Path planning method

Abstract

The present invention discloses a path planning method, including the following steps: establishing an empirical map and a corresponding episodic cognitive map using a RatSLAM algorithm based on an episodic memory model; extracting a road edge in a historical memory image with a Canny operator; performing conversion to a world coordinate system from a pixel coordinate system based on the road edge, and preliminarily judging connectivity according to slope of the road edge; continuously injecting energy into the potential path detection network according to continuous observation of a potential path, so as to further judge the road connectivity; fusing the detected potential path and the original episodic cognitive map, and correspondingly updating the empirical map; and planning a path based on the updated episodic cognitive map. The potential safe path in an environment may be detected, and a better path may be planned based on the updated episodic memory model.

Claims

1. A path planning method for improving a navigation efficiency of a mobile robot, comprising the following steps: providing the mobile robot; establishing an empirical map and a corresponding episodic cognitive map using a RatSLAM algorithm based on an episodic memory model; extracting a road edge in a historical memory image with a Canny operator; performing conversion to a world coordinate system from a pixel coordinate system based on the road edge, and preliminarily judging connectivity according to slope of the road edge; continuously injecting electric energy into a potential path detection network according to continuous observation of a potential path, so as to further judge the road connectivity; fusing the detected potential path and the original episodic cognitive map, and correspondingly updating the empirical map; planning a path based on the updated episodic cognitive map; and fusing the path based on the updated episodic cognitive map to the mobile robot to improve the navigation efficiency of the mobile robot, wherein the episodic memory model is a path planning algorithm; the episodic cognitive map is a two-dimensional incremental matrix and composed of a discrete limited event space and an event transition set; the preliminarily judging connectivity according to slope of the road edge comprises: when an absolute value of a difference between the slope of the road edge is less than a set threshold, determining that there exists a possibility of connection between two points; the potential path detection network has a two-dimensional network structure proposed under inspiration of a continuous attractor network in a RatSLAM model, and is configured to simulate a process of judging whether roads are connected by living things; the updated episodic cognitive map is a new map obtained by correcting an event transition weight in the original episodic cognitive map according to the detected potential path.

2. The path planning method according to claim 1, wherein the RatSLAM algorithm is a bionic navigation algorithm, and the establishing an empirical map using a RatSLAM algorithm comprises: establishing a two-dimensional empirical map using RGB (Red, Green, and Blue) image information collected by a monocular camera.

3. The path planning method according to claim 1, wherein the Canny operator is an edge extraction algorithm.

Description

BRIEF DESCRIPTION OF DRAWINGS

(1) The present invention is further described below with reference to the accompanying drawings and embodiments:

(2) FIG. 1 is a schematic flow chart of a path planning method according to an embodiment of the present invention.

(3) FIG. 2 is a schematic diagram of a motion track of a mobile robot.

(4) FIG. 3 is a schematic diagram of an empirical map established using a RatSLAM algorithm.

(5) FIG. 4 is a schematic diagram of a road edge detection effect based on a Canny operator.

(6) FIG. 5 is a schematic diagram of a potential path detection network.

(7) FIG. 6 is a schematic diagram of an original episodic cognitive map obtained based on an episodic memory model.

(8) FIG. 7 is a schematic diagram of an updated episodic cognitive map obtained after the potential path detection network is fused.

(9) FIG. 8 is a schematic diagram of an updated empirical map generated with the RatSLAM algorithm based on the potential path detection network.

DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

(10) The present disclosure is further described below with reference to the accompanying drawings and embodiments.

(11) As shown in FIG. 1, one embodiment of the present invention provides a path planning method, and in the present embodiment, the path planning method is an episodic memory path planning method based on memory fusion, and the path planning method includes the following steps:

(12) S1: establishing an empirical map and a corresponding episodic cognitive map using a RatSLAM algorithm based on an episodic memory model;

(13) S2: extracting a road edge in a historical memory image with a Canny operator;

(14) S3: performing conversion to a world coordinate system from a pixel coordinate system based on the road edge, and preliminarily judging connectivity according to slope of the road edge;

(15) S4: continuously injecting energy into the potential path detection network according to continuous observation of a potential path, so as to further judge the road connectivity;

(16) S5: fusing the detected potential path and the original episodic cognitive map, and correspondingly updating the empirical map; and

(17) S6: planning a path based on the updated episodic cognitive map.

(18) In step S1, the RatSLAM algorithm is a bionic navigation algorithm; the establishing an empirical map using a RatSLAM algorithm includes: establishing a two-dimensional empirical map using RGB image information collected by a monocular camera. The episodic memory model is a path planning algorithm; the episodic cognitive map is a two-dimensional incremental matrix and composed of a discrete limited event space and an event transition set. FIG. 2 shows a schematic diagram of a motion track 100 of a mobile robot, the dotted line representing a potential path 200. FIG. 3 shows a schematic diagram of the empirical map established using the RatSLAM algorithm.

(19) In step S2, the Canny operator is an edge extraction algorithm. FIG. 4 shows successful detection of a road edge 300 of a hallway based on the Canny operator. In the above, the Canny operator has high noise interference resistance, may adapt to different environments, has a good detection performance, and thus is selected as an edge detection algorithm. A detection result based on the Canny operator has rich environment structure edge information, but only the road edge information is required when the path is planned, and therefore, other redundant edges are required to be removed. Two longest edges in the image are detected by setting an appropriate detection region, thereby detecting the road edge information.

(20) In step S3, the preliminarily judging connectivity according to slope of the road edge 300 includes: when an absolute value of a difference between the slope of the road edge 300 is less than a set threshold, preliminarily determining that there exists a possibility of connection between two points.

(21) In step S4, the potential path 200 is a potential safe path, and the potential path detection network has a two-dimensional network structure proposed under inspiration of a continuous attractor network in a RatSLAM model, and is configured to simulate a process of judging whether roads are connected by living things. FIG. 5 shows a schematic diagram of the potential path detection network.

(22) In step S6, the updated episodic cognitive map is a new map obtained by correcting an event transition weight in the original episodic cognitive map according to the detected potential path 200.

(23) FIG. 6 shows a schematic diagram of the original episodic cognitive map obtained based on the episodic memory model in S1. FIG. 7 shows a schematic diagram of the updated episodic cognitive map obtained after the original episodic cognitive map and the potential path detection network are fused. FIG. 8 shows a schematic diagram of the updated empirical map generated with the RatSLAM algorithm based on the potential path detection network.

(24) According to the embodiments of the present invention, the potential safe path in an environment is searched using the potential path detection network, and compared with an original episodic memory model only containing a track of the mobile robot in the past time and space, the episodic memory model after the potential path detection network is fused may plan the better path for the mobile robot.

(25) Certainly, the above-mentioned embodiments are merely illustrative of the technical concepts and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All modifications made in accordance with the spirit of the main technical solution of the present invention are intended to be covered by the protection scope of the present invention.