CN-121659815-B - Mars vehicle non-contact trafficability prediction method and system based on thermal inertia

CN121659815BCN 121659815 BCN121659815 BCN 121659815BCN-121659815-B

Abstract

The invention belongs to the technical field of data processing, and discloses a non-contact trafficability prediction method and a non-contact trafficability prediction system for a Mars vehicle based on thermal inertia, wherein the method comprises the steps of obtaining a time sequence of ground surface temperature and environmental parameters of a target area; the method comprises the steps of constructing a thermal inertia estimation model, inputting a surface temperature time sequence and environmental parameters into the thermal inertia estimation model to obtain a thermal soil thermal inertia estimation value, constructing a thermal inertia and trafficability index relation model, inputting the thermal soil thermal inertia estimation value into the thermal inertia and trafficability index relation model to output a predicted trafficability index, determining a trafficability state level according to the predicted trafficability index, generating a navigation control suggestion, and enabling a Mars vehicle to pass through a target area according to the Mars vehicle navigation control suggestion. According to the invention, the passing index of the Mars is predicted by extracting the thermal inertia estimated value of the fire soil of the target area, so that the evaluation accuracy of the Mars passing through the target area can be effectively improved, and the running safety of the Mars is ensured.

Inventors

QI YINGCHUN
HAN XUEJIE
HUANG HESHU
ZOU MENG
JIN JINGFU
YU QINGYU
HE LIANBIN

Assignees

吉林大学

Dates

Publication Date: 20260512
Application Date: 20260209

Claims (9)

1. The spark non-contact trafficability estimation method based on the thermal inertia is characterized by comprising the following steps of: determining a target area, and acquiring a surface temperature time sequence and environmental parameters of the target area; the determining the target area and acquiring the surface temperature time sequence and the environment parameters of the target area specifically comprises the following steps: determining a target area, acquiring an area shape of the target area, and determining time resolution according to the area shape; determining a preset illumination mode, and performing thermal radiation detection on the target area by adopting thermal infrared imaging equipment on a Mars vehicle according to the time resolution and the preset illumination mode to obtain multi-frame thermal infrared images of the target area in a preset time period; wherein the preset illumination mode comprises a natural illumination mode and an active heat radiation mode; Extracting a sequence of the change of the surface temperature along with time in the multi-frame thermal infrared image to obtain a surface temperature time sequence; acquiring environmental parameters of the target area; constructing a thermal inertia estimation model, and inputting the earth surface temperature time sequence and the environmental parameters into the thermal inertia estimation model to obtain a fire soil thermal inertia estimated value; Building a thermal inertia and passability index relation model, inputting the fire soil thermal inertia estimated value into the thermal inertia and passability index relation model, and outputting a predicted passability index; And determining a passing state grade according to the predicted passing state index, and generating a navigation control suggestion according to the passing state grade, so that the Mars vehicle passes through the target area according to the Mars vehicle navigation control suggestion.
2. The thermal inertia-based non-contact trafficability prediction method of the Mars vehicle according to claim 1, wherein the extracting the sequence of the change of the surface temperature with time in the multi-frame thermal infrared image to obtain the surface temperature time sequence specifically comprises: preprocessing the multi-frame thermal infrared image, wherein the preprocessing comprises fixed dead point identification processing, denoising processing, alignment processing and characteristic point extraction processing, so as to obtain a preprocessed image; calculating the temperature mean value and standard deviation of effective pixels in each frame of image in the preprocessed image, and obtaining a target temperature value according to the temperature mean value and the standard deviation; arranging the target temperature values in time sequence to obtain an initial temperature time sequence; and carrying out smoothing treatment on the initial temperature time sequence to obtain a surface temperature time sequence.
3. The thermal inertia-based Mars vehicle non-contact trafficability estimation method of claim 1, wherein the environmental parameter includes albedo; the obtaining the environmental parameters of the target area specifically comprises the following steps; Carrying out multiband imaging processing and radiation calibration processing on the target area by adopting a multi-spectrum camera carried by a Mars vehicle to obtain an albedo image, and calculating the average albedo in the albedo image to obtain the albedo; or a high-resolution visible light camera or a color camera carried by a Mars is adopted to carry out imaging processing and radiation calibration processing on a terrain area with a shadow boundary in the target area, so as to obtain a reflectivity image; dividing the reflectivity image into a direct illumination area and a shadow area by adopting an image processing algorithm, and calculating the average reflectivity of the direct illumination area and the shadow area; performing atmospheric scattering correction treatment on the average reflectivity of the shadow region to obtain an albedo; Or constructing a pre-training depth convolution neural network, obtaining a visible light image of the target area, and analyzing the visible light image through the pre-training depth convolution neural network to obtain the albedo.
4. The thermal inertia-based Mars vehicle non-contact trafficability estimation method according to claim 3, wherein the constructing a thermal inertia estimation model, and inputting the surface temperature time sequence and the environmental parameter into the thermal inertia estimation model to obtain a fire soil thermal inertia estimated value, specifically comprises: constructing a thermal inertia estimation model based on a Mars earth surface thermal balance equation and a thermal conduction equation, inputting the earth surface temperature time sequence and the environmental parameter into the thermal inertia estimation model, and carrying out soil thermal inertia calculation on the earth surface temperature time sequence and the environmental parameter through the thermal inertia estimation model to obtain a fire earth thermal inertia estimation value; the expression of the thermal inertia estimation model is as follows: ; Wherein, the Is the thermal inertia estimated value of the fire soil, For the integrated correction factor associated with the target area environment, For the albedo in the environmental parameter, And (3) obtaining the maximum surface temperature difference in a selected time period in the surface temperature time sequence.
5. The thermal inertia-based non-contact trafficability prediction method of the Mars vehicle according to claim 1, wherein the construction of the thermal inertia and trafficability index relation model, the input of the thermal inertia estimation value to the thermal inertia and trafficability index relation model, and the output of the prediction trafficability index specifically comprises: preparing a plurality of groups of simulated fire soil sample pieces, and acquiring a thermal inertia actual measurement value and a mechanical parameter actual measurement value of the simulated fire soil sample pieces; Constructing a data set according to the thermal inertia actual measurement value and the mechanical parameter actual measurement value, and dividing the data set into a training set, a verification set and a test set; determining a polynomial regression model, and carrying out model training on the polynomial regression model according to the training set to obtain an initial model; Or adopting a support vector regression model or a gradient lifting regression tree model, and carrying out model training on the support vector regression model or the gradient lifting regression tree model according to the training set to obtain an initial model; Cross-verifying the initial model according to the verification set, and optimizing the model according to the test set to obtain a thermal inertia and passability index relation model; And inputting the fire soil thermal inertia estimated value into the thermal inertia and trafficability index relation model, and outputting a predicted trafficability index.
6. The thermal inertia-based non-contact trafficability prediction method of the Mars vehicle according to claim 1, wherein the determining a trafficability state level according to the predicted trafficability index, and generating a navigation control suggestion according to the trafficability state level, so that the Mars vehicle passes through the target area according to the Mars vehicle navigation control suggestion, specifically comprises: determining a preset safety margin and a preset safety threshold; if the predicted passing index is greater than or equal to the sum of the preset safety margin and the preset safety threshold, judging that the target area is a first passing state grade; if the predicted passability index is larger than the preset safety threshold and smaller than the sum of the preset safety margin and the preset safety threshold, judging that the target area is a second passability state level; If the predicted passability index is smaller than the preset safety threshold, judging that the target area is a third passability state level; and respectively generating corresponding navigation control suggestions according to the first passing state level, the second passing state level and the third passing state level, so that the Mars pass through the target area according to the Mars navigation control suggestions.
7. A thermal inertia-based Mars contactless trafficability prediction system, wherein the thermal inertia-based Mars contactless trafficability prediction system is configured to implement the thermal inertia-based Mars contactless trafficability prediction method according to any one of claims 1 to 6, and the thermal inertia-based Mars contactless trafficability prediction system includes: the regional data acquisition module is used for determining a target region and acquiring a surface temperature time sequence and environmental parameters of the target region; The thermal inertia estimation module is used for constructing a thermal inertia estimation model, inputting the earth surface temperature time sequence and the environmental parameters into the thermal inertia estimation model, and obtaining a fire soil thermal inertia estimation value; the passability index output module is used for constructing a relation model of thermal inertia and passability index, inputting the fire soil thermal inertia estimated value into the relation model of thermal inertia and passability index, and outputting a predicted passability index; And the navigation advice generation module is used for determining a passing state grade according to the predicted passing state index, generating navigation control advice according to the passing state grade, and enabling the Mars to pass through the target area according to the Mars navigation control advice.
8. A terminal comprising a memory, a processor, and a thermal inertia-based Mars contactless trafficability prediction program stored on the memory and operable on the processor, wherein the thermal inertia-based Mars contactless trafficability prediction program when executed by the processor implements the steps of the thermal inertia-based Mars contactless trafficability prediction method according to any one of claims 1 to 6.
9. A computer readable storage medium, wherein the computer readable storage medium stores a thermal inertia-based Mars contactless trafficability estimation program, and the thermal inertia-based Mars contactless trafficability estimation program realizes the steps of the thermal inertia-based Mars contactless trafficability estimation method according to any one of claims 1 to 6 when executed by a processor.

Description

Mars vehicle non-contact trafficability prediction method and system based on thermal inertia Technical Field The present invention relates to the field of data processing technologies, and in particular, to a non-contact passing performance estimating method, system, terminal and computer readable storage medium for a Mars vehicle based on thermal inertia. Background Mars are covered by desert in large area, and because of the existence of Mars atmosphere, mars have various complex and dangerous terrains such as wave-shaped hills, soft fine sand, hard thin shells and the like. These terrains are visually confusing, for example, a layer of loose sand, perhaps tens of centimeters deep, under a layer of hard thin shell, on the order of millimeters to centimeters, a piece of seemingly flat, homogenous sand, the density and load bearing capacity of which may vary by orders of magnitude from region to region. The inconsistency of the surface morphology and the deep mechanical properties makes the Mars easy to sink or slide seriously in a seemingly safe area, and constitutes a serious continuous threat to the driving safety. In order to solve the problems, the trafficability estimation of the existing Mars is mainly based on two types of technical paths, wherein the first type is based on geometric trafficability judgment of visual sensors such as a visible light camera and a laser radar, and the second type is based on kinetic data inversion after wheels are in contact with soil. However, the two modes cannot sense and predict the internal mechanical characteristics of the soil in advance, so that the passing performance evaluation precision of the Mars is low, and the driving safety of the Mars is influenced. Accordingly, the prior art is still in need of improvement and development. Disclosure of Invention The invention mainly aims to provide a non-contact type passing performance prediction method and system for a Mars vehicle based on thermal inertia, and aims to solve the problems that the passing performance evaluation precision of the Mars vehicle is low and the driving safety of the Mars vehicle is affected because the internal mechanical characteristics of the Mars soil cannot be sensed and predicted in advance in the prior art. In order to achieve the above purpose, the invention provides a thermal inertia-based non-contact trafficability prediction method for a Mars vehicle, which comprises the following steps: determining a target area, and acquiring a surface temperature time sequence and environmental parameters of the target area; constructing a thermal inertia estimation model, and inputting the earth surface temperature time sequence and the environmental parameters into the thermal inertia estimation model to obtain a fire soil thermal inertia estimated value; Building a thermal inertia and passability index relation model, inputting the fire soil thermal inertia estimated value into the thermal inertia and passability index relation model, and outputting a predicted passability index; And determining a passing state grade according to the predicted passing state index, and generating a navigation control suggestion according to the passing state grade, so that the Mars vehicle passes through the target area according to the Mars vehicle navigation control suggestion. Optionally, the thermal inertia-based non-contact trafficability prediction method for the Mars vehicle, wherein the determining a target area and acquiring a surface temperature time sequence and an environmental parameter of the target area specifically includes: determining a target area, acquiring an area shape of the target area, and determining time resolution according to the area shape; determining a preset illumination mode, and performing thermal radiation detection on the target area by adopting thermal infrared imaging equipment on a Mars vehicle according to the time resolution and the preset illumination mode to obtain multi-frame thermal infrared images of the target area in a preset time period; wherein the preset illumination mode comprises a natural illumination mode and an active heat radiation mode; Extracting a sequence of the change of the surface temperature along with time in the multi-frame thermal infrared image to obtain a surface temperature time sequence; And acquiring the environmental parameters of the target area. Optionally, the thermal inertia-based non-contact trafficability prediction method of the Mars vehicle, wherein the extracting the sequence of the change of the surface temperature along with time in the multi-frame thermal infrared image to obtain the surface temperature time sequence specifically includes: preprocessing the multi-frame thermal infrared image, wherein the preprocessing comprises fixed dead point identification processing, denoising processing, alignment processing and characteristic point extraction processing, so as to obtain a preprocessed image; calculating the tempera