  • the first traffic cost component corresponding to the traffic distance and the environment may be calculated.
  • the first pass cost component of the first region and the second pass cost component may be added to obtain a pass cost for the first region.
  • the first pass cost component of the first region and the second pass cost component of the first region may be weighted to obtain a pass cost of the first region, where the weighting coefficient may be specific Depending on the situation, for example, if the task to be executed is more sensitive to the traffic distance of the area, the weighting factor of the size can be set higher.
  • the second pass cost may be a coefficient multiplied by the first pass cost component to obtain a pass cost, and then the first pass cost component and the coefficient may be combined to obtain the first region.
  • the cost of the passage may be a coefficient multiplied by the first pass cost component to obtain a pass cost, and then the first pass cost component and the coefficient may be combined to obtain the first region. The cost of the passage.
  • the third pass cost component in addition to the passing distance of the area and the characterization value of the environmental feature, other factors may be considered, for example, determining the area according to the signal quality of the wireless signal (eg, satellite signal, network signal, etc.).
  • the first pass cost component, the second pass cost component, and the third pass cost component may be added or weighted to obtain a pass cost for the region.
  • the second pass cost component for acquiring the location of each region may be determined according to a correspondence between a characteristic value interval of the environment feature and a traffic cost, and a representation value of the environmental feature of each region.
  • the characterization values of the environmental features can be divided into three levels: good, medium, and poor. Each level includes a range of values that can be quantified. Each level can correspond to a different second pass cost component, and the characterization of the acquired environmental features. After the value, the level to which the characterization value of the environmental feature belongs can be determined, and the second pass cost component corresponding to the level is obtained.
  • the coefficient corresponding to the characterization value of the environmental feature is 1, the corresponding coefficient in the characterization value of the environmental feature is 5, the coefficient corresponding to the characterization value difference of the environmental feature is 10, and the pass cost corresponding to the distance at a certain position is 10 (straight line) and 14 (oblique line), if the characterization value of the environmental feature at the position is poor, the pass cost of the straight line and the slant line at the position may be determined to be 100 and 140 if the environmental feature at the position If the characterization value is medium, the pass cost of the straight line and the oblique line at the position can be determined as 50 and 70. If the characterization value of the environmental feature at the position is good, the straight line and the oblique line at the position can be passed. The cost is determined to be 10 and 14.
  • the advantages and disadvantages of the environmental features represent the difficulty level of performing the task when the environment feature is adopted, and the quality representative is easy to perform the task, the quality is poor, and the representative is difficult to perform the task.
  • a transit distance may be set in the environment map for each of the plurality of environmental features, and the task may be determined when the task is executed by using the environment map.
  • the traffic cost of each area may be obtained by combining at least one type of task to be executed. And optionally, the traffic cost corresponding to the task type may be marked in the environment map. When the task is executed by using the environment map, the traffic cost corresponding to the task may be determined, and path planning is performed.
  • the tasks to be performed include, but are not limited to, at least one of positioning, communication, networking, detection, and identification.
  • the environmental feature comprises a visual signal; each of each of the first regions is acquired according to a characterization value of a visual signal in each of the plurality of directions through each of the first regions Corresponding second pass cost calculation parameters of the direction; according to the first pass cost component of each of the first regions, corresponding to a representation value of a visual signal in each direction of each of the first regions A second pass cost component determining a pass cost in each of the directions at each of the first regions.
  • the traffic cost of each area may be obtained by combining at least one type of task to be executed by the map.
  • the traffic cost corresponding to the task may be determined, and path planning may be performed.
  • the tasks that the map can perform include, but are not limited to, at least one of positioning, communication, networking, detection, and identification.
  • the wireless pass cost is determined according to the requirement of the task type for the characterization value of the environmental feature and the characterization value of the environmental feature, for example, if both the task type A and the task type B use the environmental feature a, wherein the task type A
  • the requirements for the environmental characteristics are higher than the requirements for the environmental characteristics of the task type B, and the same characterization value, the traffic cost component corresponding to the task type A is higher than the traffic cost component corresponding to the task type B.
  • the following describes how to combine the mode types to be executed to obtain the traffic cost at each area when generating the environment map in combination with mode A and mode B.
  • the environment map may be generated according to the pass cost of each of the task types at each of the first regions, wherein the environment map includes a pass cost for each of the task types at each of the first regions.
  • the traffic cost of the task type in each area is calculated separately, so that when performing path planning of a certain task type, the traffic cost of each area for the task type can be directly obtained. Therefore, a better path planning can be achieved.
  • the pass cost when calculating the second pass cost component of each task type in a certain area, can be determined according to the requirement of the task type to the characterization value of the environment feature and the characterization value of the environment feature.
  • the at least one task type includes a first task type, according to which at each of the first regions, a representation value of the at least one environmental feature that satisfies a predetermined condition in the environmental feature available for the first task type Determining a second pass cost component of the first task type at each of the first regions.
  • the at least one environmental characteristic that satisfies the predetermined condition may refer to a characterization value of the environmental feature that is better than a characterization value of a certain threshold, or a characterization value that is optimal for the characterization value.
  • the quality can be selected.
  • the better environmental features are used to calculate the cost component. For example, if the task is located, if the location can be located by the number of visual features and the sound signal, the positioning accuracy of the two modes can be estimated. The positioning accuracy of the environmental feature with better positioning accuracy is determined as a parameter for determining the traffic cost at the region.
  • the second pass cost component can be calculated by combining the characterization values of the multiple environmental features, for example, weighting the characterization values of multiple environmental features. Processing, weighting the obtained characterization value for calculating the second pass cost component, or calculating the second pass cost component separately for the characterization values of the plurality of environmental features, and performing weighting processing on the obtained plurality of second pass cost components, The second pass cost component that is finally available is obtained.
  • weighting may be used, which may be determined according to actual conditions. For example, if there are multiple environmental features, the multiple environmental features may be used cumulatively, and the representation values of the multiple environmental features may be used. A similar addition process is performed and a second pass cost component is further calculated.
  • the first area may be any area included in the candidate area, or may be an area that meets the following conditions: at each of the first areas, the representation value of the available environmental features of the first task type satisfies the The first task type requires environmental characteristics.
  • determining at least one second area wherein, at the second area, a representation value of an environmental feature available for the first task type does not satisfy a requirement of an environmental feature of the first task type;
  • the second area can be considered an obstacle.
  • each of the at least one second region is identified as an obstacle for the first task type.
  • the environment map may be generated according to the plurality of task types as a whole pass cost at each of the first regions, the environment map including the plurality of task types as a whole at each of the first regions Passing costs.
  • the plurality of task types can be regarded as a total transaction cost at each region, thereby directly obtaining each region for the multi-purpose path planning.
  • the overall cost of the task can be achieved, so that better path planning can be achieved.
  • obtaining the first type of each task type at each of the first regions Two pass cost components; weighting a plurality of second pass cost components at each of the plurality of task types at the first region to obtain the second plurality of task types as a whole at the first region Passing cost component.
  • processing modes may be used, which may be determined according to actual conditions.
  • the characterization values of the multiple types of environmental features may be similarly added, and the second pass cost component may be further calculated.
  • a plurality of second pass cost components corresponding to the plurality of task types are added to be processed as the traffic cost corresponding to the plurality of task types as a whole.
  • the at least one environmental feature that can be used for each task type may be the corresponding task type. All available environmental features at the region may also be partially available environmental features, such as at least one environmental feature that characterizes the value.
  • the first area may be any area that needs to be included in the environment map, or may be an area that meets the following conditions: at each of the first areas, an environment available for each of the multiple task types The characterization value of the feature satisfies the requirements of the environmental characteristics of each task type.
  • determining at least one third region wherein, at the third region, a representation value of an environment feature corresponding to at least one of the plurality of task types does not satisfy the at least one task type pair representation value Requirements; when planning a path, the third area can be considered an obstacle.
  • each of the at least one third region is set as an obstacle for the plurality of task types.
  • mode A and mode B can be used in combination when generating an environment map.
  • tasks to be executed using the environment map include task 1, task 2, and task 3.
  • the traffic cost can be separately calculated for task 1 task 2 and task 3, respectively, and task 1, task 2, and task 3 can be combined to calculate the traffic cost; Alternatively, calculate the pass cost of task 1, and combine task 2 and task 3 to calculate the pass cost.
  • the “species” division of environmental features may refer to different types of environmental feature types, for example, visual signals and sound signals are considered to be different kinds of environmental features; or may be the same type of environmental features. Different sources, such as, for example, the light from the sun and the light from the light in the visual signal, the distinguishing dimension of the "species" can be determined according to the actual situation.
  • the division of the "category" of the task type may also be determined in connection with a specific case, for example, agricultural use and industrial use are different kinds of task types, for example, positioning and communication are different task types.
  • the starting position and the target position are obtained.
  • a path plan is obtained from the start position to the target position based on the path plan through the pass cost of each of the first areas, the pass path including an area from the start position to the target position .
  • the environment map may be utilized to determine a path from the starting location to the target location.
  • various algorithms can be used, for example, Dijksra algorithm, A* algorithm, and the like.
  • F(n) is the traffic cost estimated from the initial node to the target node via the intermediate node n
  • G(n) is the actual acquisition pass cost from the starting node to the intermediate node n
  • H(n) is the intermediate node An estimate of the pass cost of n to the best path of the target node.
  • the H(n) calculation can be performed by the Manhattan algorithm or an algorithm thereof, and is not specifically limited herein.
  • Step 1 Add the starting node to the open list.
  • Step 2 repeat the following operations:
  • the neighboring node is already in the open list, it is better to check whether the new path is better with the G value. If so, the backtracking node of the neighboring node is taken as the current node, and the G and F values of the node are recalculated.
  • Step three save the path. From the target node, starting from the target node, the backtracking node along each node moves to the starting node, which is the selected path.
  • Figure 3 shown in Figure 3 is the starting node, the positional relationship between the obstacle and the target node.
  • Figure 4 and Figure 6 show the path calculation path corresponding only to the travel distance of the node. It is assumed that the straight line and the oblique line distance of each node are the same, and the pass cost corresponding to the straight line distance of each node can be recorded. For 10, the pass cost corresponding to the skewed distance of each node is recorded as 14.
  • Figure 7 shows the pass cost calculation path corresponding to the transit distance of the node and the characterization value of the environmental feature.
  • the lower left is the G value
  • the lower right is the H value
  • the upper left is the F value
  • the node A is the starting node
  • the node B is the target node
  • the three nodes O between the node A and the node B are obstacles, that is, nodes that are not passable.
  • the node with the lowest F value that is, the node C immediately adjacent to the right side of the start node A
  • the node C is searched.
  • Put the node C into the close list and then check the nodes adjacent to the node C. Since the node on the left is the start node and the node on the right is the obstacle, the two nodes can be ignored.
  • Put the other two adjacent nodes of the node into the open list then check the open list, check whether the new path is better with the G value, and find that the upper and lower nodes of the C node are directly connected to the starting node, and the path is more excellent.
  • the node added to the list may be selected, or may be randomly selected. For example, as shown in FIG. 5, node D is selected. And continue to make selection until the optimal path is found.
  • the resulting path can be as shown in Fig. 6, that is, the nodes requiring the path from the starting node A to the terminating node B include node D, node E, node F, node G, and node H.
  • Figure 7 is an optimal path from the starting node A to the terminating node B obtained in conjunction with the characterization values of the environmental features and the transit distance of the regions.
  • the traffic cost of the three nodes to the left of the obstacle in the environment map shown in FIG. 7 is modified to 100 and 140 (for example, modified due to poor lighting conditions). It can be seen from the figure that the backtracking nodes of the upper and lower nodes of the three nodes have changed.
  • the optimal path from node A to node B needs the path of the node including the node. I, node E, node F, node G and node H.
  • the environmental map obtained by using the characterization value and the transit distance based on the environmental features and the environment map obtained based only on the transit distance the final planned path is different, and thus based on the environmental characteristics
  • the characterization value and the environmental map generated by the travel distance are used for path planning, and more factors can be considered to make the planned path better.
  • FIG. 8 is a schematic flowchart of a map generation method 300 according to an embodiment of the present invention. As shown in FIG. 8, the method 300 includes the following.
  • a pass cost through each of the first regions is obtained based on a transit distance of each of the plurality of first regions and a characterization value of environmental features of each of the first regions.
  • an environment map is generated according to a pass cost through each of the first regions, the environment map including a pass cost through each of the first regions, for indicating the plurality of first region coverages A characterization value for each of the first regions described.
  • the specific implementation of the method for generating a map shown in FIG. 8 can be referred to the description in the method 300.
  • details are not described herein again.
  • FIG. 9 is a schematic flowchart of a path planning method 400 according to an embodiment of the present invention. As shown in FIG. 9, the method 400 includes the following.
  • an environment map is obtained, the environment map including a pass cost through each of the plurality of first regions for indicating each of the first regions within the plurality of first region coverages And a characterization value, wherein, the pass cost of each of the first regions is determined by a pass distance of each of the first regions, and a characterization value of an environmental feature of each of the first regions.
  • path planning is performed using the environment map.
  • the location to be operated is selected from the plurality of locations according to the map.
  • the robot does not actively move to the characteristic value of the environmental feature does not meet the traffic demand, thereby improving the stability of the environmental feature input, improving the robustness of the corresponding function of the robot, and the robot finds that the characteristic value of the environmental feature is not satisfied.
  • the map can be actively run to the area where the characterization value of the environmental characteristics can meet the traffic demand, and the stability and user experience of the robot use are improved.
  • a starting location and a target location are obtained; using the map, a path from the starting location to the target location is determined.
  • the specific implementation of the path planning method shown in FIG. 9 may be referred to the description in the method 200.
  • details are not described herein again.
  • FIG. 10 is a schematic block diagram of a path planning apparatus 500 in accordance with an embodiment of the present invention.
  • the path planning apparatus 500 includes: a first acquiring unit 510, configured to perform a characterization according to a traffic distance of each of the plurality of first regions, and an environmental feature of each of the first regions a value, obtaining a pass cost through each of the first regions; a second obtaining unit 520, configured to obtain a start location and a target location; and a path planning unit 530, configured to: according to the pass through each of the first regions
  • the pass cost performs path planning to determine a travel path from the start location to the target location, the pass path including an area from the start location to the target location.
  • the apparatus 600 further includes a map generating unit 540, configured to: generate an environment map according to a pass cost through each of the first areas, where the environment map includes a pass through each of the first areas a cost for indicating a characterization value of each of the first regions in the coverage of the plurality of first regions; the path planning unit 530 is further configured to: according to the environment map, The transit cost for each of the regions within the range determines the transit path.
  • a map generating unit 540 configured to: generate an environment map according to a pass cost through each of the first areas, where the environment map includes a pass through each of the first areas a cost for indicating a characterization value of each of the first regions in the coverage of the plurality of first regions; the path planning unit 530 is further configured to: according to the environment map, The transit cost for each of the regions within the range determines the transit path.
  • the first acquiring unit 510 is further configured to: determine, according to the traffic distance of each of the first regions, a first traffic cost component corresponding to the traffic distance of each of the first regions; Determining a characterization value of an environmental feature of each of the first regions, determining a second pass cost component corresponding to the characterization value of the environmental feature of each of the first regions; according to the first of each of the first regions The pass cost component and the second pass cost component calculate a pass cost through each of the first regions.
  • the first obtaining unit 510 is further configured to: acquire at least one type of task to be executed when passing the path; and select at least one environment that is available according to each of the at least one task type And characterizing, at each of the first regions, a second pass cost component corresponding to each of the task types at each of the first locations; according to the first of each of the first regions a pass cost component, and a second pass cost component corresponding to each of the first regions of each task type, calculating a pass cost through each of the first regions when performing each of the task types;
  • the path planning unit 530 is further configured to: determine, according to the pass cost of each of the first regions, when performing each of the task types, the pass path for executing each of the task types.
  • the at least one task type includes a first task type
  • the first obtaining unit 510 is further configured to: according to the environmental features available in the first task type at each of the first regions And characterizing a value of the at least one environmental feature that satisfies the predetermined condition, and determining a second pass cost component corresponding to the first task type at each of the first regions.
  • the first area is an area that satisfies the following condition: at the first area, a feature value of an environmental feature that is available for the first task type satisfies a requirement of the first task type for an environmental feature.
  • the first obtaining unit 510 is further configured to: determine at least one second area, where, at the second area, a representation value of an environmental feature that is available by the first task type does not satisfy the first A requirement of a task type for an environmental feature; the path planning unit 530 is further configured to: treat each second region of the at least one second region as an obstacle when performing path planning.
  • the first obtaining unit 510 is further configured to: acquire a plurality of task types to be executed when passing the transit path; and select at least one environmental feature that is available according to each of the plurality of task types Characterizing values, obtaining the second pass cost component corresponding to the plurality of task types as a whole at each of the first regions; according to the first pass cost component of each of the first regions, and the plurality of a task type as a second pass cost component corresponding to each of the first regions as a whole, and calculating a corresponding pass cost of the plurality of task types as a whole at each of the first regions; the path planning unit 530 further And for determining, according to the plurality of task types as a whole, a corresponding pass cost at each of the first regions, determining the pass path for executing the plurality of task types.
  • the first obtaining unit 510 is further configured to: obtain, according to the characterization value of the at least one environmental feature that is available for each of the multiple task types at each of the first regions a second pass cost component corresponding to each of the first regions of each task type; weighting processing a plurality of second pass cost components corresponding to the plurality of task types at each of the first regions, The second pass cost component corresponding to the plurality of task types as a whole at the first region is obtained.
  • the first area is an area that satisfies the following conditions: at the first area, a representation value of an environmental feature available for each of the plurality of task types meets each of the task type pairs Environmental characteristics requirements.
  • the first obtaining unit 510 is further configured to: determine at least one third area, where, at the third area, at least one of the multiple task types corresponds to an environmental feature The characterization value does not satisfy the requirement of the feature value of the at least one task type; the path planning unit 530 is further configured to: treat each third region of the at least one third region as an obstacle when performing path planning Things.
  • the first obtaining unit 510 is further configured to: determine, according to the correspondence between the characteristic value interval of the environment feature and the traffic cost component, and the representation value of the environmental feature of each region, The second pass cost component of the first region.
  • the first obtaining unit 510 is further configured to: according to the passing distance of each of the first regions, and the characterization value of the environmental features of each of the first regions acquired multiple times, in a statistical manner Obtaining a pass cost through each of the first regions; or, according to the pass distance of each of the first regions, and a representation value of an environmental feature of each of the first regions acquired in real time, real-time acquisition is performed by a pass cost for each of the first regions; or, based on the pass distance of each of the first regions, and a predicted value of the environmental feature of each of the predicted first regions, obtained through each of the first regions The cost of the passage.
  • the first obtaining unit 510 is further configured to: according to the case where the rate of change of the characteristic value of the environmental feature of each of the first regions is less than or equal to a first threshold, according to each of the first regions The transit distance, and the characterization values of the environmental features of each of the first regions acquired multiple times, acquires the pass cost through each of the first regions in a statistical manner.
  • the first obtaining unit 510 is further configured to: according to the change rate of the characteristic value of the environmental feature of each of the first regions is greater than a second threshold, according to the pass of each of the first regions The distance, and the characterization values of the environmental features of each of the first regions obtained in real time, acquire the transit cost through each of the first regions in real time.
  • the environmental feature includes a visual signal; the first acquiring unit 510 is further configured to: according to a representation value of a visual signal in each of the plurality of directions passing through each of the first locations, Acquiring a second pass cost component corresponding to each direction of each of the first locations; and corresponding to each direction of each of the first regions according to the first pass cost component of each of the first regions The second pass cost component determines a pass cost in each of the directions through each of the first regions.
  • the environmental characteristic comprises at least one of a visual signal, a sound signal, and a contact surface state.
  • the environmental feature comprises a visual signal, the representative value of the visual signal comprising a light intensity and/or a number of visual features.
  • the environmental feature comprises a sound signal, the representative value of the sound signal comprising an intensity of the sound signal.
  • the environmental feature comprises a contact surface state, the characterization value of the contact surface state comprising a slope of the contact surface at the location, a rate of change in height, and/or a degree of friction.
  • path planning apparatus 500 can perform the method shown in FIG. 2, and details are not described herein for brevity.
  • FIG. 11 is a schematic block diagram of a map generation device 600 in accordance with an embodiment of the present invention.
  • the device 600 includes an acquisition unit 610 and a map generation unit 620.
  • the obtaining unit 610 is configured to acquire a transit cost through each of the first regions according to a transit distance of each of the plurality of first regions and a representation value of an environmental feature of each of the first regions;
  • the map generating unit 620 is configured to generate an environment map according to a pass cost through each of the first regions, where the environment map includes a pass cost through each of the first regions, and is used to mark the plurality of first regions A characterization value for each of the first regions within the coverage.
  • the manner in which the obtaining unit 610 obtains the pass-through cost and the manner in which the map generating unit 620 generates the map may be referred to the description of the above method. For brevity, no further details are provided herein.
  • FIG. 12 is a schematic block diagram of a path planning apparatus 700 in accordance with an embodiment of the present invention.
  • the apparatus 700 includes an acquisition unit 710 and a path planning unit 720.
  • the obtaining unit 710 is configured to acquire an environment map, where the environment map includes a pass cost through each of the first regions, and is used to mark a representation of each of the first regions in the coverage of the plurality of first regions. a value, wherein, the pass cost of each of the first regions is determined according to a transit distance of each of the plurality of first regions, and a characterization value of the environmental features of each of the first regions.
  • the path planning unit 720 is configured to perform path planning by using the environment map.
  • the manner in which the obtaining unit 710 obtains the environment map and the manner in which the path planning unit 720 performs the path planning may be referred to the description of the above method. For brevity, details are not described herein again.
  • FIG. 13 is a schematic block diagram of an intelligent execution device 800 in accordance with an embodiment of the present invention.
  • the smart executive device 800 may refer to a mechanical device that automatically performs work, for example, may be a robot, a driverless car, or a drone.
  • the smart executive device 800 can include a control system 810, a drive mechanism 820, a sensor 830, an actuator 840, and an external output device 850.
  • the control system 810 can send an instruction to the drive mechanism 820, and the drive mechanism 820 can drive the actuator 840 to perform a corresponding action according to an instruction issued by the control system 810.
  • the control system 810 can output a signal to the outside through the external output device 850.
  • the external output device 850 can include a display, a voice output device, or a wireless transmitter, etc., wherein the display can display power, or display a planned path, etc., and the voice output device can cooperate with the sensor for detecting voice to implement a dialogue with the user.
  • the wireless transmitter can send wireless signals and the like.
  • Sensor 830 can include an internal information sensor and an external information sensor.
  • the internal information sensor can detect the working condition of each part of the intelligent execution device, for example, the position, the speed and the acceleration of each joint included in the actuator 840, and the external information sensor can detect the external information, for example, the embodiment of the present application can be obtained.
  • Other characteristics such as obtaining a voice command input by a user, receiving a wireless signal, and the like can also be obtained by referring to the characterization value of the environmental feature or the like.
  • the sensor 830 can provide the acquired information to the control system 810, which can issue commands to the drive mechanism 820 based on the sensor information and/or externally output signals via the external output device 850.
  • the drive mechanism 820 may be an electric drive device such as a stepper motor or a servo motor or the like.
  • the actuator 840 is configured to perform a corresponding action in accordance with the driving of the drive mechanism 820.
  • the actuator 840 can employ a spatial open chain link mechanism, wherein the rotary pair can be referred to as a joint, and the number of joints can determine the degree of freedom of the smart actuator.
  • the actuator 800 as an example of the robot, the actuator may include a hand, a wrist, an arm, a walking portion, etc., and the portions may optionally be connected by joints.
  • control system 810 can include a processor 814 and a memory 812.
  • the memory 812 can store program code
  • the processor 814 can execute the program code stored in the memory 812.
  • the processor 814 and the memory 812 communicate with each other through an internal connection path.
  • the method shown in FIG. 2, FIG. 8, or FIG. 9 may be performed at processor 814 by invoking program code stored in memory 812. And, optionally, the processor 814 can call the program code stored in the memory 812 to issue an instruction to the drive mechanism 820. And, optionally, the processor 814 can call the program code stored in the memory 812 to output a signal to the external output device 850.
  • the smart execution device 800 shown in FIG. 13 is only an optional embodiment of the present application.
  • the smart execution device of the embodiment of the present application may further have other mechanisms.
  • the smart execution device 800 may not include external output.
  • the device, or the wireless transceiver included in the external output device can be integrated with the receiver in the sensor.
  • the processor in the embodiment of the present invention may be an integrated circuit chip with signal processing capability.
  • the processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA), or the like. Programming logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention may be implemented or carried out.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be a read-only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (Erasable PROM, EPROM), or an electric Erase programmable read only memory (EEPROM) or flash memory.
  • the volatile memory can be a Random Access Memory (RAM) that acts as an external cache.
  • RAM Random Access Memory
  • many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (Synchronous DRAM).
  • SDRAM Double Data Rate SDRAM
  • DDR SDRAM Double Data Rate SDRAM
  • ESDRAM Enhanced Synchronous Dynamic Random Access Memory
  • SLDRAM Synchronous Connection Dynamic Random Access Memory
  • DR RAM direct memory bus random access memory
  • the disclosed systems, devices, and methods may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product.
  • the technical solution of the present invention which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
  • the instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Social Psychology (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Atmospheric Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Ecology (AREA)
  • Environmental & Geological Engineering (AREA)
  • Environmental Sciences (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明实施例提供了一种路径规划方法和装置，可以实现更优化的路径规划。该方法包括：根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价；获取起始位置和目标位置；根据通过所述每个第一区域的所述通行代价进行路径规划，确定从所述起始位置到达所述目标位置的通行路径，所述通行路径包括从所述起始位置到达所述目标位置经过的区域。

Description

路径规划方法和装置
本申请要求于2017年1月18日提交中国专利局、申请号为201710034754.2、申请名称为“路径规划方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明实施例涉及智能控制领域，并且更具体地，涉及一种路径规划方法和装置。
背景技术
路径规划是智能控制研究领域中的一个重要分支，采用良好的路径规划技术可以节省智能执行装置(例如，机器人)的作业时间，提高执行任务的效率，并且可以提高执行任务的质量。
在进行路径规划时，可以采用地图，以实现路径规划，在现有的技术中，地图包括位置信息和障碍物的信息，从而智能执行装置可以基于该地图找到能够绕开障碍物的路径。
但是在现有的路径规划中，仅考虑位置信息和障碍物信息，并没有考虑其他因素，限制了路径规划的应用。
发明内容
本发明实施例提供了一种路径规划方法和设备，可以实现更优化的路径规划。
第一方面，提供了一种路径规划方法，包括：根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价；获取起始位置和目标位置；根据通过所述每个第一区域的所述通行代价进行路径规划，确定从所述起始位置到达所述目标位置的通行路径，所述通行路径包括从所述起始位置到达所述目标位置经过的区域。
因此，根据多个第一区域中每个第一区域的通行距离，以及该每个第一区域的环境特征的表征值，获取通过该每个第一区域的通行代价，并根据该通行代价，进行路径规划，从而可以在进行路径规划时，不仅考虑区域的通行距离，还可以考虑该区域处的环境特征的表征值，可以实现更为优化的路径规划，并且将通行距离和表征值统一量化为通行代价，可以使得智能执行装置在进行路径规划时，基于该通行代价获取通行路径，可以节省智能执行装置的作业时间，提高执行任务的效率。
可选地，该通行路径可以是通行代价最小的路径。
可选地，所述方法还包括：根据通过所述每个第一区域的通行代价，生成环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述多个第一区域覆盖范围内所述每个第一区域的表征值；所述根据通过所述每个第一区域的所述通行代价进行路 径规划，确定从所述起始位置到达所述目标位置的通行路径，包括：基于所述环境地图，根据通过所述多个区域覆盖范围内每个所述区域的通行代价确定所述通行路径。
因此，根据多个第一区域中每个第一区域的通行距离，以及该每个第一区域的环境特征的表征值，获取该每个第一区域处的通行代价，并生成标示有每个区域的通行代价的环境地图，可以得到更优的地图。
可选地，该环境地图可以是一个通行代价列表或者全局同行代价拓扑图。
可选地，所述根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价，包括：根据所述每个第一区域的通行距离，确定所述每个第一区域的所述通行距离对应的第一通行代价分量；根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量；根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价。
因此，针对每种任务类型，分别计算该任务类型在每个区域处的通行代价，由此在进行某一种任务类型的路径规划时，可以直接获取各个区域针对该任务类型的通行代价，从而可以实现更为优化的路径规划。
可选地，所述方法还包括：获取通过所述通行路径时待执行的至少一种任务类型；所述根据所述每个第一区域的环境特征的表征值，获取所述每个第一区域的所述通行距离对应的第二通行代价分量，包括：根据所述至少一种任务类型中每种任务类型可用的至少一种环境特征在所述每个第一区域处的表征值，获取所述每种任务类型在所述每个第一位置处对应的第二通行代价分量；所述根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价，包括：根据所述每个第一区域的所述第一通行代价分量，和所述每种任务类型在所述每个第一区域对应的第二通行代价分量，计算执行所述每种任务类型时通过所述每个第一区域的通行代价；所述根据通过所述每个第一区域的所述通行代价进行路径规划，包括：根据执行所述每种任务类型时通过所述每个第一区域的通行代价，确定用于执行所述每种任务类型的所述通行路径。
可选地，所述至少一种任务类型包括第一任务类型，所述获取执行所述每种任务类型在所述每个第一区域处对应的所述第二通行代价分量，包括：根据在所述每个第一区域处，所述第一任务类型可用的环境特征中表征值满足预定条件的至少一种环境特征的表征值，确定所述第一任务类型在所述每个第一区域处对应的第二通行代价分量。
可选地，所述第一区域为满足以下条件的区域：在所述第一区域处，所述第一任务类型可用的环境特征的特征值满足所述第一任务类型对环境特征的要求。
可选地，所述方法还包括：确定至少一个第二区域，其中，在所述第二区域处，所述第一任务类型可用的环境特征的表征值不满足所述第一任务类型对环境特征的要求；在进行路径规划时，将所述至少一个第二区域中每个第二区域视为障碍物。
可选地，所述方法还包括：获取通过所述通行路径时待执行的多种任务类型；所述根据所述每个第一区域的环境特征的表征值，获取所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量，包括：根据所述多种任务类型中每种任务类型可用的至少一种环境特征的表征值，获取所述多种任务类型作为整体在所述每个第一区域处对应的第二通行代价分量；所述根据所述每个第一区域的所述第一通行代价分量和所述第二通行代 价分量，计算通过所述每个第一区域的通行代价，包括：根据所述每个第一区域的所述第一通行代价分量，和所述多种任务类型作为整体在每个第一区域处对应的第二通行代价分量，计算所述多种任务类型作为整体在所述每个第一区域处对应的通行代价；所述根据通过所述每个第一区域的所述通行代价进行路径规划，包括：根据所述多种任务类型作为整体在所述每个第一区域处对应的通行代价，确定用于执行所述多种任务类型的所述通行路径。
因此，针对多种任务类型，可以将该多种任务类型作为整体在每个区域处的通行代价，由此在进行需要执行多种任的路径规划时，可以直接获取各个区域针对该多种任务整体的通行代价，从而可以节省智能执行装置的处理时间，提高处理效率。
可选地，所述获取所述多种任务类型作为整体在所述每个第一区域处对应的第二通行代价分量，包括：根据所述每个第一区域处，所述多种任务类型中每种任务类型可用的至少一种环境特征的表征值，得到所述每种任务类型在所述每个第一区域处对应的第二通行代价分量；对所述多种任务类型在所述每个第一区域处对应的多个第二通行代价分量进行加权处理，以得到所述多种任务类型作为整体在所述第一区域处对应的所述第二通行代价分量。
可选地，所述第一区域为满足以下条件的区域：在所述第一区域处，所述多种任务类型中每种任务类型可用的环境特征的表征值满足所述每种任务类型对环境特征的要求。
可选地，所述方法还包括：确定至少一个第三区域，其中，在所述第三区域处，所述多种任务类型中的至少一种任务类型对应的环境特征的表征值不满足所述至少一种任务类型对特征值的要求；在进行路径规划时，将所述至少一个第三区域中每个第三区域视为障碍物。
可选地，所述根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量，包括:根据环境特征的表征值区间与通行代价分量的对应关系，以及所述每个区域的环境特征的表征值，确定所述获取所述每个第一区域的所述第二通行代价分量。
可选地，所述根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价，包括：根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价；或，根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的环境特征的表征值，实时获取通过所述每个第一区域的通行代价；或，根据所述每个第一区域的通行距离，以及预测的所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域处的通行代价。
可选地，所述根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价，包括：在所述每个第一区域的环境特征的变化率小于等于第一阈值的情况下，根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价。
可选地，所述根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的环境特征的表征值，实时获取通过所述每个第一区域的通行代价，包括：在所述每个 第一区域的环境特征的变化率大于第二阈值的情况下，根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的所述环境特征的表征值，实时获取通过所述每个第一区域的通行代价。
可选地，所述环境特征包括视觉信号；所述根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量，包括：根据通过所述每个第一位置的所述多个方向中每个方向上的视觉信号的表征值，获取所述每个第一位置的每个方向对应的第二通行代价分量；所述根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价，包括：根据所述每个第一区域的所述第一通行代价分量，和所述每个第一区域的每个方向对应的第二通行代价分量，确定通过所述每个第一区域的所述每个方向上的通行代价。
可选地，所述环境特征包括视觉信号、声音信号和接触面状态中的至少一种。
可选地，所述环境特征包括视觉信号，所述视觉信号的表征值包括光线强度和/或可视特征的数量。
可选地，所述环境特征包括声音信号，所述声音信号的表征值包括所述声音信号的强度。
可选地，所述环境特征包括接触面状态，所述接触面状态的表征值包括所处位置的接触面的倾斜度、高度改变率和/或摩擦度。
第二方面，提供了一种路径规划装置，该路径规划装置可以包括用于执行第一方面或其任一可选的实现方式中的方法的单元。
第三方面，提供了一种路径规划装置，该路径规划装置可以包括存储器和处理器，该存储器可以存储程序代码，该处理器和该存储器之间通过内部连接通路互相通信，该处理器可以调用该存储器中存储的程序代码执行第一方面或其任一种可选实现方式中的方法。
第四方面，提供了一种存储介质，该存储介质可以存储程序代码，该存储器中存储的程序代码可以被处理器调用，以执行第一方面或其任一种可选实现方式中的方法。
附图说明
图1是根据本发明实施例的用于路径规划的系统的示意性图。
图2是根据本发明实施例的路径规划方法的示意性流程图。
图3是根据本发明实施例的根据通行代价进行路径规划的示意图。
图4是根据本发明实施例的根据通行代价进行路径规划的示意图。
图5是根据本发明实施例的根据通行代价进行路径规划的示意图。
图6是根据本发明实施例的根据通行代价进行路径规划的示意图。
图7是根据本发明实施例的根据通行代价进行路径规划的示意图。
图8是根据本发明实施例的地图生成方法的示意性流程图。
图9是根据本发明实施例的路径规划方法的示意性流程图。
图10是根据本发明实施例的路径规划装置的示意性框图。
图11是根据本发明实施例的地图生成设备的示意性框图。
图12是根据本发明实施例的路径规划装置的示意性框图。
图13是根据本发明实施例的处理设备的示意性框图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行描述。
图1是根据本发明实施例的用于路径规划的系统的示意性图。如图1所述，在该系统中，可以包括环境系统110和智能执行装置120。
环境系统110可以产生环境特征，其中，环境特征可以包括视觉信号、声音信号和接触面状态中的至少一种。当然，环境特征也可以包括其他特征，在此不做具体限定。
智能执行装置120可以基于环境系统110产生的环境特征的表征值，进行路径规划。
具体地，智能执行装置120可以基于环境特征的表征值，生成环境地图，并基于该环境地图，进行路径规划。
可选地，该系统还可以包括智能执行装置130。
智能执行装置120还可以将生成的环境地图，发送给智能执行装置130。智能执行装置130可以基于智能执行装置120发送的环境地图，进行路径规划。
应理解，本发明实施例提到的智能执行装置可以是指自动执行工作的机器装置，例如，可以为机器人，无人驾驶汽车，或无人机等。虽然图1所示的智能执行装置120和130为机器人，但是仅仅便于读者理解，并不是为了限制本发明的范围。类似地，环境系统110的图示方式不应对本发明实施例的范围构成任何限定。
在进行路径规划时，可以将备选区域划分为多个区域，在全部或部分区域处标记通过该区域的通行代价，通行代价越大意味着通过该区域付出的代价越大，在路径规划时，被选中的机率越小。
可选地，通行代价可以是一个数值，所有的区域可以基于相同的标准得到各个区域对应的无单位的数值。
以下将具体描述如何获取通过多个区域的通行代价，并根据多个区域的通行代价生成环境地图，以及描述如何根据多个区域的通行代价，进行路径规划。
图2是根据本发明实施例的一种路径规划方法200的示意性流程图。该方法200可以应用于图1所示的系统。该方法可选的可以由图1所示的智能执行装置120执行。应理解，该方法200可以由其他设备执行，本发明实施例仅以智能执行装置为例进行描述。
如图2所示，该方法200包括以下内容。
在210中，根据多个第一区域中每个第一区域的通行距离，以及该每个第一区域的环境特征的表征值，获取通过该每个第一区域的通行代价。
可选地，智能执行装置可以直接检测各个区域处的环境特征的表征值，或者，也可以接收其他设备发送的环境特征的表征值，或者，也可以接收人工输入的环境特征的表征值。
可选地，智能执行装置在直接检测各个区域处的环境特征的表征值时，可以遍历各个区域得到环境特征的表征值，以用于计算通行代价。
可选地，本发明实施例提到的区域可以称为节点，该区域可以是正方形形结构，也可以是矩形，六角形或者其他任意形状。
可选地，一个地图中所有的区域的通行距离可以相同，也可以不相同。
可选地，第一区域的通行距离指第一区域的任意两点之间的长度，例如，以栅格方式进行区域的划分为例，任意两点之间的长度可以为直行通过的距离或斜行通过的距离。
可选地，本发明实施例提到的环境特征可以包括视觉信号、声音信号和接触面状态中的至少一种。
可选地，所述视觉信号的表征值包括光线强度和/或可视特征的数量。
可选地，视觉信号可以用于定位，例如可以通过可视特征进行定位，因此，如果可视特征数量多，则认为更易于定位，在进行定位时，光线强度也会影响到定位，例如，光线强度符合智能执行设备本身的视觉要求，则更易于定位。
可选地，所述环境特征包括声音信号，所述声音信号的表征值包括所述声音信号的强度。
可选地，该声音信号可以分为噪声和有益声音信号，有益声音信号可以包括超声信号，可以通过该信号进行定位。
例如，可以记录各个区域的噪声的强度，如果某一位置的噪声强度小或无噪声，该位置处更易通行。
再例如，在通过声音进行通信或定位时，如果某一区域的声音信号强度大，则认为该区域处更易通行。
可选地，所述接触面状态的表征值包括所处位置的接触面的倾斜度、高度改变率和/或摩擦度。
例如，假设接触面为路面，则路面的表征值可以为路面难行或颠簸程度，是否泥泞，打滑情况，路面倾斜角度情况等。
其中，可以人工获取接触面的状态，或者利用设备自探来识别不同位置处的接触面状态。
例如，可以根据路面情况进行人工打分。例如遇到有水的路面记为0分，路面泥泞记为10分，路面倾斜角度大于5度记为0分，打滑程度或颠簸程度超过某阈值记为10分，其他情况都记为100分，根据分值确定通行代价，例如，分值越高，则通行代价越低。
例如，可以采用视觉识别的办法估计路面材质。如果地面有电线，门槛，楼梯等视觉能够识别的物体，可以对此进行量化得到表征值。可以采用多种定位方式和机器人里程计信息比对的方法来估计打滑程度，可以通过记录电机输出功率估计相应路段的难行程度。路面倾角可以通过机器人自带重力计或摄像头等传感器计算得出。
应理解，本发明实施例提到的第一区域可以是备选区域中的任意区域，也可以是满足一定条件的区域，例如，环境特征的表征值满足一定条件的区域，在该区域下可以计算通行代价，对于不满足条件的区域，可以直接将该区域视为障碍物。
应理解，在本发明实施例中通过第一区域的通行代价有时也可以称为第一区域的通行代价或第一区域处的通行代价。
可选地，在本发明实施例中，智能执行装置可以根据通过所述每个第一区域的通行代价，生成环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述多个第一区域覆盖范围内所述每个第一区域的表征值，该环境地图可以进行路径规划。
可选地，该环境地图可以是一个通行代价列表或者全局同行代价拓扑图。
应理解，本发明实施例中，环境地图可以对环境特征的表征值起到标示作用，但并 不意味着地图中各个区域的通行代价仅与环境特征的表征值有关系，还与各个区域的通行距离有关系，例如，如果通行距离不一致，相同的通行代价可能环境特征的表征值不一样。
应理解，在本发明实施例中，智能执行装置还可以不生成地图，而是直接根据多个第一区域的通行代价进行路径规划。
可选地，智能执行装置可以采用多次获取的环境特征的表征值，以统计或投票的方式得到的对应区域处的通行代价；或者，也可以采用实时获取的环境特征的表征值，实时获取对应区域处的通行代价；或者，也可以预测的环境特征的表征值获的对应区域的通行代价。
具体地，可以采用多次获取的环境特征的表征值，以统计或投票的方式得到的对应区域处的通行代价，来生成环境地图；或者，也可以采用实时获取的环境特征的表征值得到的对应区域处的通行代价，对环境地图进行实时更新；或者，也可以预测的环境特征的表征值获的对应区域的通行代价，来生成环境地图。
其中，统计方式是指将多次获取的环境特征的表征值进行统一处理，例如，加权处理等，得到对应区域处的通行代价。投票方式是从多次获取的环境特征的表征值中选择部分次获取的环境特征的表征值，以得到对应区域的通行代价。
具体是采用统计或投票的方式获取通行代价，或是实时获取通行代价，或是预测的方式获取通行代价，或者任两种方式的结合获取通行代价，可以结合实际情况而定。
可选地，在环境特征的表征值的稳定性较好时，可以以统计的方式得到对应区域的通行代价；在环境特征的表征值的稳定性较差时，可以实时获取对应无线的通行代价。
例如，在环境特征为视觉信号时，在室外环境下，不同时段的光照条件是不同的，可以按时段进行地图的更新。则，在室内环境(例如，商场营业期间)，相同的时间段的光照条件是基本相同的，则可以统计的方式生成地图。
其中，环境特征的表征值的稳定性可以是指环境特征的改变率，例如，环境特征的强度的改变率小于等于预定值或者方向的改变率小于等于预定值，则认为是稳定性较好。
可选地，在环境特征为可预测的环境特征时，即通过某一时刻和/或某一区域的环境特征的表征值可以预测另一时刻和/或另一区域的环境特征的表征值时，则可以认为该环境特征为可预测的环境特征。
例如，在环境特征是视觉信号时，可以根据某一时间段的光照条件预测其他时间段的光照条件等。在环境特征是声音信号时，可以根据某一时间段的声音信号预测其他时间段的声音信号。在环境信号为路面状态时，可以根据天气预测情况，预测该路面状态。
应理解，本发明实施例对环境特征的表征值的预测方式还可以有其他实现方式，在此不再赘述。
应理解，本发明实施例对环境特征的表征值的预测方式还可以有其他实现方式，在此不再赘述。
可选地，本发明实施例中的环境地图可以包括多个区域处每个区域的通行代价，其中，每个区域的通行代价可以包括多个通行代价，例如，可以包括预测的在各个时刻的通行代价，从而，在进行路径规划时，可以结合某一区域各个时刻的通行代价，以及运行到此处的时刻，得到对应的该区域处的路径规划，从而可以选择出更优的路径。
可选地，本发明实施例中的地图可以包括多个区域处每个区域在多个方向上的通行 代价，其中，每个方向的通行代价是指按照此方向通过该区域时的通行代价。例如，对于环境特征为视觉信号而言，不同的方向可以代具有不同的表征值，例如，背着太阳通行时的表征值不同于顺着太阳通行时的表征值。
假设地图中的某一区域处，通行方向可以包括0度，45度，90度，135度，180度，225度，270度，315度八种方向，可以根据该区域处8个方向时的摄像头采集到的光照条件确定通行代价。
应理解，还可以确定其他数量的通行代价，具体可以根据各个区域的划分形状、智能执行设备的能力和待执行的任务要求等而定。
因此，在本发明实施例中，根据多个第一区域中每个第一区域的通行距离，以及该每个第一区域的环境特征的表征值，获取该每个第一区域处的通行代价，从而可以在生成环境地图时，在该每个区域标识该每个区域处的通行代价，由此在生成环境地图时，可以不仅考虑区域的通行距离，还可以考虑该区域处的环境特征的表征值，将通行距离和环境特征的表征值进行量化得到通行代价，可以得到更优的环境地图，从而使得环境地图的应用范围更为广泛，可以实现更为良好的路径规划，并且将通行距离和环境特征的表征值统一量化为通行代价，可以使得机器人在进行路径规划时，基于该通行代价进行获取通行路径，可以节省机器人作业时间，提高执行任务的效率。
可选地，在本发明实施例中，在结合第一区域的通行距离和环境特征的表征值得到该第一区域处的通行代价时，可以计算通行距离对应的第一通行代价分量，以及环境特征的表征值对应的第二通行代价分量，并结合第一通行代价分量和该第二通行代价分量，得到通过该区域的通行代价。
在一种实现方式中，可以将第一区域的第一通行代价分量与该第二通行代价分量进行相加，得到该第一区域的通行代价。
在另一种实现方式，可以将该第一区域的第一通行代价分量与该第一区域的第二通行代价分量进行加权处理，得到该第一区域的通行代价，其中，加权系数可以根据具体情况而定，例如，如果待执行的任务对区域的通行距离的灵敏度较大，则可以将尺寸的加权系数设置的较高。
在另一种实现方式中，该第二通行代价可以是与该第一通行代价分量进行相乘以得到通行代价的系数，则可以结合该第一通行代价分量和该系数，得到该第一区域处的通行代价。
应理解，在本发明实施例中，除了区域的通行距离以及环境特征的表征值，还可以考虑其他因素，例如，根据无线信号(例如，卫星信号，网络信号等)的信号质量，确定该区域处的第三通行代价分量，则可以将第一通行代价分量、第二通行代价分量和第三通行代价分量进行相加或进行加权处理，得到该区域的通行代价。
可选地，可以根据环境特征的表征值区间与通行代价的对应关系，以及该每个区域的环境特征的表征值，确定该获取该每个区域位置的第二通行代价分量。
例如，可以将环境特征的表征值分为好、中和差三个等级，每个等级均包括可以量化的数值范围，每个等级可以对应不同的第二通行代价分量，在获取环境特征的表征值之后，可以确定该环境特征的表征值所属的等级，并得到该等级对应的第二通行代价分量。
例如，环境特征的表征值好对应的系数为1，环境特征的表征值中对应的系数为5， 环境特征的表征值差对应的系数为10，某一位置处的距离对应的通行代价为10(直行)和14(斜行)，如果该位置处的环境特征的表征值差，则可以将该位置处的直行和斜行的通行代价确定为100和140，如果该位置处的环境特征的表征值为中，则可以将该位置处的直行和斜行的通行代价确定为50和70，如果该位置处的环境特征的表征值为好，则可以将该位置处的直行和斜行通行代价确定为10和14。
应理解，本发明实施例中，环境特征的优劣代表采用该环境特征时，执行任务的难易程度，质量优代表易于执行任务，质量差，代表不易执行任务。
可选地，在本发明实施例中，可以结合通行距离，针对多种环境特征中的每种环境特征在环境地图中设置通行代价，在利用环境地图执行任务时，可以确定该任务可以采用的环境特征，并利用基于该可以采用的环境特征得到的通行代价，进行路径规划。
可选地，在本发明实施例中，可以结合待执行的至少一种任务类型，得到各个区域的通行代价。并且可选地可以将该任务类型对应的通行代价标示在环境地图中，在利用环境地图执行任务时，可以确定该任务对应的通行代价，进行路径规划。其中，待执行的任务包括但不限于定位、通信、联网、探测和识别中的至少一种。
可选地，所述环境特征包括视觉信号；根据通过所述每个第一区域的所述多个方向中每个方向上的视觉信号的表征值，获取所述每个第一区域的每个方向的对应的第二通行代价计算参数；根据所述每个第一区域的所述第一通行代价分量，和通过所述每个第一区域的每个方向上的视觉信号的表征值对应的第二通行代价分量，确定所述每个第一区域处的所述每个方向上的通行代价。
可选地，在本发明实施例中，可以结合地图待执行的至少一种任务类型，得到各个区域的通行代价，在利用地图执行任务时，可以确定该任务对应的通行代价，进行路径规划。其中，地图可以执行的任务包括但不限于定位、通信、联网、探测和识别中的至少一种。
可选地，结合任务类型对环境特征的表征值的要求，以及环境特征的表征值，确定无线通行代价，例如，如果任务类型A和任务类型B均用到环境特征a，其中，任务类型A对环境特征的要求高于任务类型B对于环境特征的要求，则相同的表征值，任务类型A对应的通行代价分量高于任务类型B对应的通行代价分量。
以下将结合方式A和方式B描述在生成环境地图时，如何结合待执行的任务类型来得到各个区域处的通行代价。
方式A
获取待执行的至少一种任务类型；根据该至少一种任务类型中每种任务类型可用的至少一种环境特征在该每个第一区域处的表征值，获取该每种任务类型在该每个第一区域处的第二通行代价分量；根据该每个第一区域的该第一通行代价分量，和该每种任务类型在该每个第一区域处的第二通行代价分量，计算该每种任务类型在该每个第一区域处的通行代价。
可选地，可以根据每种任务类型在该每个第一区域处的通行代价，生成该环境地图，其中，该环境地图包括该每种任务类型在该每个第一区域处的通行代价。
也就说，针对每种任务类型，分别计算该任务类型在每个区域处的通行代价，由此在进行某一种任务类型的路径规划时，可以直接获取各个区域针对该任务类型的通行代 价，从而可以实现更为良好的路径规划。
其中，在计算每种任务类型在某个区域的第二通行代价分量时，可以结合任务类型对环境特征的表征值的要求，以及环境特征的表征值，确定通行代价。
可选地，该至少一种任务类型包括第一任务类型，根据在该每个第一区域处，该第一任务类型可用的环境特征中表征值满足预定条件的至少一种环境特征的表征值，确定该第一任务类型在该每个第一区域处的第二通行代价分量。
可选地，满足预定条件的至少一种环境特征可以指环境特征的表征值优于一定门槛的表征值，或者表征值最优的一种表征值。
具体地说，由于针对某一任务，在可用的环境特征存在多种的情况下，由于在智能执行装置运行此处执行待执行的任务时，可以选择质量较优的环境特征，则可以选择质量较优的环境特征进行通行代价分量的计算，例如，对于任务为定位，如果某一区域处可以通过可视特征的数量和声音信号进行定位，则可以预估该两种方式的定位精度，将定位精度较好的环境特征的定位精度确定为用于确定该区域处的通行代价的参数。
当然，对于第一任务类型而言，某区域处存在多种可用的环境特征，可以结合该多种环境特征的表征值计算第二通行代价分量，例如，对多种环境特征的表征值进行加权处理，加权处理得到的表征值用于计算第二通行代价分量，或者，对多种环境特征的表征值分别计算第二通行代价分量，对于得到的多个第二通行代价分量可以进行加权处理，得到最终可用的第二通行代价分量。当然，除了加权处理，也可以是其他处理方式，具体可以根据实际情况而定，例如，如果存在多种环境特征，该多种环境特征可以累加使用，则可以将该多种环境特征的表征值进行类似相加处理，并进一步计算得到第二通行代价分量。
可选地，该第一区域可以是备选区域中包含的任意区域，也可以是满足以下条件的区域：该每个第一区域处，该第一任务类型可用的环境特征的表征值满足该第一任务类型对环境特征的要求。
可选地，确定至少一个第二区域，其中，在该第二区域处，该第一任务类型可用的环境特征的表征值不满足该第一任务类型对环境特征的要求；在进行路径规划时，可以将该第二区域视为障碍物。
可选地，在该环境地图中，针对该第一任务类型，将该至少一个第二区域中每个第二区域标识为障碍物。
方式B
获取待执行的多种任务类型；根据该多种任务类型中每种任务类型可用的至少一种环境特征的表征值，获取该多种任务类型作为整体在该每个第一区域处的第二通行代价分量；根据该每个第一区域的该第一通行代价分量，和该多种任务类型作为整体在每个第一区域处的第二通行代价分量，计算该多种任务类型作为整体在该每个第一区域处的通行代价。
可选地，可以根据该多种任务类型作为整体在该每个第一区域处的通行代价，生成该环境地图，该环境地图包括该多种任务类型作为整体在该每个第一区域处的通行代价。
也就说，针对多种任务类型，可以将该多种任务类型作为整体在每个区域处的通行代价，由此在进行需要执行多种任的路径规划时，可以直接获取各个区域针对该多种任务整体的通行代价，从而可以实现更为良好的路径规划。
可选地，根据该每个第一区域处，该多种任务类型中每种任务类型可用的至少一种环境特征的表征值，得到该每种任务类型在该每个第一区域处的第二通行代价分量；对该多种任务类型在该每个第一区域处的多个第二通行代价分量进行加权处理，以得到该多种任务类型作为整体在该第一区域处的该第二通行代价分量。
除了加权处理，也可以是其他处理方式，具体可以根据实际情况而定，例如，则可以将该多种类型的环境特征的表征值进行类似相加处理，并进一步计算得到第二通行代价分量。或者，将多个任务类型对应的多个第二通行代价分量进行相加处理，作为该多种任务类型作为整体所对应的通行代价。
应理解，在本发明实施例中，在多种任务类型作为整体计算在某一区域处的第二通行代价分量时，采用的每种任务类型可用的至少一种环境特征可以是对应的任务类型在该区域处的全部可用的环境特征，也可以是部分可用的环境特征，例如，表征值最优的至少一种环境特征。
可选地，该第一区域可以是环境地图中需要包含的任意区域，也可以是满足以下条件的区域：在该每个第一区域处，该多种任务类型中每种任务类型可用的环境特征的表征值满足该每种任务类型对环境特征的要求。
可选地，确定至少一个第三区域，其中，在该第三区域处，该多种任务类型中的至少一种任务类型对应的环境特征的表征值不满足该至少一种任务类型对表征值的要求；在进行路径规划时，可以将第三区域视为障碍物。
可选地，在该环境地图中，针对该多种任务类型，将该至少一个第三区域中每个第三区域设置为障碍物。
应理解，在生成环境地图时，以上方式A和方式B可以结合使用。
例如，利用该环境地图待执行的任务包括任务1、任务2和任务3，可以分别针对任务1任务2和任务3分别计算通行代价，以及将任务1、任务2和任务3结合计算通行代价；或者，计算任务1的通行代价，将任务2和任务3结合计算通行代价。
应理解，在本发明实施例中，环境特征的“种”划分可以是指环境特征类型本身的不同，例如，视觉信号和声音信号即认为不同种的环境特征；也可以是同类型的环境特征的不同来源，例如，例如视觉信号中来自太阳的光线和来自灯的光线，“种”的区分维度可以根据具体实际情况而定。
类似地，关于任务类型的“种类”的划分也可以结合具体情况而定，例如，农业用途与工业用途为不同种类的任务类型，例如，定位和通信为不同的任务类型。
在220中，获取起始位置和目标位置。
在230中，根据通过该每个第一区域的该通行代价进行路径规划，确定从该起始位置到达该目标位置的通行路径，该通行路径包括从该起始位置到达该目标位置经过的区域。
可选地，在本发明实施例中，可以利用环境地图，确定从起始位置到目标位置的路径。
其中，在利用环境地图进行路径规划时，可以采用多种算法，例如，Dijksra算法、A*算法等。
为了便于理解，以下将结合A*搜索算法描述如何实现路径的规划。
其中，在A*算法中，需要用到以下公式1：
F(n)＝G(n)+H(n)             公式1
其中，F(n)是从初始节点经由中间节点n到目标节点估计的通行代价；G(n)是从起始节点到中间节点n的实际获取的通行代价；H(n)是从中间节点n到目标节点的最佳路径的通行代价的估计。
其中，H(n)计算可以通过曼哈顿算法或其算法，在此不再具体限定。
其中，找到最优路径的条件，关键在于估价函数F(n)的选取。为了更加清楚地理解该算法，以下将具体描述该算法的执行方式。
步骤一、将起始节点添加到开启列表中。
步骤二、重复如下的操作:
a)寻找开启列表中F值最低的节点，也即当前节点；
b)将当前节点切换到关闭列表；
c)对当前节点的每个相邻节点执行以下操作：
(1)如果相邻节点不可通过或者已经在关闭列表中，忽略该节点，反之如下：
(2)如果不在开启列表中，将该相邻节点添加进去，把当前节点作为该节点的回溯节点，记录该节点的F、G和H值；
(3)如果该相邻节点已经在开启列表中，用G值为参考检查新的路径是否更好。如果是这样，将该相邻节点的回溯节点作为当前节点，并且重新计算该节点的G和F值。
d)存在以下两种情况停止：
(1)把目标节点添加至关闭列表，这时候路径已经被找到；
(2)没有找到目标路径，这时开启列表已经空了，此时表示没有找到路径。
步骤三、保存路径。从目标节点，从目标节点开始，沿着每一节点的回溯节点移动至起始节点，即为选择的路径。
为了更加清楚地理解A*算法的实现方式，以下将结合图3-6进行描述。
其中，图3所示的为起始节点，障碍物与目标节点的位置关系。
图4、图5和图6所示为仅以节点的通行距离对应的通行代价计算路径，其中，假设各个节点的直行和斜行距离分别一致，可以将各个节点的直行距离对应的通行代价记为10，将各个节点的斜行距离对应的通行代价记为14。
图7所示是以节点的通行距离和环境特征的表征值对应的通行代价计算路径。
其中，在图4-7所示的图示中，左下方是G值，右下方是H值，左上方是F值，以及
Figure PCTCN2018073114-appb-000001
指向表示当前节点的回溯节点。
其中，如图3所示，节点A为起始节点，节点B为目标节点，节点A、节点B之间的三个节点O为障碍物，也即不可通行的节点。
如图4所示，在起始节点被切换到关闭列表之后，在开启列表中，查找F值最低的节点，也即与起始节点A右侧紧邻的节点C。将该节点C放入关闭列表中，然后检查节点C相邻的节点，由于左侧的节点是起始节点，右侧的节点是障碍物，可以忽略该两个节点。将节点的另外两个相邻节点放入开启列表中，然后检查开启列表中，用G值为参考检查新的路径是否更好，发现从C节点的上下节点直接与起始节点相通，路径更优。由于C节点的上下节点的F值一致，可以选择最后添加进列表的节点，或者可以随机选择。例如，可如图5所示，选择了节点D。并继续进行选择，直到找到最优路径。最终得到的路径可 以如图6所示，也即从起始节点A到终止节点B需要途径的节点包括节点D、节点E、节点F、节点G和节点H。
图7是在结合环境特征的表征值和区域的通行距离得到的从起始节点A到终止节点B的最优路径。其中，图7所示的环境地图中障碍物左边的三个节点的通行代价被修改为100和140(例如，由于光线条件较差而被修改)。从图中可以看出，该三个节点的上下的两个节点的回溯节点已经发生改变，按照A*算法以及更新后的代价，从节点A到节点B的最优路径需要途径的节点包括节点I，节点E，节点F，节点G和节点H。
因此，从图3-图7可以看出，使用基于环境特征的表征值和通行距离得到的环境地图和使用仅基于通行距离得到的环境地图，最终规划的路径不一样，由此在基于环境特征的表征值和通行距离生成的环境地图进行路径规划，可以考虑更多的因素，使得规划出的路径更优质。
图8是根据本发明实施例的地图生成方法300的示意性流程图。如图8所示，该方法300包括以下内容。
在310中，根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价。
在320中，根据通过所述每个第一区域的通行代价，生成环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述多个第一区域覆盖范围内所述每个第一区域的表征值。
可选地，图8所示的地图生成方法的具体实现可以参考方法300中的描述，为了简洁，在此不再赘述。
图9是根据本发明实施例的路径规划方法400的示意性流程图。如图9所示，该方法400包括以下内容。
在410中，获取环境地图，所述环境地图包括通过多个第一区域中每个第一区域的通行代价，用于标示所述多个第一区域覆盖范围内所述每个第一区域的表征值，其中，所述，每个第一区域的通行代价是所述每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值确定的。
在420中，利用所述环境地图，进行路径规划。
在一种实现方式中，在所述当前位置的环境特征的表征值不满足通行需求时，根据所述地图，从所述多个位置中选择待运行至的位置。
由此，机器人不会主动运动到环境特征的表征值不满足通行需求，从而提高了环境特征输入的稳定性，提高了机器人相应功能的鲁棒性，并且，机器人发现环境特征的表征值不满足通行需求时，能根据地图主动运行到环境特征的表征值能满足通行需求的区域，提高了机器人使用的稳定性和用户体验。
在另一种实现方式中，获取起始位置和目标位置；利用所述地图，确定从所述起始位置到所述目标位置的路径。
可选地，图9所示的路径规划方法的具体实现可以参考方法200中的描述，为了简洁，在此不再赘述。
图10是根据本发明实施例的路径规划装置500的示意性框图。如图10所示，该路径规划装置500包括：第一获取单元510，用于根据多个第一区域中每个第一区域的通行 距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价；第二获取单元520，用于获取起始位置和目标位置；路径规划单元530，用于根据通过所述每个第一区域的所述通行代价进行路径规划，确定从所述起始位置到达所述目标位置的通行路径，所述通行路径包括从所述起始位置到达所述目标位置经过的区域。
可选地，所述装置600还包括地图生成单元540，用于：根据通过所述每个第一区域的通行代价，生成环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述多个第一区域覆盖范围内所述每个第一区域的表征值；所述路径规划单元530进一步用于：基于所述环境地图，根据通过所述多个区域覆盖范围内每个所述区域的通行代价确定所述通行路径。
可选地，所述第一获取单元510进一步用于：根据所述每个第一区域的通行距离，确定所述每个第一区域的所述通行距离对应的第一通行代价分量；根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量；根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价。
可选地，所述第一获取单元510进一步用于：获取通过所述通行路径时待执行的至少一种任务类型；根据所述至少一种任务类型中每种任务类型可用的至少一种环境特征在所述每个第一区域处的表征值，获取所述每种任务类型在所述每个第一位置处对应的第二通行代价分量；根据所述每个第一区域的所述第一通行代价分量，和所述每种任务类型在所述每个第一区域对应的第二通行代价分量，计算执行所述每种任务类型时通过所述每个第一区域的通行代价；所述路径规划单元530进一步用于：根据执行所述每种任务类型时通过所述每个第一区域的通行代价，确定用于执行所述每种任务类型的所述通行路径。
可选地，所述至少一种任务类型包括第一任务类型，所述第一获取单元510进一步用于：根据在所述每个第一区域处，所述第一任务类型可用的环境特征中表征值满足预定条件的至少一种环境特征的表征值，确定所述第一任务类型在所述每个第一区域处对应的第二通行代价分量。
可选地，所述第一区域为满足以下条件的区域：在所述第一区域处，所述第一任务类型可用的环境特征的特征值满足所述第一任务类型对环境特征的要求。
可选地，所述第一获取单元510进一步用于：确定至少一个第二区域，其中，在所述第二区域处，所述第一任务类型可用的环境特征的表征值不满足所述第一任务类型对环境特征的要求；所述路径规划单元530进一步用于：在进行路径规划时，将所述至少一个第二区域中每个第二区域视为障碍物。
可选地，所述第一获取单元510进一步用于：获取通过所述通行路径时待执行的多种任务类型；根据所述多种任务类型中每种任务类型可用的至少一种环境特征的表征值，获取所述多种任务类型作为整体在所述每个第一区域处对应的第二通行代价分量；根据所述每个第一区域的所述第一通行代价分量，和所述多种任务类型作为整体在每个第一区域处对应的第二通行代价分量，计算所述多种任务类型作为整体在所述每个第一区域处对应的通行代价；所述路径规划单元530进一步用于：根据所述多种任务类型作为整体在所述每个第一区域处对应的通行代价，确定用于执行所述多种任务类型的所述通行路径。
可选地，所述第一获取单元510进一步用于：根据所述每个第一区域处，所述多种 任务类型中每种任务类型可用的至少一种环境特征的表征值，得到所述每种任务类型在所述每个第一区域处对应的第二通行代价分量；对所述多种任务类型在所述每个第一区域处对应的多个第二通行代价分量进行加权处理，以得到所述多种任务类型作为整体在所述第一区域处对应的所述第二通行代价分量。
可选地，所述第一区域为满足以下条件的区域：在所述第一区域处，所述多种任务类型中每种任务类型可用的环境特征的表征值满足所述每种任务类型对环境特征的要求。
可选地，所述第一获取单元510进一步用于：确定至少一个第三区域，其中，在所述第三区域处，所述多种任务类型中的至少一种任务类型对应的环境特征的表征值不满足所述至少一种任务类型对特征值的要求；所述路径规划单元530进一步用于：在进行路径规划时，将所述至少一个第三区域中每个第三区域视为障碍物。
可选地，所述第一获取单元510进一步用于：根据环境特征的表征值区间与通行代价分量的对应关系，以及所述每个区域的环境特征的表征值，确定所述获取所述每个第一区域的所述第二通行代价分量。
可选地，所述第一获取单元510进一步用于：根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价；或，根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的环境特征的表征值，实时获取通过所述每个第一区域的通行代价；或，根据所述每个第一区域的通行距离，以及预测的所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域处的通行代价。
可选地，所述第一获取单元510进一步用于：在所述每个第一区域的环境特征的表征值的变化率小于等于第一阈值的情况下，根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价。
可选地，所述第一获取单元510进一步用于：在所述每个第一区域的环境特征的表征值的变化率大于第二阈值的情况下，根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的所述环境特征的表征值，实时获取通过所述每个第一区域的通行代价。
可选地，所述环境特征包括视觉信号；所述第一获取单元510进一步用于：根据通过所述每个第一位置的所述多个方向中每个方向上的视觉信号的表征值，获取所述每个第一位置的每个方向对应的第二通行代价分量；根据所述每个第一区域的所述第一通行代价分量，和所述每个第一区域的每个方向对应的第二通行代价分量，确定通过所述每个第一区域的所述每个方向上的通行代价。
可选地，所述环境特征包括视觉信号、声音信号和接触面状态中的至少一种。
可选地，所述环境特征包括视觉信号，所述视觉信号的表征值包括光线强度和/或可视特征的数量。
可选地，所述环境特征包括声音信号，所述声音信号的表征值包括所述声音信号的强度。
可选地，所述环境特征包括接触面状态，所述接触面状态的表征值包括所处位置的接触面的倾斜度、高度改变率和/或摩擦度。
应理解，该路径规划装置500可以执行图2所示的方法，为了简洁，在此不再赘述。
图11是根据本发明实施例的地图生成设备600的示意性框图。如图11所示，该设备600包括获取单元610和地图生成单元620。获取单元610用于，根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价；地图生成单元620用于根据通过所述每个第一区域的通行代价，生成环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述多个第一区域覆盖范围内所述每个第一区域的表征值。
应理解，该获取单元610获取通行代价的方式，以及地图生成单元620生成地图的方式，可以参考上文方法的描述，为了简洁，在此不再赘述。
图12是根据本发明实施例的路径规划装置700的示意性框图。如图12所示，该装置700包括获取单元710和路径规划单元720。其中，获取单元710用于获取环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述多个第一区域覆盖范围内所述每个第一区域的表征值，其中，所述，每个第一区域的通行代价是根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值确定的。所述路径规划单元720用于利用所述环境地图，进行路径规划。
应理解，该获取单元710获取环境地图的方式，以及路径规划单元720进行路径规划的方式，可以参考上文方法的描述，为了简洁，在此不再赘述。
图13是根据本发明实施例的智能执行装置800的示意性框图。该智能执行装置800可以是指自动执行工作的机器装置，例如，可以为机器人，无人驾驶汽车，或无人机等。
如图13所示，该智能执行装置800可以包括控制系统810、驱动机构820、传感器830、执行机构840和对外输出装置850。
其中，控制系统810可以向驱动机构820发送指令，驱动机构820可以根据控制系统810发出的指令，驱动执行机构840执行相应的动作。
控制系统810可以通过对外输出装置850对外输出信号。可选地，该对外输出装置850可以包括显示器、语音输出装置或无线发送器等，其中，显示器可以显示电量，或者显示规划的路径等，语音输出装置可以配合检测语音的传感器实现与用户的对话等，无线发送器可以发送无线信号等。
传感器830可以包括内部信息传感器和外部信息传感器。其中，内部信息传感器可以检测智能执行装置的各部分的工作状况，例如，执行机构840包括的各关节的位置，速度和加速度等；外部信息传感器可以检测外界信息，例如，可以获取本申请实施例提到的环境特征的表征值等，还可以获取其他信息，例如，获取用户输入的语音指令，接收无线信号等。
传感器830可以将获取的信息提供给控制系统810，控制系统810可以根据传感器的信息，向驱动机构820发出指令和/或通过对外输出装置850对外输出信号。
可选地，驱动机构820可以是电力驱动装置，例如步进电机或伺服电机等。
可选地，执行机构840用于按照驱动机构820的驱动执行相应的动作。执行机构840可以采用空间开链连杆机构，其中的转动副可以称为关节，关节的数量可以决定智能执行机构的自由度。以智能执行机构800为机器人为例，执行机构可以包括手部，腕部，臂部和行走部等，各部分之间可选地可以由关节相连。
可选地，控制系统810可以包括处理器814和存储器812。其中，该存储器812可以存储有程序代码，该处理器814可以执行该存储器812中存储的程序代码。所述处理器814和所述存储器812之间通过内部连接通路互相通信。
可选地，在处理器814可以调用存储器812中存储的程序代码，执行图2、图8或图9所示的方法。以及，可选地，处理器814可以调用存储器812中存储的程序代码，向驱动机构820发出指令。以及，可选地，处理器814可以调用存储器812中存储的程序代码，通过对外输出装置850对外输出信号。
应理解，图13所示的智能执行装置800仅是本申请的一种可选实施例，本申请实施例的智能执行装置还可以有其他机构，例如，该智能执行装置800可以不包括对外输出装置，或者，对外输出装置中包括的无线收发器可以与传感器中的接收器集成在一起。可以理解，本发明实施例中的处理器可以是一种集成电路芯片，具有信号的处理能力。上述的处理器可以是通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本发明实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
本发明实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本发明所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所 显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明实施例的具体实施方式，但本发明实施例的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明实施例揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明实施例的保护范围之内。因此，本发明实施例的保护范围应所述以权利要求的保护范围为准。

Claims (32)

  1. 一种路径规划方法，其特征在于，包括：
    根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价；
    获取起始位置和目标位置；
    根据通过所述每个第一区域的所述通行代价进行路径规划，确定从所述起始位置到达所述目标位置的通行路径，所述通行路径包括从所述起始位置到达所述目标位置经过的区域。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    根据通过所述每个第一区域的通行代价，生成环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述每个第一区域的表征值；
    所述根据通过所述每个第一区域的所述通行代价进行路径规划，确定从所述起始位置到达所述目标位置的通行路径，包括：
    基于所述环境地图，根据通过所述每个第一区域的通行代价，确定所述通行路径。
  3. 根据权利要求1或2所述的方法，其特征在于，所述根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价，包括：
    根据所述每个第一区域的通行距离，确定所述每个第一区域的所述通行距离对应的第一通行代价分量；
    根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量；
    根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价。
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    获取通过所述通行路径时待执行的至少一种任务类型；
    所述根据所述每个第一区域的环境特征的表征值，获取所述每个第一区域的所述通行距离对应的第二通行代价分量，包括：
    根据所述至少一种任务类型中每种任务类型可用的至少一种环境特征在所述每个第一区域处的表征值，获取所述每种任务类型在所述每个第一位置处对应的第二通行代价分量；
    所述根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价，包括：
    根据所述每个第一区域的所述第一通行代价分量，和所述每种任务类型在所述每个第一区域对应的第二通行代价分量，计算执行所述每种任务类型时通过所述每个第一区域的通行代价；
    所述根据通过所述每个第一区域的所述通行代价进行路径规划，包括：
    根据执行所述每种任务类型时通过所述每个第一区域的通行代价，确定用于执行所 述每种任务类型的所述通行路径。
  5. 根据权利要求4所述的方法，其特征在于，所述至少一种任务类型包括第一任务类型，所述获取所述每种任务类型在所述每个第一区域处对应的所述第二通行代价分量，包括：
    根据在所述每个第一区域处，所述第一任务类型可用的环境特征中表征值满足预定条件的至少一种环境特征的表征值，确定所述第一任务类型在所述每个第一区域处对应的第二通行代价分量。
  6. 根据权利要求5所述的方法，其特征在于，所述第一区域为满足以下条件的区域：在所述第一区域处，所述第一任务类型可用的环境特征的特征值满足所述第一任务类型对环境特征的要求。
  7. 根据权利要求6所述的方法，其特征在于，所述方法还包括：
    确定至少一个第二区域，其中，在所述第二区域处，所述第一任务类型可用的环境特征的表征值不满足所述第一任务类型对环境特征的要求；
    在进行路径规划时，将所述至少一个第二区域中每个第二区域视为障碍物。
  8. 根据权利要求3所述的方法，所述方法还包括：
    获取通过所述通行路径时待执行的多种任务类型；
    所述根据所述每个第一区域的环境特征的表征值，获取所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量，包括：
    根据所述多种任务类型中每种任务类型可用的至少一种环境特征的表征值，获取所述多种任务类型作为整体在所述每个第一区域处对应的第二通行代价分量；
    所述根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价，包括：
    根据所述每个第一区域的所述第一通行代价分量，和所述多种任务类型作为整体在每个第一区域处对应的第二通行代价分量，计算所述多种任务类型作为整体在所述每个第一区域处对应的通行代价；
    所述根据通过所述每个第一区域的所述通行代价进行路径规划，包括：
    根据所述多种任务类型作为整体在所述每个第一区域处对应的通行代价，确定用于执行所述多种任务类型的所述通行路径。
  9. 根据权利要求8所述的方法，其特征在于，所述获取所述多种任务类型作为整体在所述每个第一区域处对应的第二通行代价分量，包括：
    根据所述每个第一区域处，所述多种任务类型中每种任务类型可用的至少一种环境特征的表征值，得到所述每种任务类型在所述每个第一区域处对应的第二通行代价分量；
    对所述多种任务类型在所述每个第一区域处对应的多个第二通行代价分量进行加权处理，以得到所述多种任务类型作为整体在所述第一区域处对应的所述第二通行代价分量。
  10. 根据权利要求9所述的方法，其特征在于，所述第一区域为满足以下条件的区域：在所述第一区域处，所述多种任务类型中每种任务类型可用的环境特征的表征值满足所述每种任务类型对环境特征的要求。
  11. 根据权利要求10所述的方法，其特征在于，所述方法还包括：
    确定至少一个第三区域，其中，在所述第三区域处，所述多种任务类型中的至少一种任务类型对应的环境特征的表征值不满足所述至少一种任务类型对特征值的要求；
    在进行路径规划时，将所述至少一个第三区域中每个第三区域视为障碍物。
  12. 根据权利要求3至11中任一项所述的方法，其特征在于，所述根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量，包括：
    根据环境特征的表征值区间与通行代价分量的对应关系，以及所述每个区域的环境特征的表征值，确定所述获取所述每个第一区域的所述第二通行代价分量。
  13. 根据权利要求3至12中任一项所述的方法，其特征在于，所述环境特征包括视觉信号；
    所述根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量，包括：
    根据通过所述每个第一位置的所述多个方向中每个方向上的视觉信号的表征值，获取所述每个第一位置的每个方向对应的第二通行代价分量；
    所述根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价，包括：
    根据所述每个第一区域的所述第一通行代价分量，和所述每个第一区域的每个方向对应的第二通行代价分量，确定通过所述每个第一区域的所述每个方向上的通行代价。
  14. 根据权利要求1至13中任一项所述的方法，其特征在于，所述根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价，包括：
    根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价；或，
    根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的环境特征的表征值，实时获取通过所述每个第一区域的通行代价；或，
    根据所述每个第一区域的通行距离，以及预测的所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域处的通行代价。
  15. 根据权利要求14所述的方法，其特征在于，所述根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价，包括：
    在所述每个第一区域的环境特征的表征值的变化率小于等于第一阈值的情况下，根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价。
  16. 根据权利要求14所述的方法，其特征在于，所述根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的环境特征的表征值，实时获取通过所述每个第一区域的通行代价，包括：
    在所述每个第一区域的环境特征的表征值的变化率大于第二阈值的情况下，根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的所述环境特征的表征值，实时获取通过所述每个第一区域的通行代价。
  17. 一种路径规划装置，其特征在于，包括：
    第一获取单元，用于根据多个第一区域中每个第一区域的通行距离，以及所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域的通行代价；
    第二获取单元，用于获取起始位置和目标位置；
    路径规划单元，用于根据通过所述每个第一区域的所述通行代价进行路径规划，确定从所述起始位置到达所述目标位置的通行路径，所述通行路径包括从所述起始位置到达所述目标位置经过的区域。
  18. 根据权利要求17所述的装置，其特征在于，所述装置还包括地图生成单元，用于：
    根据通过所述每个第一区域的通行代价，生成环境地图，所述环境地图包括通过所述每个第一区域的通行代价，用于标示所述每个第一区域的表征值；
    所述路径规划单元进一步用于：
    基于所述环境地图，根据通过所述每个第一区域的通行代价确定所述通行路径。
  19. 根据权利要求17或18所述的装置，其特征在于，所述第一获取单元进一步用于：
    根据所述每个第一区域的通行距离，确定所述每个第一区域的所述通行距离对应的第一通行代价分量；
    根据所述每个第一区域的环境特征的表征值，确定所述每个第一区域的所述环境特征的表征值对应的第二通行代价分量；
    根据所述每个第一区域的所述第一通行代价分量和所述第二通行代价分量，计算通过所述每个第一区域的通行代价。
  20. 根据权利要求19所述的装置，其特征在于，所述第一获取单元进一步用于：
    获取通过所述通行路径时待执行的至少一种任务类型；
    根据所述至少一种任务类型中每种任务类型可用的至少一种环境特征在所述每个第一区域处的表征值，获取所述每种任务类型在所述每个第一位置处对应的第二通行代价分量；
    根据所述每个第一区域的所述第一通行代价分量，和所述每种任务类型在所述每个第一区域对应的第二通行代价分量，计算执行所述每种任务类型时通过所述每个第一区域的通行代价；
    所述路径规划单元进一步用于：
    根据执行所述每种任务类型时通过所述每个第一区域的通行代价，确定用于执行所述每种任务类型的所述通行路径。
  21. 根据权利要求20所述的装置，其特征在于，所述至少一种任务类型包括第一任务类型，所述第一获取单元进一步用于：
    根据在所述每个第一区域处，所述第一任务类型可用的环境特征中表征值满足预定条件的至少一种环境特征的表征值，确定所述第一任务类型在所述每个第一区域处对应的第二通行代价分量。
  22. 根据权利要求21所述的装置，其特征在于，所述第一区域为满足以下条件的区域：在所述第一区域处，所述第一任务类型可用的环境特征的特征值满足所述第一任务类 型对环境特征的要求。
  23. 根据权利要求22所述的装置，其特征在于，所述第一获取单元进一步用于：
    确定至少一个第二区域，其中，在所述第二区域处，所述第一任务类型可用的环境特征的表征值不满足所述第一任务类型对环境特征的要求；
    所述路径规划单元进一步用于：
    在进行路径规划时，将所述至少一个第二区域中每个第二区域视为障碍物。
  24. 根据权利要求19所述的装置，所述第一获取单元进一步用于：
    获取通过所述通行路径时待执行的多种任务类型；
    根据所述多种任务类型中每种任务类型可用的至少一种环境特征的表征值，获取所述多种任务类型作为整体在所述每个第一区域处对应的第二通行代价分量；
    根据所述每个第一区域的所述第一通行代价分量，和所述多种任务类型作为整体在每个第一区域处对应的第二通行代价分量，计算所述多种任务类型作为整体在所述每个第一区域处对应的通行代价；
    所述路径规划单元进一步用于：
    根据所述多种任务类型作为整体在所述每个第一区域处对应的通行代价，确定用于执行所述多种任务类型的所述通行路径。
  25. 根据权利要求24所述的装置，其特征在于，所述第一获取单元进一步用于：
    根据所述每个第一区域处，所述多种任务类型中每种任务类型可用的至少一种环境特征的表征值，得到所述每种任务类型在所述每个第一区域处对应的第二通行代价分量；
    对所述多种任务类型在所述每个第一区域处对应的多个第二通行代价分量进行加权处理，以得到所述多种任务类型作为整体在所述第一区域处对应的所述第二通行代价分量。
  26. 根据权利要求25所述的装置，其特征在于，所述第一区域为满足以下条件的区域：在所述第一区域处，所述多种任务类型中每种任务类型可用的环境特征的表征值满足所述每种任务类型对环境特征的要求。
  27. 根据权利要求26所述的装置，其特征在于，所述第一获取单元进一步用于：
    确定至少一个第三区域，其中，在所述第三区域处，所述多种任务类型中的至少一种任务类型对应的环境特征的表征值不满足所述至少一种任务类型对特征值的要求；
    所述路径规划单元进一步用于：
    在进行路径规划时，将所述至少一个第三区域中每个第三区域视为障碍物。
  28. 根据权利要求19至27中任一项所述的装置，其特征在于，所述第一获取单元进一步用于：
    根据环境特征的表征值区间与通行代价分量的对应关系，以及所述每个区域的环境特征的表征值，确定所述获取所述每个第一区域的所述第二通行代价分量。
  29. 根据权利要求19至28中任一项所述的装置，其特征在于，所述环境特征包括视觉信号；
    所述第一获取单元进一步用于：
    根据通过所述每个第一位置的所述多个方向中每个方向上的视觉信号的表征值，获取所述每个第一位置的每个方向对应的第二通行代价分量；
    根据所述每个第一区域的所述第一通行代价分量，和所述每个第一区域的每个方向对应的第二通行代价分量，确定通过所述每个第一区域的所述每个方向上的通行代价。
  30. 根据权利要求17至29中任一项所述的装置，其特征在于，所述第一获取单元进一步用于：
    根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价；或，
    根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的环境特征的表征值，实时获取通过所述每个第一区域的通行代价；或，
    根据所述每个第一区域的通行距离，以及预测的所述每个第一区域的环境特征的表征值，获取通过所述每个第一区域处的通行代价。
  31. 根据权利要求30所述的装置，其特征在于，所述第一获取单元进一步用于：
    在所述每个第一区域的环境特征的表征值的变化率小于等于第一阈值的情况下，根据所述每个第一区域的通行距离，以及多次获取的所述每个第一区域的环境特征的表征值，以统计的方式获取通过所述每个第一区域的通行代价。
  32. 根据权利要求30所述的装置，其特征在于，所述第一获取单元进一步用于：
    在所述每个第一区域的环境特征的表征值的变化率大于第二阈值的情况下，根据所述每个第一区域的通行距离，以及实时获取的所述每个第一区域的所述环境特征的表征值，实时获取通过所述每个第一区域的通行代价。
PCT/CN2018/073114 2017-01-18 2018-01-18 路径规划方法和装置 WO2018133805A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP18741121.0A EP3564624A4 (en) 2017-01-18 2018-01-18 ROUTE PLANNING METHOD AND DEVICE
US16/515,502 US20190339703A1 (en) 2017-01-18 2019-07-18 Path Planning Method and Apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710034754.2 2017-01-18
CN201710034754.2A CN108318046B (zh) 2017-01-18 2017-01-18 路径规划方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/515,502 Continuation US20190339703A1 (en) 2017-01-18 2019-07-18 Path Planning Method and Apparatus

Publications (1)

Publication Number Publication Date
WO2018133805A1 true WO2018133805A1 (zh) 2018-07-26

Family

ID=62892174

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/073114 WO2018133805A1 (zh) 2017-01-18 2018-01-18 路径规划方法和装置

Country Status (4)

Country Link
US (1) US20190339703A1 (zh)
EP (1) EP3564624A4 (zh)
CN (1) CN108318046B (zh)
WO (1) WO2018133805A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112650252A (zh) * 2020-12-25 2021-04-13 珠海市一微半导体有限公司 用于搜索起始清扫位置的寻径代价获取方法及芯片
CN113324761A (zh) * 2020-02-28 2021-08-31 苏州宝时得电动工具有限公司 电动工具、车轮打滑确定系统及方法
US11256261B1 (en) * 2018-10-16 2022-02-22 Amazon Technologies, Inc. System for movement of autonomous mobile device

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11530921B2 (en) * 2018-09-28 2022-12-20 Intel Corporation Method of generating a collision free path of travel and computing system
KR102224637B1 (ko) 2019-07-05 2021-03-08 엘지전자 주식회사 이동 로봇 및 그 제어방법
KR102275300B1 (ko) 2019-07-05 2021-07-08 엘지전자 주식회사 이동 로봇 및 그 제어방법
KR102297496B1 (ko) 2019-07-11 2021-09-02 엘지전자 주식회사 인공지능을 이용한 이동 로봇 및 이동 로봇의 제어방법
KR102361130B1 (ko) 2019-07-11 2022-02-09 엘지전자 주식회사 이동 로봇 및 그 제어방법
KR102302575B1 (ko) * 2019-07-16 2021-09-14 엘지전자 주식회사 이동 로봇 및 그 제어방법
CN111103887B (zh) * 2020-01-14 2021-11-12 大连理工大学 一种基于多传感器的多移动机器人调度系统设计方法
CN111781925A (zh) * 2020-06-22 2020-10-16 北京海益同展信息科技有限公司 路径规划方法、装置、机器人及存储介质
CN111830973B (zh) * 2020-06-29 2021-07-20 北京大学 动态环境下的移动机器人路径规划方法及装置
CN112945255B (zh) * 2021-01-29 2022-06-21 中国人民解放军国防科技大学 汽车搭载多架无人机协同多区域覆盖路径规划方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103576686A (zh) * 2013-11-21 2014-02-12 中国科学技术大学 一种机器人自主导引及避障的方法
CN104165625A (zh) * 2013-05-17 2014-11-26 北京百度网讯科技有限公司 路径规划方法和设备
CN104615138A (zh) * 2015-01-14 2015-05-13 上海物景智能科技有限公司 一种划分移动机器人室内区域动态覆盖方法及其装置
CN104897168A (zh) * 2015-06-24 2015-09-09 清华大学 基于道路危险评估的智能车路径搜索方法及系统
US20160123751A1 (en) * 2011-11-08 2016-05-05 Saab Ab Route planning system and method for minimizing exposure to threats

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3994950B2 (ja) * 2003-09-19 2007-10-24 ソニー株式会社 環境認識装置及び方法、経路計画装置及び方法、並びにロボット装置
US8886453B2 (en) * 2008-12-11 2014-11-11 Telogis, Inc. System and method for efficient routing on a network in the presence of multiple-edge restrictions and other constraints
JP5810621B2 (ja) * 2011-05-16 2015-11-11 株式会社デンソー 道路勾配データ作成装置、記憶媒体、並びに、車両のエネルギー消費量予測装置
JP5724110B2 (ja) * 2011-07-07 2015-05-27 株式会社日立製作所 経路作成システム、経路作成方法及びプログラム
CN103558856A (zh) * 2013-11-21 2014-02-05 东南大学 动态环境下服务动机器人导航方法
US9216508B2 (en) * 2014-01-14 2015-12-22 Qualcomm Incorporated Connectivity maintenance using a quality of service-based robot path planning algorithm
CN104599588B (zh) * 2015-02-13 2017-06-23 中国北方车辆研究所 一种栅格地图通行成本的计算方法
CN105067004B (zh) * 2015-09-14 2017-10-20 武大吉奥信息技术有限公司 一种基于地形的路径搜索方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160123751A1 (en) * 2011-11-08 2016-05-05 Saab Ab Route planning system and method for minimizing exposure to threats
CN104165625A (zh) * 2013-05-17 2014-11-26 北京百度网讯科技有限公司 路径规划方法和设备
CN103576686A (zh) * 2013-11-21 2014-02-12 中国科学技术大学 一种机器人自主导引及避障的方法
CN104615138A (zh) * 2015-01-14 2015-05-13 上海物景智能科技有限公司 一种划分移动机器人室内区域动态覆盖方法及其装置
CN104897168A (zh) * 2015-06-24 2015-09-09 清华大学 基于道路危险评估的智能车路径搜索方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3564624A4

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11256261B1 (en) * 2018-10-16 2022-02-22 Amazon Technologies, Inc. System for movement of autonomous mobile device
CN113324761A (zh) * 2020-02-28 2021-08-31 苏州宝时得电动工具有限公司 电动工具、车轮打滑确定系统及方法
CN112650252A (zh) * 2020-12-25 2021-04-13 珠海市一微半导体有限公司 用于搜索起始清扫位置的寻径代价获取方法及芯片
CN112650252B (zh) * 2020-12-25 2024-05-07 珠海一微半导体股份有限公司 用于搜索起始清扫位置的寻径代价获取方法及芯片

Also Published As

Publication number Publication date
US20190339703A1 (en) 2019-11-07
EP3564624A4 (en) 2020-01-22
EP3564624A1 (en) 2019-11-06
CN108318046B (zh) 2020-12-15
CN108318046A (zh) 2018-07-24

Similar Documents

Publication Publication Date Title
WO2018133805A1 (zh) 路径规划方法和装置
WO2018133804A1 (zh) 路径规划方法和装置
CN109709945B (zh) 一种基于障碍物分类的路径规划方法、装置及机器人
Kümmerle et al. A navigation system for robots operating in crowded urban environments
WO2018121448A1 (zh) 移动机器人的拓扑地图创建方法、导航方法、可编程设备及计算机可读介质
Wurm et al. Bridging the gap between feature-and grid-based SLAM
CN112000754A (zh) 地图构建方法、装置、存储介质及计算机设备
CN111090282A (zh) 机器人的避障方法、机器人以及装置
JP7450814B2 (ja) 駐車スペースのハイブリッド探索を用いた自律駐車
CN111609852A (zh) 语义地图构建方法、扫地机器人及电子设备
CN103926925A (zh) 一种基于改进的vfh算法的定位与避障方法及机器人
Gomez et al. Hybrid topological and 3d dense mapping through autonomous exploration for large indoor environments
CN112394725B (zh) 用于自动驾驶的基于预测和反应视场的计划
JP2011054082A (ja) 自律移動装置
CN111694356A (zh) 一种行驶控制方法、装置、电子设备及存储介质
CN116703984B (zh) 机器人路径规划及红外光图像融合方法、系统及存储介质
O’Mahony et al. Adaptive multimodal localisation techniques for mobile robots in unstructured environments: A review
Berrio et al. Identifying robust landmarks in feature-based maps
Ruiz et al. A general algorithm for exploration with gaussian processes in complex, unknown environments
JP2020095339A (ja) 移動体、移動体の制御方法及びプログラム
Dong et al. Indoor tracking using crowdsourced maps
Liu et al. Action selection for active and cooperative global localization based on localizability estimation
AU2021273605B2 (en) Multi-agent map generation
WO2023103142A1 (zh) 障碍物轨迹预测的方法、系统和计算机可读存储介质
Chipka et al. Estimation and navigation methods with limited information for autonomous urban driving

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18741121

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018741121

Country of ref document: EP

Effective date: 20190801