An environmental information updating method and device, and a storage medium

Abstract

The application discloses an environment information updating method and device and a storage medium. The environment information updating method comprises the following steps: acquiring sensor data of each working device at a current moment and global probabilities of each environment element in prior environment information at the current moment; obtaining each target detected by each working device based on the acquired sensor data of the working device at the current moment, and calculating local probabilities of the targets; calculating transition probabilities between target data of each target and each environment element based on the calculated local probabilities of the targets; and updating the global probabilities of each environment element in the prior environment information at a next moment according to the acquired global probabilities of each environment element in the prior environment information at the current moment and the calculated transition probabilities, so as to complete the environment information updating. The application can provide a basis for a working process and can update the prior environment information.

Description

Technical Field

[0001] This invention relates to a method, apparatus, and storage medium for updating environmental information, belonging to the field of engineering machinery technology. Background Technology

[0002] Unlike autonomous driving in passenger vehicles, digital construction of engineering machinery involves the interaction between the construction environment and the equipment operation process. In this situation, environmental factors that hinder the construction process come not only from dynamic targets intruding into the equipment's operating range, but also from environmental factors that "grow" in the environment itself under the influence of the equipment's operation.

[0003] In response to the above situation, engineering machinery and equipment equipped with digital construction systems need to detect, describe, and manage changes in environmental conditions, and build a mechanism for the mutual construction between prior and subsequent environmental information knowledge.

[0004] Chinese patent application CN115223118A discloses a method for judging the confidence level of high-precision maps. The method includes: after detecting the use of a high-precision map, acquiring real road traffic information at the current location; based on the real road traffic information, narrowing down the total elements to obtain judgment elements for which confidence levels need to be judged; based on the judgment elements, acquiring corresponding map traffic information for the current location on the high-precision map, and comparing the map traffic information with the judgment elements to obtain the confidence level of the judgment elements; and evaluating the confidence level of the high-precision map based on the confidence level of the judgment elements. This invention evaluates the timeliness and reliability of high-precision maps, improving the accuracy of autonomous driving algorithms in using high-precision map information.

[0005] This invention patent only considers the guiding role of prior environmental factors on equipment behavior, and adds confidence attribute and confidence judgment function on the basis of the guiding role, but does not consider the possible counter-effect of equipment behavior on environmental factors. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, apparatus, and storage medium for updating environmental information, which can provide a basis for the operation process and update prior environmental information. To achieve the above objective, this invention employs the following technical solution:

[0007] In a first aspect, the present invention provides an environmental information updating method, comprising:

[0008] Obtain the sensor data of each operating device at the current moment and the global probability of each environmental element in the prior environmental information at the current moment;

[0009] Based on the sensor data of the operating equipment at the current moment, the targets detected by each operating equipment are obtained, and the local probability of each target is calculated.

[0010] Based on the calculated local probabilities of each target, the transition probabilities between the target data of each target and each environmental element are calculated. Based on the global probabilities of each environmental element in the prior environmental information at the current moment and the calculated transition probabilities, the global probabilities of each environmental element in the prior environmental information at the next moment are updated, thus completing the environmental information update.

[0011] In conjunction with the first aspect, optionally, obtaining the various targets detected by each working device based on the sensor data of the working devices at the current moment includes:

[0012] The initial number of working devices is n, and each device is D(i), where i = 1…n;

[0013] Feature data is obtained by extracting features from the sensor data of the operating equipment at the current moment.

[0014] Based on Bayes' theorem, the extracted feature data is tracked to obtain the m detected by each operating device D(i). i Each target O(i, j) and its corresponding target data and state data are defined, where i = 1…n, j = 1…m. i The target's state data includes the expected value of the target's state. And the uncertainty value σ, where i = 1…n, j = 1…m i .

[0015] In conjunction with the first aspect, optionally, the local probability includes local existence probability, local semantic probability, and local behavior probability;

[0016] The calculation of the local probability of each target includes:

[0017] Based on the state data of target O(i, j), determine whether the target type is a point target, a surface target, or a volume target; where i = 1…n, j = 1…m i ;

[0018] When the type of target O(i,j) is a point target, calculate the local existence probability of target O(i,j);

[0019] When the type of target O(i,j) is a surface target, calculate the local existence probability and local semantic probability of target O(i,j);

[0020] When the type of target O(i,j) is a volume target, calculate the local existence probability, local semantic probability, and local behavior probability of target O(i,j).

[0021] In conjunction with the first aspect, optionally, the calculation of the local existence probability, local semantic probability, and local behavior probability of the target O(i,j) includes:

[0022] Calculate the local existence probability of the target O(i, j), including:

[0023] Based on the state data of target O(i,j), the target state x has the following relationship: in, Let σ be the expected value of the target state, and σ be the uncertainty value of the target state.

[0024] The signal-to-noise ratio (SNR) of the target data is a monotonic function of σ, and there exists a relationship SNR = f(σ);

[0025] Based on the local existence probability of target O(i,j) Relationship between the signal-to-noise ratio (SNR) and the target data The local existence probability of target O(i,j) is calculated. Where g(SNR) is the local existence probability calculation of the signal-to-noise ratio (SNR) of the target data;

[0026] The local semantic probability of target O(i,j) is calculated using a deep learning network.

[0027] Calculate the local behavior probability of target O(i,j), including:

[0028] Based on the local semantic probability of target O(i,j) Determine the semantic information of target O(i,j). Where X is the semantic set corresponding to the digital construction scenario;

[0029] Initialize the semantic set that affects construction tasks in the digital construction scenario as follows: The prior probability f1(x) of the influence of the semantic information of the objective O(i,j) on the execution of the construction task is calculated using the following formula:

[0030]

[0031] Initialize the construction task T(i) corresponding to the device D(i), and calculate the correlation between the objective O(i, j) and the construction task T(i).

[0032] Based on the relative pose vector between target O(i,j) and device D(i) Local existence probability of target O(i,j) Given the correlation degree d(O(i,j)) between objective O(i,j) and construction task T(i), calculate the posterior probability that objective O(i,j) influences the execution of construction task T(i). Where F() is used to calculate the posterior probability;

[0033] Calculate the probability that a target O(i,j) with semantic information X′ has an impact on construction task T(i).

[0034] Local semantic probabilities based on target O(i,j) Sum of probabilities Calculate the local behavior probability of target O(i,j)

[0035] In conjunction with the first aspect, optionally, the step of calculating the transition probability between target data of each target and each environmental element based on the calculated local probabilities of each target, and updating the global probability of each environmental element in the prior environmental information at the next time moment based on the global probability of each environmental element in the prior environmental information at the current time moment and the calculated transition probability, includes:

[0036] Calculate the state transition probabilities between target data for each objective and each environmental element. Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. and the calculated state transition probabilities The update obtains the global existence probability of each environmental element in the prior environment information for the next time step.

[0037] Calculate the semantic transition probability P(A|A0) between the target data of each target and each environmental element. Based on the global semantic probability P(A0) of each environmental element in the prior environmental information at the current time and the calculated semantic transition probability P(A|A0), update the global semantic probability P(A) of each environmental element in the prior environmental information at the next time.

[0038] Calculate the behavior transition probability P(ξ|ξ0) between the target data of each target and each environmental element. Based on the global behavior probability P(ξ0) of each environmental element in the prior environmental information at the current time and the calculated behavior transition probability P(ξ|ξ0), update the global behavior probability P(ξ) of each environmental element in the prior environmental information at the next time.

[0039] In conjunction with the first aspect, optionally, the calculation of the state transition probabilities between the target data of each target and each environmental element... Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. and the calculated state transition probabilities The update obtains the global existence probability of each environmental element in the prior environment information for the next time step. include:

[0040] Calculate the state correlation between the target data O(i,j) from device D(i) and each environmental element E(k). Based on the state association gate Γ(k), the state data association between O(i,j) and E(k) is completed to obtain D(i,j);

[0041] Calculate the state transition probabilities between the target data O(i,j) from device D(i) and each environmental element E(k).

[0042] According to the DS evidence theory, the obtained state transition probabilities By fusing the data, we obtain the state transition probabilities between the target data from device D(i) and each environmental element E(k). in, For fusion computing;

[0043] According to the DS evidence theory, the state transition probabilities obtained from different devices D(i) are... By merging the data, we can obtain the state transition probabilities between each target from each device and each environmental element at the next moment.

[0044] Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. And the obtained state transition probabilities between each target and each environmental element from each device at the next moment. Update the global existence probability of each environmental element E(k) in the prior environment information for the next time step.

[0045] In conjunction with the first aspect, optionally, the step of calculating the semantic transition probability P(A|A0) between the target data of each target and each environmental element, and updating the global semantic probability P(A) of each environmental element in the prior environmental information at the next moment based on the global semantic probability P(A0) of each environmental element in the prior environmental information at the current moment and the calculated semantic transition probability P(A|A0), includes:

[0046] Calculate the semantic association between the target data O(i,j) from device D(i) and each environmental element E(k). Based on the semantic association gate Λ(k), the semantic association between O(i,j) and E(k) is completed, resulting in... Where Y(k) is the semantic set of environmental elements, and P(d) is the representative element of semantic probability. Let O(i,j) be the local semantic probability of the target.

[0047] Calculate the semantic transfer probability between target data O(i,j) from device D(i) and each environmental element E(k).

[0048] According to the DS evidence theory, the obtained semantic transition probability P ij (A|A0) are fused to obtain the semantic transfer probabilities between the target detection results from device D(i) and each environmental element. in, For fusion computing;

[0049] According to the DS evidence theory, the semantic transition probability P obtained from different devices D(i) i (A|A0) are fused to obtain the semantic transfer probabilities of each target and each environmental element from each device at the next moment.

[0050] Based on the global semantic probability P(A0) of each environmental element in the prior environmental information at the current moment, and the semantic transition probability P(A|A0) of each target and each environmental element from each device at the next moment, update the global semantic probability P(A) = P(A0)P(A|A0) of each environmental element E(k) in the prior environmental information at the next moment.

[0051] In conjunction with the first aspect, optionally, the calculation of the behavior transition probability P(ξ|ξ0) between the target data of each target and each environmental element, and the updating of the global behavior probability P(ξ) of each environmental element in the prior environmental information at the next moment based on the global behavior probability P(ξ0) of each environmental element in the prior environmental information at the current moment and the calculated behavior transition probability P(ξ|ξ0), includes:

[0052] Calculate the behavioral correlation between the construction task T(i) corresponding to each different device D(i) and each environmental element E(k).

[0053] according to Calculate the probability of behavioral association between device D(i) and each environmental element E(k) at the next time step. Where F() is the calculation of the behavior association probability;

[0054] Based on behavioral association gate The obtained behavioral correlation probability P T(i, k), for a specific prior environmental element E(k), classify the degree of correlation for different devices D(i);

[0055] At behavioral association level L t In this process, the correlation between target data O(i,j) from device D(i) and each environmental element E(k) is calculated. Based on the state association gate Γ(k), the data association between O(i,j) and E(k) is completed, and D(i,j) is obtained;

[0056] At behavioral association level L t In this context, based on the DS evidence theory, the behavioral transition probability between target data O(i,j) from device D(i) and each environmental element E(k) is calculated. in, For fusion computing;

[0057] At behavioral association level L t In this context, according to the DS evidence theory, at the construction task correlation level L... t In the middle, for different devices D(i), the obtained behavior transition probability P ti (ξ|ξ0) are fused to obtain the behavior transition probabilities of each target and each environmental element from each device in the next moment.

[0058] According to the DS evidence theory, different behavioral correlation levels L t For all devices D(i), the obtained behavior transition probability P t (ξ|ξ0) are fused to obtain the behavior transition probabilities of each target and each environmental element from each device in the next moment.

[0059] Based on the global behavior probability P(ξ0) of each environmental element in the prior environmental information at the current moment, and the behavior transition probability P(ξ|ξ0) of each target and each environmental element from each device at the next moment, update the global behavior probability P(ξ)=P(ξ0)P(ξ|ξ0) of each environmental element E(k) in the prior environmental information at the next moment.

[0060] In a second aspect, the present invention provides an environmental information updating device, comprising:

[0061] Acquisition module: used to acquire the sensor data of each operating device at the current time and the global probability of each environmental element in the prior environment information at the current time;

[0062] First calculation module: used to obtain the targets detected by each working device based on the sensor data of the working device at the current time, and calculate the local probability of each target;

[0063] The calculation and update module is used to calculate the transition probability between the target data of each target and each environmental element based on the calculated local probability of each target. Based on the global probability of each environmental element in the prior environmental information at the current time and the calculated transition probability, it updates the global probability of each environmental element in the prior environmental information at the next time and completes the environmental information update.

[0064] Thirdly, the present invention provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the steps of the environmental information update method described in the first aspect.

[0065] Compared with the prior art, the beneficial effects achieved by the environmental information updating method, apparatus and storage medium provided in the embodiments of the present invention include:

[0066] This invention acquires the global probability of each environmental element in the current time's sensor data of each working device and the current time's prior environmental information; this invention can provide a basis for the operation process based on sensor data and prior environmental information, ensuring normal operation;

[0067] This invention obtains the various targets detected by each working device based on the sensor data of the working equipment at the current moment, and calculates the local probability of each target; based on the calculated local probabilities of each target, it calculates the transition probability between the target data of each target and each environmental element; and based on the global probability of each environmental element in the prior environmental information at the current moment and the calculated transition probability, it updates the global probability of each environmental element in the prior environmental information at the next moment; this invention can update the prior environmental information.

[0068] The present invention collects sensor data and prior environmental information in real time, and updates prior environmental information in real time. It takes into account the relationship between the environment and the operating equipment, and can improve the efficiency and stability of the operation process and enhance the safety of the system. Attached Figure Description

[0069] Figure 1 This is a flowchart of an environmental information updating method according to Embodiment 1 of the present invention;

[0070] Figure 2 This is a flowchart illustrating the calculation of the local existence probability in an environmental information updating method according to Embodiment 1 of the present invention.

[0071] Figure 3This is a flowchart illustrating the calculation of local behavior probability in an environmental information updating method according to Embodiment 1 of the present invention.

[0072] Figure 4 This is a flowchart illustrating the calculation of state transition probability and the updating of global existence probability in an environmental information updating method according to Embodiment 1 of the present invention;

[0073] Figure 5 This is a flowchart of calculating semantic transition probability and updating global semantic probability in an environmental information updating method according to Embodiment 1 of the present invention;

[0074] Figure 6 This is a flowchart of calculating the behavior transition probability and updating the global behavior probability in an environmental information updating method according to Embodiment 1 of the present invention;

[0075] Figure 7 This is a flowchart illustrating the prediction process of the environmental state layer containing the target data in an environmental information updating method according to Embodiment 2 of the present invention.

[0076] Figure 8 This is a flowchart of the update process of the environmental status layer where the environmental elements are located in an environmental information update method according to Embodiment 2 of the present invention;

[0077] Figure 9 This is a state transition diagram based on the environmental state layer defined in an environmental information update method according to Embodiment 2 of the present invention. Detailed Implementation

[0078] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0079] Example 1:

[0080] like Figure 1 As shown, this embodiment provides an environmental information updating method, including:

[0081] Obtain the sensor data of each operating device at the current moment and the global probability of each environmental element in the prior environmental information at the current moment;

[0082] Based on the sensor data of the operating equipment at the current moment, the targets detected by each operating equipment are obtained, and the local probability of each target is calculated.

[0083] Based on the calculated local probabilities of each target, the transition probabilities between the target data of each target and each environmental element are calculated. Based on the global probabilities of each environmental element in the prior environmental information at the current moment and the calculated transition probabilities, the global probabilities of each environmental element in the prior environmental information at the next moment are updated, thus completing the environmental information update.

[0084] The specific steps include:

[0085] Step 1: Obtain the sensor data of each working device at the current moment and the global probability of each environmental element in the prior environmental information at the current moment.

[0086] Step 2: Based on the sensor data of the operating equipment at the current moment, obtain the targets detected by each operating equipment and calculate the local probability of each target.

[0087] Step 2.1: Based on the sensor data of the operating equipment at the current moment, obtain the targets detected by each operating equipment.

[0088] Step 2.1.1: Initialize the number of working devices to n, and each device to D(i), where i = 1…n.

[0089] Step 2.1.2: Extract features from the sensor data of the operating equipment at the current moment to obtain feature data.

[0090] Step 2.1.3: Based on Bayes' theorem, track the extracted feature data to obtain the m detected by each operating device D(i). i Each target O(i, j) and its corresponding target data and state data are defined, where i = 1…n, j = 1…m. i The target's state data includes the expected value of the target's state. And the uncertainty value σ, where i = 1…n, j = 1…m i .

[0091] Step 2.2: Calculate the local probability of each target.

[0092] Regarding the local probability of the target, this specifically corresponds to the following three issues.

[0093] Question 1: Regarding the device itself, is the target stably existent? The answer to this question can generate the probability of the target's local existence. describe.

[0094] Question 2: From the perspective of the device itself, what type of target is it? The answer to this question can generate the local semantic probability of the target. describe.

[0095] Question 3, regarding the relationship between the target and the construction task from the perspective of the equipment itself, the answer to this question can generate the local behavioral probability of the target. describe.

[0096] Therefore, local probability includes local existence probability, local semantic probability, and local behavior probability.

[0097] Based on the state data of target O(i, j), determine whether the target type is a point target, a surface target, or a volume target; where i = 1…n, j = 1…m i .

[0098] When the type of target O(i,j) is a point target, calculate the local existence probability of target O(i,j).

[0099] When the type of target O(i,j) is a surface target, calculate the local existence probability and local semantic probability of target O(i,j).

[0100] When the type of target O(i,j) is a volume target, calculate the local existence probability, local semantic probability, and local behavior probability of target O(i,j).

[0101] For a specific sensor detection result, it must contain both the true value and noise, representing the probability of the target's local existence. It can be defined as a function of the signal-to-noise ratio (SNR) of the measurement result. For example... Figure 2 As shown, the local existence probability of target O(i, j) is calculated, including:

[0102] Based on the state data of target O(i,j), the target state x has the following relationship: in, Let σ be the expected value of the target state, and σ be the uncertainty value of the target state.

[0103] The signal-to-noise ratio (SNR) of the target data is a monotonic function of σ, and there exists a relationship SNR = f(σ);

[0104] Based on the local existence probability of target O(i,j) Relationship between the signal-to-noise ratio (SNR) and the target data The local existence probability of target O(i,j) is calculated. Where g(SNR) is the local existence probability calculation of the signal-to-noise ratio (SNR) of the target data;

[0105] If the global probability of each environmental element in the prior environmental information at the current moment does not exist, calculate the global probability of each environmental element in the prior environmental information at the current moment.

[0106] For some sensors, the type of a target can be determined by optical or color features from the raw sensor data, and a probability of the target belonging to a specific type can be given; this is called local semantic probability. Calculating the local semantic probability of target O(i,j) includes: using a deep learning network to calculate the local semantic probability of target O(i,j).

[0107] Local behavior probability of the target Break it down into the following issues:

[0108] First, the probability that the target belongs to a specific semantic category is calculated using the target's local semantic probability. To describe;

[0109] Secondly, the probability that a target with a specific semantic meaning will affect the construction task. Perform the calculation based on the following relationship: Where f1(x) is the prior probability that a specific semantic x affects the execution of the construction task, the semantic set is X, and the set of semantics that will affect the construction task is... f2(O) is the posterior probability that the objective O affects the execution of the construction task T.

[0110] like Figure 3 As shown, the calculation of the local behavior probability of target O(i, j) includes:

[0111] Based on the local semantic probability of target O(i,j) Determine the semantic information of target O(i,j). Where X is the semantic set corresponding to the digital construction scenario;

[0112] Initialize the semantic set that affects construction tasks in the digital construction scenario as follows: The prior probability f1(x) of the influence of the semantic information of the objective O(i,j) on the execution of the construction task is calculated using the following formula:

[0113]

[0114] Initialize the construction task T(i) corresponding to the device D(i), and calculate the correlation between the objective O(i, j) and the construction task T(i).

[0115] Based on the relative pose vector between target O(i,j) and device D(i) Local existence probability of target O(i,j) Given the correlation degree d(O(i,j)) between objective O(i,j) and construction task T(i), calculate the posterior probability that objective O(i,j) influences the execution of construction task T(i). Where F() is used to calculate the posterior probability;

[0116] Calculate the probability that a target O(i,j) with semantic information X′ has an impact on construction task T(i).

[0117] Local semantic probabilities based on target O(i,j) Sum of probabilities Calculate the local behavior probability of target O(i,j)

[0118] Step 3: Based on the calculated local probabilities of each target, calculate the transition probabilities between the target data of each target and each environmental element. Based on the global probabilities of each environmental element in the prior environmental information at the current moment and the calculated transition probabilities, update the global probabilities of each environmental element in the prior environmental information at the next moment, and complete the environmental information update.

[0119] Step 3.1: If the global probability of each environmental element in the prior environmental information at the current time does not exist, calculate the global probability of each environmental element. At time t, the construction task corresponding to different operating equipment D(i) is T(i), where i = 1…n.

[0120] The global probability of environmental factors corresponds to the following three questions.

[0121] Question 1: From a global perspective, what is the life cycle of an environmental element, including its occurrence and extinction? The answer to this question can generate the probability of the environmental element's existence. describe.

[0122] Question 2: What type of environmental element is it from a global perspective? The answer to this question can generate a semantic probability description P(A) of the environmental element.

[0123] Question 3, the relationship between environmental factors and construction tasks from a global perspective. The answer to this question can be described by the behavioral probability P(ξ) of the environmental factors.

[0124] The calculation of the global probability of each environmental element based on this method includes the following steps:

[0125] Step 3.1.1: Calculate the state correlation degree between the target data of each working device and the prior environmental elements, and complete the state data correlation between the target data of each working device and the prior environmental elements.

[0126] The state correlation degree D(i,j,k) between the target detection result O(i,j) from device D(i) and the prior environmental element E(k) is as follows:

[0127]

[0128] Based on the required correlation degree D(i, j, k), targets that fall within the state correlation gate Γ(k) are selected, and a total of j′ targets fall within the state correlation gate T(k).

[0129] By filtering through state association gates, the data association between the target data O(i,j) and the prior environment element E(k) is completed, thereby reducing the dimensionality of the association degree and transforming D(i,j,k) into D(i,j).

[0130] Step 3.1.2: Calculate the semantic correlation between the target data of each working device and the prior environmental elements, and complete the semantic correlation between the target data of each working device and the prior environmental elements.

[0131] Let X(i,j) be the semantic set corresponding to the target data O(i,j) from device D(i), and Y(k) be the semantic set corresponding to the prior environment element E(k). Then, the semantic correlation between O(i,j) and E(k) is... as follows:

[0132]

[0133] Based on the semantic association gate Λ(k), semantic association is achieved by filtering semantic information that falls within it, thereby reducing the dimensionality of semantic association degree. Become

[0134] Step 3.1.3: Calculate the behavioral correlation between the construction task T(i) corresponding to each different piece of equipment D(i) and the prior environmental element E(k). As shown in the following formula,

[0135]

[0136] Then based on The probability of association between device D(i) and prior environmental element E(k) at time t0+Δt conforms to the following relationship:

[0137]

[0138] Then based on the behavior association gate The obtained behavioral correlation probability P T For a specific prior environmental element E(k), the degree of correlation is classified for different devices D(i), which can be divided into τ behavioral correlation levels, denoted as L. t , (where t=1…τ).

[0139] Step 3.2: Calculate the state transition probabilities between the target data of each objective and each environmental element. Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. and the calculated state transition probabilities The update obtains the global existence probability of each environmental element in the prior environment information for the next time step.

[0140] like Figure 4 As shown, it includes:

[0141] Step 3.2.1: Calculate the state correlation degree between the target data O(i,j) from device D(i) and each environmental element E(k). Based on the state association gate Γ(k), the state data association between O(i,j) and E(k) is completed to obtain D(i,j).

[0142] Step 3.2.2: Calculate the state transition probabilities between the target data O(i,j) from device D(i) and each environmental element E(k).

[0143] Step 3.2.3: Based on the DS evidence theory, calculate the obtained state transition probabilities. By fusing the data, we obtain the state transition probabilities between the target data from device D(i) and each environmental element E(k). in, For fusion computing.

[0144] Step 3.2.4: Based on the DS evidence theory, obtain the state transition probabilities from different devices D(i). By merging the data, we can obtain the state transition probabilities between each target from each device and each environmental element at the next moment.

[0145] Step 3.2.5: Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. And the state transition probabilities obtained from each target and each environmental element from each device at the next moment. Update the global existence probability of each environmental element E(k) in the prior environment information for the next time step.

[0146] Step 3.3: Calculate the semantic transition probability P(A|A0) between the target data of each target and each environmental element. Based on the global semantic probability P(A0) of each environmental element in the prior environmental information at the current time and the calculated semantic transition probability P(A|A0), update the global semantic probability P(A) of each environmental element in the prior environmental information at the next time.

[0147] like Figure 5 As shown, it includes:

[0148] Step 3.3.1: Calculate the semantic association between the target data O(i,j) from device D(i) and each environmental element E(k). Based on the semantic association gate Λ(k), the semantic association between O(i,j) and E(k) is completed, resulting in... Where Y(k) is the semantic set of environmental elements, and P(d) is the representative element of semantic probability. Let O(i,j) be the local semantic probability of the target.

[0149] Step 3.3.2: Calculate the semantic transfer probability between the target data O(i,j) from device D(i) and each environmental element E(k).

[0150] Step 3.3.3: Based on the DS evidence theory, calculate the obtained semantic transition probability P. ij (A|A0) are fused to obtain the semantic transfer probabilities between the target detection results from device D(i) and each environmental element. in, For fusion computing.

[0151] Step 3.3.4: Based on the DS evidence theory, calculate the semantic transition probability P obtained from different devices D(i). i (A|A0) are fused to obtain the semantic transfer probabilities of each target and each environmental element from each device at the next moment.

[0152] Step 3.3.5: Based on the global semantic probability P(A0) of each environmental element in the prior environmental information at the current time and the semantic transition probability P(A|A0) of each target and each environmental element from each device at the next time, update the global semantic probability P(A) = P(A0)P(A|A0) of each environmental element E(k) in the prior environmental information at the next time.

[0153] Step 3.4: Calculate the behavior transition probability P(ξ|ξ0) between the target data of each target and each environmental element. Based on the global behavior probability P(ξ0) of each environmental element in the prior environmental information at the current time and the calculated behavior transition probability P(ξ|ξ0), update the global behavior probability P(ξ) of each environmental element in the prior environmental information at the next time.

[0154] like Figure 6 As shown, it includes:

[0155] Step 3.4.1: Calculate the behavioral correlation between the construction task T(i) corresponding to each different device D(i) and each environmental element E(k).

[0156] Step 3.4.2: According to Calculate the probability of behavioral association between device D(i) and each environmental element E(k) at the next time step. Where F() is the probability calculation of behavioral association.

[0157] Step 3.4.3: Based on behavior association gate The obtained behavioral correlation probability P T (i, k), for a specific prior environmental element E(k), classify the degree of correlation for different devices D(i).

[0158] Step 3.4.4: At the behavioral association level L t In this process, the correlation between target data O(i,j) from device D(i) and each environmental element E(k) is calculated. Based on the state association gate Γ(k), the data association between O(i,j) and E(k) is completed, and D(i,j) is obtained.

[0159] Step 3.4.5: At the behavioral association level L t In this context, based on the DS evidence theory, the behavioral transition probability between the target data O(i,j) from device D(i) and each environmental element E(k) is calculated. in, For fusion computing.

[0160] Step 3.4.6: At the behavioral association level L t In this context, according to the DS evidence theory, at the construction task correlation level L... t In the middle, for different devices D(i), the obtained behavior transition probability P ti (ξ|ξ0) are fused to obtain the behavior transition probabilities of each target and each environmental element from each device in the next moment.

[0161] Step 3.4.7: According to the DS evidence theory, the correlation level L for different behaviors t For all devices D(i), the obtained behavior transition probability P t (ξ|ξ0) are fused to obtain the behavior transition probabilities of each target and each environmental element from each device in the next moment.

[0162] Step 3.4.8: Based on the global behavior probability P(ξ0) of each environmental element in the prior environmental information at the current moment and the behavior transition probability P(ξ|ξ0) of each target and each environmental element from each device at the next moment, update the global behavior probability P(ξ)=P(ξ0)P(ξ|ξ0) of each environmental element E(k) in the prior environmental information at the next moment.

[0163] The real-time sensor data and prior environmental information collected in this embodiment provide a basis for the normal operation of the work process; it can update the prior environmental information, thereby improving the efficiency and stability of the work process and enhancing the security of the system.

[0164] Example 2:

[0165] Based on the inventive concept of Embodiment 1, this embodiment provides a method to divide the description of the environmental state into three environmental state layers based on the obstructive effect of environmental elements on the equipment operation process: foreground, midground and background.

[0166] The foreground includes environmental factors that inevitably hinder the operation of the equipment. Foreground objectives include two types:

[0167] Firstly, dynamic targets that intrude into the operating range of the equipment are foreground dynamic targets;

[0168] Secondly, during equipment operation, the static targets generated by the working environment under the influence of the operation process are the foreground static targets.

[0169] There are four sources for future goals:

[0170] Firstly, it is generated randomly during the operation process;

[0171] Secondly, it was transformed from a mid-range target.

[0172] Third, it is directly transformed from the background objective;

[0173] Fourth, its own potential transformation.

[0174] Mid-range targets encompass potential environmental elements that may hinder the operation of equipment. Mid-range targets refer to targets that already exist in the work environment, do not currently hinder the operation, but whose hindering effects will gradually become apparent as the operation progresses.

[0175] For Zhongjing's targets, there are four sources:

[0176] Firstly, it is generated randomly during the operation process;

[0177] Secondly, it stems from the degradation of forward-looking goals;

[0178] Third, it is derived from the background objective;

[0179] Fourth, its own potential changes.

[0180] The background includes environmental elements that do not hinder the operation of the equipment. The background target itself does not constitute an obstacle.

[0181] As for the background objective, there are four sources:

[0182] Firstly, it exists inherently, independent of the work process;

[0183] Secondly, it stems directly from the degradation of forward-looking goals;

[0184] Third, it is derived from the degradation of mid-range targets;

[0185] Fourth, its own potential changes.

[0186] Based on the above method of classifying environmental states, the changes in environmental states originate from four aspects:

[0187] Firstly, the random occurrence, transformation, and disappearance of dynamic foreground targets;

[0188] Secondly, the random occurrence, transformation, and disappearance of static foreground targets;

[0189] Third, the emergence, change, and disappearance of mid-range targets;

[0190] Fourth, the potential changes and disappearance of the background target.

[0191] This embodiment provides a method for updating environmental information based on an environment layer, including:

[0192] Step 1: Obtain the sensor data of each working device at the current moment and the global probability of each environmental element in the prior environmental information at the current moment.

[0193] Step 2: Initialize the environment state layer containing each environmental element in the prior environment information at the current moment.

[0194] Step 3: Based on the sensor data of the operating equipment at the current moment, obtain the targets detected by each operating equipment and calculate the local probability of each target.

[0195] Step 4: Determine the target type. When the target type is a volume target, determine its local semantic probability. With local behavior probability Predict the environmental state layer to which the target belongs.

[0196] Specific steps are as follows: Figure 7 As shown:

[0197] Step 4.1: Based on the local semantic probability of target O(i, j) Determine the semantic information of target O(i,j). The semantic set corresponding to the digital construction scenario is X.

[0198] Step 4.2: Initialize the semantic set that affects construction tasks in the digital construction scenario. The prior probability that the semantic information of objective O(i,j) affects the execution of the construction task is calculated using the following relation.

[0199]

[0200] Step 4.3: The local behavior probability based on the target O(i, j) is

[0201] If f1(x) = 1, and Greater than a given threshold Right now Then target O(i,j) belongs to the foreground target.

[0202] If f1(x) = 1, and Greater than a given threshold But not exceeding a given threshold Right now Then target O(i,j) belongs to the mid-range target.

[0203] If f1(x) = 0, or Not exceeding a given threshold Right now Then target O(i,j) belongs to the background target.

[0204] Step 5: Based on the calculated local probabilities of each target, calculate the transition probabilities between the target data of each target and each environmental element. Based on the global probabilities of each environmental element in the prior environmental information at the current time and the calculated transition probabilities, update the global probabilities of each environmental element in the prior environmental information at the next time, and complete the environmental information update.

[0205] The local probability of the target data is fused with the global probability of the prior environment elements in a targeted manner. Specifically: the local probability of the foreground local target is fused with the global probability of the foreground prior environment elements; the local probability of the mid-ground local target is fused with the global probability of the mid-ground prior environment elements; and the local probability of the background local target is fused with the global probability of the background prior environment elements.

[0206] Step 6: Based on the global semantic probability and global behavioral probability of the prior environmental elements in the next time step, update the environmental state layer of the prior environmental elements in the next time step.

[0207] Specific steps are as follows: Figure 8 As shown:

[0208] Step 6.1: Based on the local semantic probability P(A) of the target O(i,j), determine the semantic information of the prior environment element E(k), X′={x0∈X|P(x0)≥P(A)), where the semantic set corresponding to the digital construction scenario is X.

[0209] Step 6.2: The semantic set that affects construction tasks in a digital construction scenario is as follows: The prior probability that the semantic information of objective O(i,j) affects the execution of the construction task can be calculated using the following relation.

[0210]

[0211] Step 6.3: The global behavior probability of the prior environmental element E(k) is P(ξ).

[0212] like If P(ξ) is greater than the given threshold P1, i.e. P(ξ) > P1, then the prior environmental element E(k) belongs to the foreground target.

[0213] like And if P(ξ) is greater than the given threshold P00, but does not exceed the given threshold P1, that is, P0<P(ξ)≤P1, then the prior environmental element E(k) belongs to the mid-range target;

[0214] like If P(ξ) does not exceed the given threshold P0, i.e. P(ξ)≤P0, then the prior environmental element E(k) belongs to the background target.

[0215] After attribute fusion is completed, based on the updated global semantic probability and global behavioral probability of the environmental element, it is determined again which environmental state layer it belongs to, and the environmental state layer of the prior environmental element in the next moment is updated.

[0216] like Figure 9 As shown, in this embodiment, the environmental state changes defined by the environmental state layer have the following 13 possible forms:

[0217] (1) The process of random occurrence of the foreground target represented by number 1 in the figure;

[0218] (2) The process of state transition of the foreground target represented by number 2 in the figure within this layer;

[0219] (3) The process of the foreground target represented by number 3 in the figure disappearing;

[0220] (4) The process of the mid-ground target represented by number 4 in the figure being transformed into a foreground target;

[0221] (5) The process by which the foreground target represented by number 5 in the figure degenerates into a midground target;

[0222] (6) The process by which the background target represented by number 6 in the figure is directly transformed into the foreground target;

[0223] (7) The process by which the foreground target represented by number 7 in the figure directly degenerates into the background target;

[0224] (8) The process of random occurrence of the mid-range target represented by number 8 in the figure;

[0225] (9) The process of state transition of the mid-ground target represented by number 9 in the figure within this layer;

[0226] (10) The process of the mid-ground target represented by number 10 in the figure disappearing;

[0227] (11) The process by which the background target represented by number 11 in the figure is transformed into a mid-ground target;

[0228] (12) The process by which the mid-ground target represented by number 12 in the figure degenerates into a background target;

[0229] (13) The background update process represented by number 13 in the figure.

[0230] This embodiment takes into account the relationship between the environment and the operating equipment, and can balance improving the efficiency and stability of the operation process and enhancing the safety of the system.

[0231] Example 3:

[0232] This embodiment provides an environmental information updating device, including:

[0233] Acquisition module: used to acquire the sensor data of each operating device at the current moment and the global probability of each environmental element in the prior environment information at the current moment;

[0234] First calculation module: used to obtain the targets detected by each working device based on the sensor data of the working device at the current time, and calculate the local probability of each target;

[0235] The calculation and update module is used to calculate the transition probability between the target data of each target and each environmental element based on the calculated local probability of each target. Based on the global probability of each environmental element in the prior environmental information at the current time and the calculated transition probability, it updates the global probability of each environmental element in the prior environmental information at the next time and completes the environmental information update.

[0236] Example 4:

[0237] This embodiment provides a computer-readable storage medium storing a computer program / instruction thereon. When the computer program / instruction is executed by a processor, it implements the steps of the environmental information update method described in Embodiment 1 or Embodiment 2.

[0238] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0239] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0240] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0241] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0242] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for updating environmental information, characterized in that, include: Obtain the sensor data of each operating device at the current moment and the global probability of each environmental element in the prior environmental information at the current moment; Based on the sensor data of the operating equipment at the current moment, the targets detected by each operating equipment are obtained, and the local probability of each target is calculated. The step of obtaining each target detected by each working device based on the sensor data of the working devices at the current moment includes: The initial number of working devices is n, and each working device is ,in ; Feature data is obtained by extracting features from the sensor data of the operating equipment at the current moment. Based on Bayes' theorem, the extracted feature data is tracked to obtain the data for each operating device. Detected One goal And the corresponding target data and target status data, among which , The target's state data includes the expected value of the target's state. With uncertainty value ; The local probabilities include local existence probability, local semantic probability, and local behavior probability. The calculation of the local probability of each target includes: According to the goal The state data is used to determine the target type as a point target, area target, or volume target; among which... , ; When the target When the target type is a point target, calculate the target. The probability of local existence; When the target When the type is a surface target, calculate the target. The local existence probability and the local semantic probability; When the target When the type is a volume target, calculate the target. The probability of local existence, the probability of local semantics, and the probability of local behavior; Based on the calculated local probabilities of each target, the transition probabilities between the target data of each target and each environmental element are calculated. Based on the global probabilities of each environmental element in the prior environmental information at the current moment and the calculated transition probabilities, the global probabilities of each environmental element in the prior environmental information at the next moment are updated, thus completing the environmental information update.

2. The environmental information updating method according to claim 1, characterized in that, The computational objective The local existence probability, local semantic probability, and local behavior probability include: Calculation target The probability of local existence includes: According to the goal State data, target state Existence Relationship ,in, The expected value of the target state. The uncertainty value of the target state; Signal-to-noise ratio of target data For about A monotonic function has a relation. ; Based on the goal Local existence probability Signal-to-noise ratio of target data Relationship The target was calculated. Local existence probability ;in For the signal-to-noise ratio of the target data Perform local existence probability calculation; Utilizing deep learning networks to compute the target Local semantic probability ; Calculation target The local behavior probability includes: According to the goal Local semantic probability Determine the target semantic information ,in, A semantic set corresponding to digital construction scenarios; Initialize the semantic set that affects construction tasks in the digital construction scenario as follows: Calculate the target The prior probability that semantic information influences the execution of construction tasks. Calculated using the following formula: ； Initialize device Corresponding construction tasks Calculate the target Construction tasks correlation between ; Based on the goal With equipment Relative pose vectors between ,Target Local existence probability With the goal Construction tasks correlation between Calculate the target For construction tasks The posterior probability of the effect of execution Where F() is used to calculate the posterior probability; Computation possesses semantic information goal For construction tasks Probability of having an impact ; Based on the goal Local semantic probability Sum of probabilities Calculate the target Local behavior probability .

3. The environmental information updating method according to claim 1, characterized in that, The process involves calculating the transition probabilities between target data and environmental elements based on the calculated local probabilities of each target, and updating the global probabilities of environmental elements in the prior environmental information at the next time step based on the global probabilities of each environmental element in the prior environmental information at the current time step and the calculated transition probabilities. This includes: Calculate the state transition probabilities between target data for each objective and each environmental element. Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. and the calculated state transition probabilities The global existence probability of each environmental element in the prior environment information is updated to obtain the next time step. ; Calculate the semantic transfer probability between target data for each objective and each environmental element. Based on the global semantic probabilities of each environmental element in the prior environmental information obtained at the current moment. and the calculated semantic transition probability The global semantic probabilities of each environmental element in the prior environment information for the next time step are updated. ; Calculate the probability of behavioral transition between target data for each objective and each environmental element. Based on the global behavior probabilities of each environmental element in the prior environmental information obtained at the current moment. and the calculated behavior transition probability Update the global behavior probabilities of each environmental element in the prior environment information for the next time step. .

4. The environmental information updating method according to claim 3, characterized in that, The calculation of the state transition probabilities between the target data of each objective and each environmental element... Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. and the calculated state transition probabilities The global existence probability of each environmental element in the prior environment information is updated to obtain the next time step. ,include: Calculation from device Target data With various environmental factors State correlation between State-related gates ,Finish and By associating the state data between them, we can obtain ; Calculation from device Target data With various environmental factors State transition probabilities between ; According to the DS evidence theory, the obtained state transition probabilities To merge, obtain from the device Target data and various environmental factors State transition probabilities between ;in, For fusion computing; According to the DS evidence theory, evidence from different devices The obtained state transition probabilities By merging the data, we can obtain the state transition probabilities between each target from each device and each environmental element at the next moment. ; Based on the global existence probability of each environmental element in the prior environment information obtained at the current moment. And the state transition probabilities between each target and each environmental element from each device at the next moment. Update the environmental elements in the prior environment information for the next time step. global existence probability .

5. The environmental information updating method according to claim 3, characterized in that, The semantic transfer probability between the target data of each objective and each environmental element is calculated. Based on the global semantic probabilities of each environmental element in the prior environmental information obtained at the current moment. and the calculated semantic transition probability The global semantic probabilities of each environmental element in the prior environment information for the next time step are updated. ,include: Calculation from device Target data With various environmental factors Semantic relevance between Based on semantic association gate ,Finish and The semantic relationship between them is obtained ;in, A semantic set of environmental elements. This represents the semantic probability element. For the goal Local semantic probability; Calculation from device Target data With various environmental factors Semantic transition probability between ; According to the DS evidence theory, the obtained semantic transition probability To merge, obtain from the device The semantic transfer probability between target detection results and various environmental elements ;in, For fusion computing; According to the DS evidence theory, the semantic transition probabilities obtained from different devices D(i) are... By fusing the data, we can obtain the semantic transfer probabilities of each target and each environmental element from each device at the next moment. ; Based on the global semantic probabilities of each environmental element in the prior environmental information obtained at the current moment. And the semantic transfer probabilities of each target and each environmental element from each device at the next moment. Update the environmental elements in the prior environment information for the next time step. global semantic probability .

6. The environmental information updating method according to claim 3, characterized in that, The calculation of the behavioral transition probability between target data of each objective and each environmental element. Based on the global behavior probabilities of each environmental element in the prior environmental information obtained at the current moment. and the calculated behavior transition probability Update the global behavior probabilities of each environmental element in the prior environment information for the next time step. ,include: Calculate the different devices Corresponding construction tasks With various environmental factors Behavioral correlation between ; according to computing devices With various environmental factors Probability of behavioral correlation between them in the next moment Where F() is the probability calculation of behavioral association; Based on behavioral association gate The obtained behavioral association probability For specific prior environmental factors For different devices Classify the degree of correlation; In behavioral association level In the middle, calculations come from the device Target data With various environmental factors correlation between Based on state association gate ,Finish and Data correlation between them to obtain ; In behavioral association level In this context, based on the DS evidence theory, the calculation of evidence from the device... Target data With various environmental factors Behavioral transition probability between ;in, For fusion computing; In behavioral association level In China, based on the DS evidence theory, different devices... The obtained behavior transition probability By merging the data, we can obtain the behavior transition probabilities of each target and each environmental element from each device at the next moment. ; According to the DS evidence theory, different levels of correlation between behaviors All devices The obtained behavior transition probability By merging the data, we can obtain the behavior transition probabilities of each target and each environmental element from each device at the next moment. ; Based on the global behavior probabilities of each environmental element in the prior environmental information obtained at the current moment. And the probability of behavior transition between each target and each environmental element from each device at the next moment. Update the environmental elements in the prior environment information for the next time step. global behavior probability .

7. An environmental information updating device, characterized in that, include: Acquisition module: used to acquire the sensor data of each operating device at the current time and the global probability of each environmental element in the prior environment information at the current time; First calculation module: used to obtain the targets detected by each working device based on the sensor data of the working device at the current time, and calculate the local probability of each target; The step of obtaining each target detected by each working device based on the sensor data of the working devices at the current moment includes: The initial number of working devices is n, and each working device is ,in ; Feature data is obtained by extracting features from the sensor data of the operating equipment at the current moment. Based on Bayes' theorem, the extracted feature data is tracked to obtain the data for each operating device. Detected One goal And the corresponding target data and target status data, among which , The target's state data includes the expected value of the target's state. With uncertainty value ; The local probabilities include local existence probability, local semantic probability, and local behavior probability. The calculation of the local probability of each target includes: According to the goal The state data is used to determine the target type as a point target, area target, or volume target; among which... , ; When the target When the target type is a point target, calculate the target. The probability of local existence; When the target When the type is a surface target, calculate the target. The local existence probability and the local semantic probability; When the target When the type is a volume target, calculate the target. The probability of local existence, the probability of local semantics, and the probability of local behavior; The calculation and update module is used to calculate the transition probability between the target data of each target and each environmental element based on the calculated local probability of each target. Based on the global probability of each environmental element in the prior environmental information at the current time and the calculated transition probability, it updates the global probability of each environmental element in the prior environmental information at the next time and completes the environmental information update.

8. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the environmental information update method according to any one of claims 1-6.

Images