A robot intelligent obstacle avoidance system and method based on environmental information

Abstract

The present invention relates to the field of robot obstacle avoidance technology, specifically a robot intelligent obstacle avoidance system and method based on environmental information, the system includes an obstacle avoidance planning collaborative analysis and screening module, the obstacle avoidance planning collaborative analysis and screening module generates various obstacle avoidance planning path plans based on obstacle feature information when the passing collision risk value is abnormal; combined with the obstacle avoidance environment feature information around the robot, the corresponding collaborative risk interference value when the state of the robot's external device is switched to the initial state at the current time is calculated, and the interference impact value of each obstacle avoidance path plan on the robot's passing state is obtained. The present invention not only takes into account the preset shape of the robot, but also takes into account the influence of the difference in the state of the corresponding external device carried by the robot on the shape of the robot and the change of the occupied space range, and continues to accurately screen the planned obstacle avoidance path based on the robot's shape difference when planning the obstacle avoidance path, so as to achieve effective control of the robot's intelligent obstacle avoidance.

Description

Technical Field

[0001] The present invention relates to the technical field of robot obstacle avoidance, and in particular to a robot intelligent obstacle avoidance system and method based on environmental information. Background Art

[0002] With the continuous advancement and popularization of robotics technology, robots have been widely used in various complex environments, such as homes, factories, hospitals, shopping malls, etc. In these environments, robots need to be able to autonomously navigate, identify and avoid obstacles to ensure their safe operation and efficient operation.

[0003] Traditional robot obstacle avoidance technology mainly relies on sensors (such as ultrasonic sensors, infrared sensors or lidar, etc.) to obtain obstacle information, and then plans the obstacle avoidance path based on the acquired information; usually, the size of the robot itself needs to be taken into account during the planning of the obstacle avoidance path to avoid the risk of collision when the robot moves along the planned obstacle avoidance path.

[0004] However, in the prior art, the robot volume considered in planning the obstacle avoidance path is often preset. In real life, when the robot realizes various functions, it is often equipped with corresponding external devices (such as mechanical grippers, etc.). The state of the external devices often causes the shape of the robot and the space occupied by it to change. Therefore, when planning the obstacle avoidance path, continuing to plan based on the preset robot volume in the prior art often leads to a high risk of collision and obstacle avoidance failure, and thus the prior art has major defects. Summary of the invention

[0005] The purpose of the present invention is to provide a robot intelligent obstacle avoidance system and method based on environmental information to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a robot intelligent obstacle avoidance method based on environmental information, the method comprising the following steps:

[0007] S1, constructing obstacle feature information set and obstacle avoidance environment feature information around the robot through the collected images acquired in real time by the robot's built-in sensors;

[0008] S2, based on the obstacle avoidance environment feature information around the robot, combined with the initial state information of the robot, the current passage path and the state information of the robot's external device at the current time, obtain the robot's passage collision risk value based on the obstacle feature information set;

[0009] S3. When the passing collision risk value is abnormal, each obstacle avoidance planning path plan is generated based on the obstacle feature information; combined with the obstacle avoidance environment feature information around the robot, the collaborative risk interference value corresponding to the state of the robot's external device switching to the initial state at the current time is calculated, and the interference impact value of each obstacle avoidance path plan on the robot's passing state is obtained, and the best obstacle avoidance planning path plan of the robot is screened to generate the best obstacle avoidance planning plan for the robot at the current time;

[0010] S4. Based on the best obstacle avoidance plan of the robot at the current time, the current path of the robot in the database is updated in real time; and obstacle avoidance log information is generated based on the update results and fed back to the administrator in real time.

[0011] Furthermore, the sensor includes a laser radar, a depth camera or an ultrasonic sensor.

[0012] Each element in the obstacle feature information set corresponds to an obstacle feature information, and the obstacle feature information includes the position, size and outline of the corresponding obstacle extracted based on the collected image;

[0013] The obstacle avoidance environment characteristic information includes the road surface smoothness of the road surface corresponding to different image areas in the corresponding collected image.

[0014] The present invention obtains obstacle feature information and obstacle avoidance environment feature information in order to determine the risk of collision when the robot moves along the current path in subsequent steps; it provides data support for subsequent planning of obstacle avoidance paths.

[0015] Further, the initial state information of the robot includes the orthographic projection of the external contour of the robot when it is initially running on a plane perpendicular to the forward direction and a first distance; the state information of the external device of the robot at the current time includes the orthographic projection of the external contour of the robot at the current time on a plane perpendicular to the forward direction and a second distance; the first distance represents the maximum value of the distance between the midpoint position of the robot axle in the corresponding orthographic projection in the initial state information of the robot and the two ends in the width direction of the corresponding orthographic projection; the second distance represents the maximum value of the distance between the midpoint position of the robot axle in the corresponding orthographic projection in the state information of the external device of the robot at the current time and the two ends in the width direction of the corresponding orthographic projection;

[0016] When the robot's passing collision risk value based on the obstacle feature information set is obtained in S2, the robot's passing collision risk value based on the obstacle feature information set is recorded as E.

[0017] E=max{L1+L3,L2+L3},

[0018] Among them, L1 represents the first distance in the initial state information of the robot; L2 represents the second distance in the state information of the robot's external device at the current time; L3 represents the overlapping width of the robot's current path and the obstacle contour in the obstacle feature information set; when the robot's current path does not overlap with the obstacle contour in the obstacle feature information set, L3 is equal to the inverse of the shortest distance between the robot's current path and the obstacle contour in the obstacle feature information set; max{} represents the operation of finding the maximum value.

[0019] Further, when judging whether the traffic collision risk value is abnormal, the traffic collision risk value with a corresponding value greater than 0 is judged to be abnormal, otherwise, the corresponding traffic collision risk value is judged to be normal;

[0020] When generating each obstacle avoidance planning path plan, the detour boundary feature node corresponding to each obstacle in the obstacle feature information is obtained, the outline of each obstacle in the obstacle feature information and its corresponding detour boundary feature node are marked in the current pass path, and the lines between the current position of the robot and each detour boundary node are respectively connected, and the area divided by the obtained lines that does not intersect with the outline of each obstacle is recorded as a safe obstacle avoidance planning area; the safe obstacle avoidance planning area includes one or more obstacle avoidance planning sub-areas; based on the Dijkstra algorithm, the obstacle avoidance planning path plan of each obstacle avoidance planning sub-area is obtained respectively; each obstacle avoidance planning sub-area corresponds to an obstacle avoidance planning path plan;

[0021] The dynamic acquisition of the safe obstacle avoidance planning area in the present invention realizes the determination of the number of obstacle avoidance planning path plans, and combines the existing Dijkstra algorithm technology to plan the information of each obstacle avoidance planning path plan respectively, so as to provide data reference for the subsequent analysis of the interference impact value of each obstacle avoidance path plan on the robot's passage state, and to construct the optimal obstacle avoidance planning plan for the robot at the current time.

[0022] The method for obtaining the interference impact value of each obstacle avoidance path scheme on the robot's passage state in S3 comprises the following steps:

[0023] S31, obtaining the obstacle avoidance environment feature information around the robot and the status information of the robot's external device at the current time;

[0024] S32, calculate the collaborative risk interference value corresponding to the state of the robot external device switching to the initial state at the current time, recorded as GX,

[0025]

[0026] Among them, N1 represents the total number of operation instructions executed in the process of switching the state of the robot's external device to the initial state at the current time in the database; N2 represents the total number of operation instructions executed in the process of switching the robot from the initial state to the state required by the robot's external device after obstacle avoidance in the database; N3 represents the total number of operation instructions executed in the process of switching the state of the robot's external device at the current time to the state required by the robot's external device after obstacle avoidance in the database; Represents the first risk interference value. If N1+N2=0, then it is determined Otherwise, it is judged

[0027] LQ represents the maximum value of the second spacing corresponding to different times during the process of the state of the robot external device switching to the initial state at the current time; L2 represents the second spacing in the state information of the robot external device at the current time; g represents the coordinated interference factor and g is a constant preset in the database;

[0028] S33, when the state switching execution coefficient w is different, the interference impact value of the kth obstacle avoidance planning path scheme on the robot's passage state is recorded as YGk w ,

[0029]

[0030] Among them, Pkm represents the road surface flatness of the road surface corresponding to the mth image area passed through in the kth obstacle avoidance planning path plan; Bkm represents the ratio of the length of the mth image area passed through in the kth obstacle avoidance planning path plan to the total length of the corresponding obstacle avoidance planning path; m1 represents the total number of image areas passed through in the kth obstacle avoidance planning path plan; Ek represents the passing collision risk value based on the obstacle feature information set when the robot executes the kth obstacle avoidance planning path plan; LGk represents the path length corresponding to the kth obstacle avoidance planning path plan; w represents the state switching execution coefficient, and the value of w is 0 or 1;

[0031] When w=1, it is determined that when the robot executes the kth obstacle avoidance planning path plan, it is necessary to switch the state of the robot's external device at the current time to the initial state; when w=0, it is determined that when the robot executes the kth obstacle avoidance planning path plan, it is not necessary to switch the state of the robot's external device at the current time to the initial state.

[0032] Furthermore, when generating the optimal obstacle avoidance planning scheme for the robot at the current time in S3, an array consisting of the obstacle avoidance planning path scheme with the smallest interference impact on the robot's passage state and its corresponding state switching execution coefficient is selected as the optimal obstacle avoidance planning scheme for the robot at the current time.

[0033] Furthermore, when the obstacle avoidance log information is generated according to the update result in S4 and fed back to the administrator in real time, the obstacle avoidance log information includes the time when the obstacle avoidance log is generated, the corresponding optimal obstacle avoidance planning scheme, the obstacle feature information set obtained before obtaining the corresponding optimal obstacle avoidance planning scheme, the obstacle avoidance environment feature information, the current travel path and the status information of the robot's external device at the current time.

[0034] A robot intelligent obstacle avoidance system based on environmental information, the system comprising:

[0035] An obstacle feature extraction module, which constructs an obstacle feature information set and obstacle avoidance environment feature information around the robot through the collected images acquired in real time by the built-in sensors of the robot;

[0036] A collision risk analysis module, which obtains a collision risk value of the robot based on an obstacle feature information set based on the obstacle avoidance environment feature information around the robot, combined with the robot's initial state information, the current travel path, and the state information of the robot's external device at the current time;

[0037] The obstacle avoidance planning collaborative analysis and screening module generates various obstacle avoidance planning path plans based on obstacle feature information when the passing collision risk value is abnormal; combines the obstacle avoidance environment feature information around the robot, calculates the collaborative risk interference value corresponding to the state of the robot's external device switching to the initial state at the current time, obtains the interference impact value of each obstacle avoidance path plan on the robot's passing state, screens the robot's optimal obstacle avoidance planning path plan, and generates the optimal obstacle avoidance planning plan for the robot at the current time;

[0038] The obstacle avoidance scheme update feedback module updates the robot's current path in the database in real time according to the robot's optimal obstacle avoidance planning scheme at the current time, and generates obstacle avoidance log information based on the update results and feeds it back to the administrator in real time.

[0039] Furthermore, the obstacle avoidance planning collaborative analysis and screening module includes an obstacle avoidance planning scheme generating unit, a traffic interference analysis unit and an optimal obstacle avoidance scheme generating unit.

[0040] The obstacle avoidance planning scheme generating unit generates various obstacle avoidance planning path schemes based on obstacle feature information when the traffic collision risk value is abnormal;

[0041] The passage interference analysis unit combines the obstacle avoidance environment feature information around the robot to calculate the corresponding collaborative risk interference value when the state of the robot's external device is switched to the initial state at the current time, and obtains the interference impact value of each obstacle avoidance path scheme on the robot's passage state;

[0042] The optimal obstacle avoidance plan generating unit selects the optimal obstacle avoidance planning path plan of the robot and generates the optimal obstacle avoidance planning plan of the robot at the current time.

[0043] Compared with the prior art, the beneficial effect achieved by the present invention is that: when planning the obstacle avoidance path, the present invention not only takes into account the preset shape of the robot, but also takes into account the impact of the difference in the state of the corresponding external devices carried by the robot on the change in the shape of the robot and the occupied space range, and continues to accurately screen the planned obstacle avoidance path based on the shape difference of the robot when planning the obstacle avoidance path, thereby reducing the collision risk and obstacle avoidance failure when the robot moves along the planned obstacle avoidance path, and realizing effective control of the robot's intelligent obstacle avoidance system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 It is a flow chart of a robot intelligent obstacle avoidance system based on environmental information of the present invention;

[0046] Figure 2 It is a structural schematic diagram of a robot intelligent obstacle avoidance method based on environmental information of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 The present invention provides a technical solution: a robot intelligent obstacle avoidance system based on environmental information, the system comprising:

[0049] An obstacle feature extraction module, which constructs an obstacle feature information set and obstacle avoidance environment feature information around the robot through the collected images acquired in real time by the built-in sensors of the robot;

[0050] A collision risk analysis module, which obtains a collision risk value of the robot based on an obstacle feature information set based on the obstacle avoidance environment feature information around the robot, combined with the robot's initial state information, the current travel path, and the state information of the robot's external device at the current time;

[0051] The obstacle avoidance planning collaborative analysis and screening module generates various obstacle avoidance planning path plans based on obstacle feature information when the passing collision risk value is abnormal; combines the obstacle avoidance environment feature information around the robot, calculates the collaborative risk interference value corresponding to the state of the robot's external device switching to the initial state at the current time, obtains the interference impact value of each obstacle avoidance path plan on the robot's passing state, screens the robot's optimal obstacle avoidance planning path plan, and generates the optimal obstacle avoidance planning plan for the robot at the current time;

[0052] The obstacle avoidance scheme update feedback module updates the robot's current path in the database in real time according to the robot's optimal obstacle avoidance planning scheme at the current time, and generates obstacle avoidance log information based on the update results and feeds it back to the administrator in real time.

[0053] The obstacle avoidance planning collaborative analysis and screening module includes an obstacle avoidance planning scheme generation unit, a traffic interference analysis unit and an optimal obstacle avoidance scheme generation unit.

[0054] The obstacle avoidance planning scheme generating unit generates various obstacle avoidance planning path schemes based on obstacle feature information when the traffic collision risk value is abnormal;

[0055] The passage interference analysis unit combines the obstacle avoidance environment feature information around the robot to calculate the corresponding collaborative risk interference value when the state of the robot's external device is switched to the initial state at the current time, and obtains the interference impact value of each obstacle avoidance path scheme on the robot's passage state;

[0056] The optimal obstacle avoidance plan generating unit selects the optimal obstacle avoidance planning path plan of the robot and generates the optimal obstacle avoidance planning plan of the robot at the current time.

[0057] like Figure 2 As shown, a robot intelligent obstacle avoidance method based on environmental information comprises the following steps:

[0058] S1, constructing obstacle feature information set and obstacle avoidance environment feature information around the robot through the collected images acquired in real time by the robot's built-in sensors;

[0059] The sensor includes a lidar, a depth camera or an ultrasonic sensor,

[0060] Each element in the obstacle feature information set corresponds to an obstacle feature information, and the obstacle feature information includes the position, size and outline of the corresponding obstacle extracted based on the collected image;

[0061] The obstacle avoidance environment characteristic information includes the road surface smoothness of the road surface corresponding to different image areas in the corresponding collected image.

[0062] S2, based on the obstacle avoidance environment feature information around the robot, combined with the initial state information of the robot, the current passage path and the state information of the robot's external device at the current time, obtain the robot's passage collision risk value based on the obstacle feature information set;

[0063] The initial state information of the robot includes the orthographic projection of the external contour of the robot when it is initially running on a plane perpendicular to the forward direction and a first spacing; the state information of the external device of the robot at the current time includes the orthographic projection of the external contour of the robot at the current time on a plane perpendicular to the forward direction and a second spacing; the first spacing represents the maximum value of the distance between the midpoint position of the robot axle in the corresponding orthographic projection in the initial state information of the robot and the two ends in the width direction of the corresponding orthographic projection; the second spacing represents the maximum value of the distance between the midpoint position of the robot axle in the corresponding orthographic projection in the state information of the external device of the robot at the current time and the two ends in the width direction of the corresponding orthographic projection;

[0064] When the robot's passing collision risk value based on the obstacle feature information set is obtained in S2, the robot's passing collision risk value based on the obstacle feature information set is recorded as E.

[0065] E=max{L1+L3,L2+L3},

[0066] Among them, L1 represents the first distance in the initial state information of the robot; L2 represents the second distance in the state information of the robot's external device at the current time; L3 represents the overlapping width of the robot's current path and the obstacle contour in the obstacle feature information set; when the robot's current path does not overlap with the obstacle contour in the obstacle feature information set, L3 is equal to the inverse of the shortest distance between the robot's current path and the obstacle contour in the obstacle feature information set; max{} represents the operation of finding the maximum value.

[0067] S3. When the passing collision risk value is abnormal, each obstacle avoidance planning path plan is generated based on the obstacle feature information; combined with the obstacle avoidance environment feature information around the robot, the collaborative risk interference value corresponding to the state of the robot's external device switching to the initial state at the current time is calculated, and the interference impact value of each obstacle avoidance path plan on the robot's passing state is obtained, and the best obstacle avoidance planning path plan of the robot is screened to generate the best obstacle avoidance planning plan for the robot at the current time;

[0068] When judging whether the traffic collision risk value is abnormal, a traffic collision risk value whose corresponding value is greater than 0 is judged to be abnormal, otherwise, the corresponding traffic collision risk value is judged to be normal;

[0069] When generating each obstacle avoidance planning path plan, the detour boundary feature node corresponding to each obstacle in the obstacle feature information is obtained, the outline of each obstacle in the obstacle feature information and its corresponding detour boundary feature node are marked in the current pass path, and the lines between the current position of the robot and each detour boundary node are respectively connected, and the area divided by the obtained lines that does not intersect with the outline of each obstacle is recorded as a safe obstacle avoidance planning area; the safe obstacle avoidance planning area includes one or more obstacle avoidance planning sub-areas; based on the Dijkstra algorithm, the obstacle avoidance planning path plan of each obstacle avoidance planning sub-area is obtained respectively; each obstacle avoidance planning sub-area corresponds to an obstacle avoidance planning path plan;

[0070] The method for obtaining the interference impact value of each obstacle avoidance path scheme on the robot's passage state in S3 comprises the following steps:

[0071] S31, obtaining the obstacle avoidance environment feature information around the robot and the status information of the robot's external device at the current time;

[0072] S32, calculate the collaborative risk interference value corresponding to the state of the robot external device switching to the initial state at the current time, recorded as GX,

[0073]

[0074] Among them, N1 represents the total number of operation instructions executed in the process of switching the state of the robot's external device to the initial state at the current time in the database; N2 represents the total number of operation instructions executed in the process of switching the robot from the initial state to the state required by the robot's external device after obstacle avoidance in the database; N3 represents the total number of operation instructions executed in the process of switching the state of the robot's external device at the current time to the state required by the robot's external device after obstacle avoidance in the database; Represents the first risk interference value. If N1+N2=0, then it is determined Otherwise, it is judged

[0075] LQ represents the maximum value of the second spacing corresponding to different times during the process of the state of the robot external device switching to the initial state at the current time; L2 represents the second spacing in the state information of the robot external device at the current time; g represents the coordinated interference factor and g is a constant preset in the database;

[0076] S33, when the state switching execution coefficient w is different, the interference impact value of the kth obstacle avoidance planning path scheme on the robot's passage state is recorded as YGk w ,

[0077]

[0078] Among them, Pkm represents the road surface flatness of the road surface corresponding to the mth image area passed through in the kth obstacle avoidance planning path plan; Bkm represents the ratio of the length of the mth image area passed through in the kth obstacle avoidance planning path plan to the total length of the corresponding obstacle avoidance planning path; m1 represents the total number of image areas passed through in the kth obstacle avoidance planning path plan; Ek represents the passing collision risk value based on the obstacle feature information set when the robot executes the kth obstacle avoidance planning path plan; LGk represents the path length corresponding to the kth obstacle avoidance planning path plan; w represents the state switching execution coefficient, and the value of w is 0 or 1;

[0079] When w=1, it is determined that when the robot executes the kth obstacle avoidance planning path plan, it is necessary to switch the state of the robot's external device at the current time to the initial state; when w=0, it is determined that when the robot executes the kth obstacle avoidance planning path plan, it is not necessary to switch the state of the robot's external device at the current time to the initial state.

[0080] When generating the optimal obstacle avoidance planning scheme for the robot at the current time in S3, an array consisting of the obstacle avoidance planning path scheme with the smallest interference impact value on the robot's passage state and its corresponding state switching execution coefficient is selected as the optimal obstacle avoidance planning scheme for the robot at the current time.

[0081] S4. Based on the best obstacle avoidance plan of the robot at the current time, the current path of the robot in the database is updated in real time; and obstacle avoidance log information is generated based on the update results and fed back to the administrator in real time.

[0082] When the obstacle avoidance log information is generated according to the update result in S4 and fed back to the administrator in real time, the obstacle avoidance log information includes the time when the obstacle avoidance log is generated, the corresponding optimal obstacle avoidance planning scheme, the obstacle feature information set obtained before obtaining the corresponding optimal obstacle avoidance planning scheme, the obstacle avoidance environment feature information, the current travel path and the status information of the robot's external device at the current time.

[0083] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0084] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A robot intelligent obstacle avoidance method based on environmental information, characterized in that: The method comprises the following steps: S1, constructing obstacle feature information set and obstacle avoidance environment feature information around the robot through the collected images acquired in real time by the robot's built-in sensors; S2, based on the obstacle avoidance environment feature information around the robot, combined with the initial state information of the robot, the current passage path and the state information of the robot's external device at the current time, obtain the robot's passage collision risk value based on the obstacle feature information set; S3. When the passing collision risk value is abnormal, each obstacle avoidance planning path plan is generated based on the obstacle feature information; combined with the obstacle avoidance environment feature information around the robot, the collaborative risk interference value corresponding to the state of the robot's external device switching to the initial state at the current time is calculated, and the interference impact value of each obstacle avoidance path plan on the robot's passing state is obtained, and the best obstacle avoidance planning path plan of the robot is screened to generate the best obstacle avoidance planning plan for the robot at the current time; S4. Update the robot's current path in the database in real time based on the robot's optimal obstacle avoidance plan at the current time; and generate obstacle avoidance log information based on the update results and feed it back to the administrator in real time; The sensor includes a lidar, a depth camera or an ultrasonic sensor, Each element in the obstacle feature information set corresponds to an obstacle feature information, and the obstacle feature information includes the position, size and outline of the corresponding obstacle extracted based on the collected image; The obstacle avoidance environment characteristic information includes the road surface smoothness of the road surface corresponding to different image areas in the corresponding collected image; When judging whether the traffic collision risk value is abnormal, a traffic collision risk value whose corresponding value is greater than 0 is judged to be abnormal, otherwise, the corresponding traffic collision risk value is judged to be normal; When generating each obstacle avoidance planning path plan, the detour boundary feature node corresponding to each obstacle in the obstacle feature information is obtained, the outline of each obstacle in the obstacle feature information and its corresponding detour boundary feature node are marked in the current pass path, and the lines between the current position of the robot and each detour boundary node are respectively connected, and the area divided by the obtained lines that does not intersect with the outline of each obstacle is recorded as a safe obstacle avoidance planning area; the safe obstacle avoidance planning area includes one or more obstacle avoidance planning sub-areas; based on the Dijkstra algorithm, the obstacle avoidance planning path plan of each obstacle avoidance planning sub-area is obtained respectively; each obstacle avoidance planning sub-area corresponds to an obstacle avoidance planning path plan; The method for obtaining the interference impact value of each obstacle avoidance path scheme on the robot's passage state in S3 comprises the following steps: S31, obtaining the obstacle avoidance environment feature information around the robot and the status information of the robot's external device at the current time; S32, calculate the collaborative risk interference value corresponding to the state of the robot external device switching to the initial state at the current time, recorded as GX, Among them, N1 represents the total number of operation instructions executed in the process of switching the state of the robot's external device to the initial state at the current time in the database; N2 represents the total number of operation instructions executed in the process of switching the robot from the initial state to the state required by the robot's external device after obstacle avoidance in the database; N3 represents the total number of operation instructions executed in the process of switching the state of the robot's external device at the current time to the state required by the robot's external device after obstacle avoidance in the database; Represents the first risk interference value. If N1+N2=0, then it is determined Otherwise, it is judged LQ represents the maximum value of the second spacing corresponding to different times during the process of the state of the robot external device switching to the initial state at the current time; L2 represents the second spacing in the state information of the robot external device at the current time; g represents the coordinated interference factor and g is a constant preset in the database; S33, when the state switching execution coefficient w is different, the interference impact value of the kth obstacle avoidance planning path scheme on the robot's passage state is recorded as YGk w , Among them, Pkm represents the road surface flatness of the road surface corresponding to the mth image area passed through in the kth obstacle avoidance planning path plan; Bkm represents the ratio of the length of the mth image area passed through in the kth obstacle avoidance planning path plan to the total length of the corresponding obstacle avoidance planning path; m1 represents the total number of image areas passed through in the kth obstacle avoidance planning path plan; Ek represents the passing collision risk value based on the obstacle feature information set when the robot executes the kth obstacle avoidance planning path plan; LGk represents the path length corresponding to the kth obstacle avoidance planning path plan; w represents the state switching execution coefficient, and the value of w is 0 or 1; When w=1, it is determined that when the robot executes the kth obstacle avoidance planning path plan, it is necessary to switch the state of the robot's external device at the current time to the initial state; when w=0, it is determined that when the robot executes the kth obstacle avoidance planning path plan, it is not necessary to switch the state of the robot's external device at the current time to the initial state.

2. The robot intelligent obstacle avoidance method based on environmental information according to claim 1, characterized in that: The initial state information of the robot includes the orthographic projection of the external contour of the robot when it is initially running on a plane perpendicular to the forward direction and a first spacing; the state information of the external device of the robot at the current time includes the orthographic projection of the external contour of the robot at the current time on a plane perpendicular to the forward direction and a second spacing; the first spacing represents the maximum value of the distance between the midpoint position of the robot axle in the corresponding orthographic projection in the initial state information of the robot and the two ends in the width direction of the corresponding orthographic projection; the second spacing represents the maximum value of the distance between the midpoint position of the robot axle in the corresponding orthographic projection in the state information of the external device of the robot at the current time and the two ends in the width direction of the corresponding orthographic projection; When the robot's passing collision risk value based on the obstacle feature information set is obtained in S2, the robot's passing collision risk value based on the obstacle feature information set is recorded as E. E=max{L1+L3,L2+L3}, Among them, L1 represents the first distance in the initial state information of the robot; L2 represents the second distance in the state information of the robot's external device at the current time; L3 represents the overlapping width of the robot's current path and the obstacle contour in the obstacle feature information set; when the robot's current path does not overlap with the obstacle contour in the obstacle feature information set, L3 is equal to the inverse of the shortest distance between the robot's current path and the obstacle contour in the obstacle feature information set; max{} represents the operation of finding the maximum value.

3. The robot intelligent obstacle avoidance method based on environmental information according to claim 1, characterized in that: When generating the optimal obstacle avoidance planning scheme for the robot at the current time in S3, an array consisting of the obstacle avoidance planning path scheme with the smallest interference impact value on the robot's passage state and its corresponding state switching execution coefficient is selected as the optimal obstacle avoidance planning scheme for the robot at the current time.

4. The robot intelligent obstacle avoidance method based on environmental information according to claim 1, characterized in that: When the obstacle avoidance log information is generated according to the update result in S4 and fed back to the administrator in real time, the obstacle avoidance log information includes the time when the obstacle avoidance log is generated, the corresponding optimal obstacle avoidance planning scheme, the obstacle feature information set obtained before obtaining the corresponding optimal obstacle avoidance planning scheme, the obstacle avoidance environment feature information, the current travel path and the status information of the robot's external device at the current time.

5. A robot intelligent obstacle avoidance system based on environmental information, using a robot intelligent obstacle avoidance method based on environmental information as described in any one of claims 1 to 4, characterized in that: The system comprises: An obstacle feature extraction module, which constructs an obstacle feature information set and obstacle avoidance environment feature information around the robot through the collected images acquired in real time by the built-in sensors of the robot; A collision risk analysis module, which obtains a collision risk value of the robot based on an obstacle feature information set based on the obstacle avoidance environment feature information around the robot, combined with the robot's initial state information, the current travel path, and the state information of the robot's external device at the current time; The obstacle avoidance planning collaborative analysis and screening module generates various obstacle avoidance planning path plans based on obstacle feature information when the passing collision risk value is abnormal; combines the obstacle avoidance environment feature information around the robot, calculates the collaborative risk interference value corresponding to the state of the robot's external device switching to the initial state at the current time, obtains the interference impact value of each obstacle avoidance path plan on the robot's passing state, screens the robot's optimal obstacle avoidance planning path plan, and generates the optimal obstacle avoidance planning plan for the robot at the current time; The obstacle avoidance scheme update feedback module updates the robot's current path in the database in real time according to the robot's optimal obstacle avoidance planning scheme at the current time, and generates obstacle avoidance log information based on the update results and feeds it back to the administrator in real time.

6. The robot intelligent obstacle avoidance system based on environmental information according to claim 5, characterized in that: The obstacle avoidance planning collaborative analysis and screening module includes an obstacle avoidance planning scheme generation unit, a traffic interference analysis unit and an optimal obstacle avoidance scheme generation unit. The obstacle avoidance planning scheme generating unit generates various obstacle avoidance planning path schemes based on obstacle feature information when the traffic collision risk value is abnormal; The passage interference analysis unit combines the obstacle avoidance environment feature information around the robot to calculate the corresponding collaborative risk interference value when the state of the robot's external device is switched to the initial state at the current time, and obtains the interference impact value of each obstacle avoidance path scheme on the robot's passage state; The optimal obstacle avoidance plan generating unit selects the optimal obstacle avoidance planning path plan of the robot and generates the optimal obstacle avoidance planning plan of the robot at the current time.

Images