WO2020034085A1 - 用于检测信号传播类型的方法和装置 - Google Patents

用于检测信号传播类型的方法和装置 Download PDF

Info

Publication number
WO2020034085A1
WO2020034085A1 PCT/CN2018/100389 CN2018100389W WO2020034085A1 WO 2020034085 A1 WO2020034085 A1 WO 2020034085A1 CN 2018100389 W CN2018100389 W CN 2018100389W WO 2020034085 A1 WO2020034085 A1 WO 2020034085A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
value
signal propagation
base station
impulse response
Prior art date
Application number
PCT/CN2018/100389
Other languages
English (en)
French (fr)
Inventor
曾卓琦
刘史蒂文
王炜
于华俊
Original Assignee
罗伯特·博世有限公司
曾卓琦
刘史蒂文
王炜
于华俊
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 罗伯特·博世有限公司, 曾卓琦, 刘史蒂文, 王炜, 于华俊 filed Critical 罗伯特·博世有限公司
Priority to CN201880096605.1A priority Critical patent/CN112567834B/zh
Priority to PCT/CN2018/100389 priority patent/WO2020034085A1/zh
Priority to EP18930106.2A priority patent/EP3840490A4/en
Priority to US17/268,760 priority patent/US11791911B2/en
Publication of WO2020034085A1 publication Critical patent/WO2020034085A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/20—Monitoring; Testing of receivers
    • H04B17/21—Monitoring; Testing of receivers for calibration; for correcting measurements
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/01—Determining conditions which influence positioning, e.g. radio environment, state of motion or energy consumption
    • G01S5/011—Identifying the radio environment
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0205—Details
    • G01S5/0218—Multipath in signal reception
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0294—Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/20—Monitoring; Testing of receivers
    • H04B17/27—Monitoring; Testing of receivers for locating or positioning the transmitter
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/391—Modelling the propagation channel
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/0218—Very long range radars, e.g. surface wave radar, over-the-horizon or ionospheric propagation systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0205—Details

Definitions

  • the present invention relates to the field of ultra-wideband (UWB) positioning, and in particular, to a method and apparatus for detecting a type of signal propagation, and a computing device and a machine-readable storage medium.
  • UWB ultra-wideband
  • UWB positioning is a technology that uses extremely narrow impulse response and bandwidth above 1GHz to locate objects indoors.
  • the UWB positioning system includes multiple positioning base stations and positioning labels placed on objects to be positioned.
  • the positioning tag sends a pulse signal, which becomes an impulse response when it reaches the positioning base station through channel modulation.
  • the UWB positioning system uses the impulse response received by the positioning base station from the positioning tag to determine the positioning of the object.
  • the UWB positioning system can obtain accurate positioning of the object.
  • the signal transmission between the positioning base station and the positioning label is obstacle blocking Non-line-of-sight propagation, the positioning obtained by the UWB positioning system is usually inaccurate.
  • Embodiments of the present invention provide a method and apparatus for detecting a type of signal propagation, and a computing device and a machine-readable storage medium capable of detecting a type of signal propagation between a positioning base station and a positioning tag of a UWB positioning system.
  • a method for detecting a signal propagation type includes: when a positioning base station of an ultra-wideband positioning system currently receives an impulse response from a positioning tag, at least using the received impulse response To calculate the value of the specified characteristic as the actual value of the specified characteristic of the received impulse response; according to the last type of signal propagation determined between the certain positioning base station and the certain positioning tag,
  • the specified feature selection is a prediction model used to predict the value of the specified feature at a future time based on the value of the specified feature at a future time; by using a historical impulse response from the positioning tag previously received by the positioning base station.
  • the actual value of the specified feature is regarded as the value of the specified feature at the historical time, and the prediction model selected for the specified feature is used to obtain the value of the specified feature at the future time as the result of the received impulse response.
  • the prediction model for the specified feature selection determines a signal propagation type currently between the certain positioning base station and the certain positioning label.
  • An apparatus for detecting a signal propagation type includes a calculation module configured to: when a positioning base station of an ultra-wideband positioning system currently receives an impulse response from a positioning tag, use at least The received impulse response is used to calculate the value of the specified feature as the actual value of the specified feature of the received impulse response; a selection module is configured to, according to the last determination, between the certain positioning base station and the certain positioning A type of signal propagation between tags, selecting a prediction model for the specified feature to predict the value of the specified feature at a future time based on the value of the specified feature at a historical time; an acquisition module configured to The actual value of the specified feature of the historical impulse response received from the positioning tag by the base station before is regarded as the value of the specified feature at the historical moment, and the prediction feature selected for the specified feature is used to obtain the specified feature.
  • a determining module is configured to: Determine the type of signal propagation currently between the certain positioning base station and the certain positioning tag based on the actual and predicted values of the specified feature of the received impulse response and the prediction model selected for the specified feature .
  • a computing device includes: a processor; and a memory that stores executable instructions that, when executed, cause the processor to perform the foregoing method.
  • a machine-readable storage medium has executable instructions thereon, and when the executable instructions are executed, the machine is caused to execute the foregoing method.
  • the solution of the embodiment of the present invention when the impulse response currently received by the positioning base station of the UWB positioning system from the positioning tag, at least the received impulse response is used to calculate the actual value of the specified characteristic of the received impulse response, and a prediction model is used to Obtain the predicted values of the specified characteristics of the received impulse response, and use the actual and predicted values of the specified characteristics of the received impulse response and the prediction model used to determine the current between the positioning base station and the positioning tag Therefore, the solution of the embodiment of the present invention can detect a signal propagation type between a positioning base station and a positioning label of a UWB positioning system.
  • FIG. 1 shows an overall flowchart of a method for training a prediction model according to an embodiment of the present invention
  • FIG. 2 shows an overall flowchart of a method for detecting a signal propagation type according to an embodiment of the present invention
  • FIG. 3 shows a flowchart of a method for detecting a signal propagation type according to an embodiment of the present invention
  • FIG. 4 shows a schematic diagram of an apparatus for detecting a type of signal propagation according to an embodiment of the present invention.
  • FIG. 5 shows a schematic diagram of a computing device according to one embodiment of the invention.
  • FIG. 1 shows an overall flowchart of a method for creating a prediction model according to an embodiment of the present invention.
  • the method 100 shown in FIG. 1 may be implemented by any computing device having computing capabilities.
  • the computing device may be, but is not limited to, a desktop computer, a notebook computer, a tablet computer, a server, or a smart phone.
  • the four impulse response sets collected include a first impulse response set C1, a second impulse response set C2, a third impulse response set C3, and a fourth impulse response set C4.
  • the first impulse response set C1 is collected when the signal propagation of the UWB positioning system is changed from line-of-sight propagation to line-of-sight propagation.
  • the second impulse response set C2 is collected when the signal propagation of the UWB positioning system is changed from line-of-sight propagation to non-line-of-sight propagation.
  • the third impulse response set C3 is collected when the signal propagation of the UWB positioning system is changed from non-line-of-sight propagation to non-line-of-sight propagation.
  • the fourth impulse response set C4 is collected when the signal propagation of the UWB positioning system is changed from non-line-of-sight propagation to line-of-sight propagation.
  • the first impulse response set C1 includes a plurality of impulse response groups.
  • Each impulse response group in the first impulse response set C1 includes a plurality of first impulse responses and a second impulse response, where the plurality of first impulse responses are located on a certain occasion (such as, but not limited to, school,
  • the signal transmission between a positioning base station and a positioning tag of the UWB positioning system in an airport, train station, parking lot, shopping mall, theater, or movie theater, etc.) is received by the positioning base station in the case of line-of-sight propagation.
  • the impulse response from the certain positioning tag, and the second impulse response is after the signal propagation between the certain positioning base station and the certain positioning tag is transformed into line-of-sight propagation and the Impulse response of a positioning tag.
  • the second impulse response set C2 includes a plurality of impulse response groups. Each impulse response group in the second impulse response set C2 includes a plurality of first impulse responses and a second impulse response, wherein the plurality of first impulse responses is a certain UWB positioning system located in a certain occasion.
  • the signal propagation between the positioning base station and a certain positioning tag is the line-of-sight propagation.
  • the second impulse response is at the certain positioning base station.
  • the signal propagation with the certain positioning tag is transformed into an impulse response received by the certain positioning base station from the certain positioning tag after non-line-of-sight propagation.
  • the third impulse response set C3 includes a plurality of impulse response groups.
  • Each impulse response group in the third impulse response set C3 includes a plurality of first impulse responses and a second impulse response, wherein the plurality of first impulse responses are a certain UWB positioning system located in a certain occasion.
  • the signal propagation between the positioning base station and a certain positioning tag is non-line-of-sight propagation
  • the impulse response received by the certain positioning base station from the certain positioning tag has been received
  • the second impulse response is at the certain positioning base station.
  • the signal propagation with the certain positioning tag is transformed into an impulse response received by the certain positioning base station from the certain positioning tag after non-line-of-sight propagation.
  • the fourth impulse response set C4 includes a plurality of impulse response groups.
  • Each impulse response group in the fourth impulse response set C4 includes a plurality of first impulse responses and a second impulse response, wherein the plurality of first impulse responses is a certain UWB positioning system located in a certain occasion.
  • the signal propagation between the positioning base station and a certain positioning tag is non-line-of-sight propagation
  • the impulse response received by the certain positioning base station from the certain positioning tag has been received
  • the second impulse response is at the certain positioning base station.
  • the signal propagation with the certain positioning tag is transformed into an impulse response received by the certain positioning base station from the certain positioning tag after line-of-sight propagation.
  • the value of a single specified feature SF of each of the four impulse response sets is calculated.
  • the designated feature SF may be a feature whose value can be calculated using only one impulse response.
  • Such characteristics may be, for example, but not limited to, the distance between the positioning base station and the positioning tag, the received signal energy, the maximum amplitude, the maximum amplitude rise time, the standard deviation, the power difference between the first path and the strongest path, the first The power ratio of the path to the strongest path, the signal-to-noise ratio (SNR), the form factor, the peak delay from the start of the received pulse, the average excess delay, the mean square delay spread, the kurtosis, the crest factor, the peak-to-average power ratio, or , Skewness, etc.
  • SNR signal-to-noise ratio
  • the designated feature SF may also be a feature whose value requires multiple impulse responses to be calculated.
  • Such characteristics can be, for example, but not limited to, Euclidean distance, dynamic time warping (DTW), longest common subsequence, edit distance, Chebyshev distance, Manhattan distance, Hausdorff distance, spinner distance, one-way Distance, cosine similarity, locality between polylines, or similarity of clue perception trajectories.
  • the specified feature SF is a feature whose value needs to be calculated using multiple impulse responses
  • the value of the specified feature SF of any of the four impulse response sets uses the position of the any impulse response. The impulse responses in that impulse response group that were received before the any impulse response and the any impulse response are calculated.
  • the specified feature SF is Euclidean distance
  • the impulse response Tk is located in the impulse response group T
  • the impulse responses received before the impulse response Tk in the impulse response group T are the impulse responses Tc, Te, and Tf
  • the value of the Euclidean distance of the impulse response Tk is equal to the average of the Euclidean distance between the impulse responses Tk and Tc, the Euclidean distance between the impulse responses Tk and Te, and the Euclidean distance between the impulse responses Tk and Tf.
  • the four sets of impulse responses are used to train four prediction models M1-M4.
  • each impulse response group included in the first impulse response set C1 is used to train to obtain a prediction model M1, which is used to predict the value of the specified feature SF at a single future time based on the value of the specified feature SF at the historical time.
  • the prediction model M1 For each impulse response group C1-i in the first impulse response set C1, the values of the specified characteristics SF of those first impulse responses included in the impulse response group C1-i are regarded as the specified characteristics.
  • the value of SF at the historical moment, and the value of the designated feature SF of the second impulse response included in the impulse response group C1-i is regarded as the value of the designated feature SF at a single future moment.
  • the first impulse response and the second impulse response included in each impulse response group C1-i in the first impulse response set C1 are signal propagation between the positioning base station and the positioning tag, respectively, line-of-sight propagation and positioning base station and The signal propagation between the positioning tags is collected in the case of line-of-sight propagation. Therefore, the signal propagation change applicable to the prediction of the prediction model M1 is that the signal propagation between the positioning base station and the positioning tag is the line-of-sight propagation before the transformation. Line-of-sight propagation after transformation.
  • Each impulse response group included in the second impulse response set C2 is used to train to obtain a prediction model M2, which is used to predict the value of the specified feature SF at a single future time based on the value of the specified feature SF at the historical time.
  • the prediction model M2 For each impulse response group C2-i in the second impulse response set C2, the values of the specified characteristics SF of those first impulse responses included in the impulse response group C2-i are regarded as the specified characteristics.
  • the value of SF at the historical moment, and the value of the designated feature SF of the second impulse response included in the impulse response group C2-i is regarded as the value of the designated feature SF at a single future moment.
  • the signal propagation change applicable to the prediction of the prediction model M2 is that the signal propagation between the positioning base station and the positioning tag is the line-of-sight propagation before the transformation and the Non-line-of-sight propagation after transformation.
  • Each impulse response group included in the third impulse response set C3 is used to train to obtain a prediction model M3, which is used to predict the value of the specified feature SF at a single future time based on the value of the specified feature SF at the historical time.
  • the prediction model M3 For each impulse response group C3-i in the third impulse response set C3, the values of the specified characteristics SF of those first impulse responses included in the impulse response group C3-i are regarded as the specified characteristics.
  • the value of SF at the historical moment, and the value of the designated characteristic SF of the second impulse response included in the impulse response group C3-i is regarded as the value of the designated characteristic SF at a single future moment.
  • the signal propagation change applicable to the prediction of the prediction model M3 is that the signal propagation between the positioning base station and the positioning tag is non-line-of-sight propagation and Non-line-of-sight propagation after transformation.
  • Each impulse response group included in the fourth impulse response set C4 is used to train to obtain a prediction model M4, which is used to predict the value of the specified feature SF at a single future time based on the value of the specified feature SF at the historical time.
  • the prediction model M4 for each impulse response group C4-i in the fourth impulse response set C4, the values of the specified characteristics SF of those first impulse responses included in the impulse response group C4-i are regarded as the specified characteristics.
  • the value of SF at the historical time, and the value of the specified characteristic SF of the second impulse response included in the impulse response group C4-i is regarded as the value of the specified characteristic SF at a single future time.
  • the signal propagation change applicable to the prediction of the prediction model M4 is that the signal propagation between the positioning base station and the positioning tag is non-line-of-sight propagation and After the transformation is the line-of-sight propagation.
  • the prediction models M1-M4 may be implemented using any suitable prediction algorithm.
  • the prediction algorithm used may be, but not limited to, a time series analysis method (for example, a moving average method, or an autoregressive moving average method, etc.), machine learning Algorithm or fitting algorithm, etc.
  • FIG. 2 shows an overall flowchart of a method for detecting a signal propagation type according to a first embodiment of the present invention.
  • the method 200 shown in FIG. 2 may be implemented by any computing device having computing capabilities.
  • the computing device may be, but is not limited to, a desktop computer, a notebook computer, a tablet computer, a server, or a smart phone.
  • a positioning base station BSi in a UWB positioning system currently receives an impulse response Pn from a certain positioning tag TGj, at least the impulse response Pn is used to calculate the value of the designated feature SF. , As the actual value of the specified characteristic SF of the impulse response Pn.
  • the designated feature SF can be either a feature whose value can be calculated using only one impulse response, or a feature whose value can be calculated using multiple impulse responses.
  • the value of the designated feature SF is calculated using only the impulse response Pn. If the designated feature SF is a feature whose value requires multiple impulse responses to be calculated, then the impulse response Pn and one or more received from the positioning tag TGj before the positioning base station BSi (ie, before receiving the designated feature SF) are used. For multiple impulse responses, the value of the specified characteristic SF is calculated.
  • the signal propagation between the positioning base station and the positioning tag is selected in the signal propagation change scenario applicable to its prediction. Between the same types of signal propagation prediction models.
  • the prediction model M1 or M2 is selected because the positioning is in the situation of signal propagation changes applicable to the prediction of the prediction models M1 and M2
  • the signal propagation between the base station and the positioning tag is line-of-sight propagation before transformation.
  • the prediction model M3 or M4 is selected because the positioning base station and The signal propagation between the positioning tags is non-line-of-sight propagation before transformation.
  • the actual values of the specified characteristics SF of the respective historical impulse responses HP are regarded as the values of the specified characteristics SF at the historical time, and input to the prediction model selected in block 206 to obtain the specified characteristics SF in a single future. Value of time.
  • the value of the specified feature SF obtained at block 214 at a single future time is used as the predicted value of the specified feature SF of the impulse response Pn.
  • a first judgment result is obtained, which indicates whether the difference between the actual value and the predicted value of the specified characteristic SF of the impulse response Pn is less than a specified threshold.
  • a second judgment result is obtained, which indicates whether the signal propagation transformation case applicable to the prediction of the prediction model selected in block 206 is that the signal propagation between the positioning base station and the positioning label is both before and after transformation.
  • a specific signal propagation type where the specific signal propagation type is a signal propagation type between the positioning base station BSi and the positioning tag TGj determined last time.
  • a signal propagation type currently between the positioning base station BSi and the positioning tag TGj is determined.
  • the type of signal propagation currently between the positioning base station BSi and the positioning tag TGj is the Specific signal propagation types.
  • the specific signal propagation type is another signal propagation type.
  • the solution of this embodiment can detect the signal propagation type between the positioning base station and the positioning label of the UWB positioning system.
  • a single impulse response Pn currently received by the positioning base station BSi from the positioning tag TGj is used when detecting the type of signal propagation currently between the positioning base station BSi and the positioning tag TGj.
  • the single designated feature SF is not limited to this.
  • a single impulse response from the positioning tag TGj currently received by the positioning base station BSi may be used to specify multiple Pn. Feature MSF.
  • the multiple specified characteristics MSF Each of the specified features MSFi is the same as the specified feature SF, which can be a feature whose value can be calculated using only one impulse response, or a feature whose value can be calculated by using multiple impulse responses.
  • the specified feature SF four prediction models are trained for each specified feature MSFi. Each prediction model is used to predict the value of the specified feature MSFi at a single future moment based on the value of the specified feature MSFi at the historical time.
  • the signal propagation changes applicable to the prediction of a prediction model are one of the following four scenarios: the signal propagation between the positioning base station and the positioning tag is line-of-sight propagation before the transformation and the line-of-sight propagation after the transformation, and the positioning base station and the positioning tag The signal propagation between them is line-of-sight propagation before transformation and non-line-of-sight propagation after transformation.
  • the signal propagation between the positioning base station and the positioning tag is non-line-of-sight propagation before transformation and non-line-of-sight propagation after transformation.
  • the signal propagation between the positioning base station and the positioning tag is non-line-of-sight propagation before transformation and line-of-sight propagation after transformation.
  • the positioning base station BSi When the positioning base station BSi currently receives a single impulse response Pn from the positioning tag TGj, similar to that described in block 202, the respective actual values of the multiple specified characteristics MSF of the impulse response Pn are calculated based on at least the impulse response Pn. Then, for each of the plurality of designated characteristic MSFs, the designated characteristic MSFi is selected, and the signal propagation between the positioning base station and the positioning tag is selected before the transformation, and the last determined positioning base station BSi and The prediction model of the same signal propagation type between the positioning tags TGj. Next, as in blocks 210-218, the respective predicted values of the plurality of specified characteristics MSF of the impulse response Pn are obtained.
  • the respective first judgment results of the plurality of designated features MSF are obtained, and the first judgment result of each designated feature MSFi indicates whether the difference between the actual value and the predicted value of the designated feature MSFi of the impulse response Pn is less than a designated threshold.
  • Acquire respective second judgment results of the plurality of specified features MSF, and the second judgment results of each specified feature MSFi indicate whether the signal propagation change applicable to the prediction of the prediction model selected for the specified feature MSFi is between the positioning base station and the positioning tag
  • the signal propagation before and after the transformation are both specific signal propagation types.
  • the specific signal propagation type is the signal propagation type between the positioning base station BSi and the positioning tag TGj determined last time.
  • each candidate signal propagation type indicates a currently-located base station determined based on a first judgment result and a second judgment result of one of the plurality of specified characteristics MSF of the impulse response Pn.
  • Type of signal propagation between BSi and positioning tag TGj is used to determine the signal propagation type currently between the positioning base station BSi and the positioning tag TGj.
  • the current positioning base station BSi and positioning tags The type of signal propagation between TGj is determined as the certain signal propagation.
  • the first to fourth pulses are used in the case of detecting the type of signal propagation currently between the positioning base station BSi and the positioning tag TGj by using a plurality of impulse responses MPn currently received from the positioning tag TGj by the positioning base station BSi.
  • Each impulse response group in the response set C1-C4 includes a plurality of second impulse responses, and when the prediction model is trained, the number of the second impulse responses included in each impulse response group in each impulse response set is
  • the value of the specified feature SF is regarded as the value of the specified feature SF at multiple future times, so that each of the prediction models M1-M4 obtained by the training is used to predict based on the value of the specified feature SF at the historical time. Specify the value of feature SF at multiple future moments.
  • the impulse response MPn- is calculated based on at least each of the plurality of impulse responses MPn-i of the plurality of impulse responses MPn-i.
  • the actual value of the designated characteristic SF of i to obtain the actual value of the designated characteristic SF of each of the plurality of impulse responses MPn.
  • the actual values of the specified characteristics SF of the respective historical impulse responses HP from the positioning tag TGj previously received by the positioning base station BSi are taken as the values of the specified characteristics SF at the historical time, and input to the prediction model selected in block 206.
  • the values of the specified feature SF at multiple future times are obtained as the predicted values of the specified feature SF of the multiple impulse responses MPn.
  • the plurality of impulse responses MPn include three impulse responses MP1, MP2, and MP3 received in sequence, and that the value V1 of the designated feature SF at the first future moment is obtained using a prediction model, and the designated feature SF is at the second future.
  • the predicted value of the designated feature SF of MP3 is V3.
  • each first indication value of the plurality of impulse responses MPn is obtained, and the first indication value of each impulse response MPn-i represents a difference between an actual value and a predicted value of a specified characteristic SF of the impulse response MPn-i.
  • a second instruction value is calculated based on the first instruction values of the plurality of impulse responses MPn. For example, an average value of the absolute values of the first instruction values of the plurality of impulse responses MPn may be calculated as the second instruction value. As another example, a root mean square value of a first indication value of the plurality of impulse responses MPn may be calculated as the second indication value.
  • a first judgment result is obtained, which indicates whether the second instruction value is less than a specified threshold.
  • a second judgment result is obtained, which is shown as whether the signal propagation change applicable to the prediction of the prediction model selected by the specified feature SF is the signal propagation between the positioning base station and the positioning label before and after the transformation are both specific signal propagation types.
  • the specific signal propagation type is the signal propagation type between the positioning base station BSi and the positioning tag TGj determined last time. Finally, based on the first judgment result and the second judgment result, a signal propagation type currently between the positioning base station BSi and the positioning tag TGj is determined.
  • the propagation type is the signal propagation type between the positioning base station BSi and the positioning tag TGj determined last time.
  • the propagation type is another signal propagation type that is different from the signal propagation type between the positioning base station BSi and the positioning tag TGj determined last time.
  • Each of the plurality of specified features FSF trains four prediction models, and each prediction model trained for the specified feature FSFi is used to predict the specified feature FSFi at multiple future moments based on the value of the specified feature FSFi at the historical time.
  • the signal propagation change applicable to the prediction of each prediction model trained for the specified feature FSFi is one of the following four cases: the signal propagation between the positioning base station and the positioning label is the line-of-sight propagation and Line-of-sight propagation after transformation, signal propagation between the positioning base station and positioning tag is line-of-sight propagation before transformation and non-line-of-sight propagation after transformation, and signal propagation between positioning base station and positioning tag is non-transmission before transformation Line-of-sight propagation and non-line-of-sight propagation after transformation, and signal propagation between the positioning base station and the positioning tag are non-line-of-sight before transformation After propagation and spread converted horizon.
  • the impulse response PMP- is calculated based on at least each of the multiple impulse responses PMP-i in the multiple impulse response PMP- respective actual values of the plurality of specified characteristics FSF of i to obtain respective actual values of the plurality of specified characteristics FSF of each of the plurality of impulse responses PMP-PMP-i. Then, a prediction model is selected for each specified feature FSFi of the plurality of specified features FSF, in which the signal propagation between the positioning base station and the positioning tag is transformed in a signal propagation change situation where prediction of the selected prediction model is applicable.
  • the type of signal propagation between the previously determined positioning base station BSi and the positioning tag TGj is the same.
  • the actual value of each specified feature FSFi of each of the historical impulse responses HP received by the positioning base station BSi from the positioning tag TGj is regarded as the value of the specified feature FSFi at the historical moment, and input to the prediction selected for the specified feature FSFi
  • the model obtains the values of the specified feature FSFi at multiple future moments as the predicted values of the specified feature FSFi of the multiple impulse response PMPs.
  • each first indication value of the plurality of specified characteristics FSF of each of the plurality of impulse responses PMP-PMP-i is obtained, wherein each first indication value of each of the specified characteristics FMP of the impulse response PMP-i Represents the difference between the actual and predicted values of the specified characteristic FSFi of the impulse response PMP-i.
  • the second instruction value of each of the plurality of specified features FSF is obtained, wherein the second instruction value of each of the specified features FSFi is calculated based on the first instruction value of the specified feature FSFi of the plurality of impulse responses PMP. For example, an average value of the absolute values of the first indication values of the specified characteristic FSFi of the plurality of impulse responses PMP may be calculated as the second indication value of the specified characteristic FSFi.
  • the root mean square value of the first indication value of the specified characteristic FSFi of the plurality of impulse responses PMP may be calculated as the second indication value of the specified characteristic FSFi. Then, a first judgment result of each of the plurality of designated features FSF is obtained, wherein the first judgment result of each designated feature FSFi indicates whether the second indication value of the designated feature FSFi is less than a designated threshold.
  • a second judgment result of each of the plurality of specified features FSF is obtained, wherein the second judgment result of each specified feature FSFi indicates whether the signal propagation change applicable to the prediction of the prediction model selected for the specified feature FSFi is a positioning base station and a positioning tag
  • the signal propagation between them is a specific signal propagation type before and after the transformation, and the specific signal propagation type is the signal propagation type between the positioning base station BSi and the positioning tag TGj determined last time.
  • a plurality of candidate signal propagation types are obtained, where each candidate signal propagation type indicates a currently-located base station BSi that is determined based on a first judgment result and a second judgment result of one of the plurality of specified feature FSFj.
  • a signal propagation type currently between the positioning base station BSi and the positioning tag TGj is determined. For example, but not limited to, assuming that more than half of the candidate signal propagation types in the multiple candidate signal propagation types belong to a specific signal propagation (line-of-sight propagation or non-line-of-sight propagation), the current positioning base station BSi and positioning tags The type of signal propagation between TGj is determined to be a certain specific signal propagation.
  • the present invention is not limited to this. In some other embodiments of the present invention, only two prediction models may be trained for each specified feature, wherein the signal propagation changes applicable to the prediction of one of the two prediction models are applicable to the following two cases: 1: The signal propagation between the positioning base station and the positioning tag is line-of-sight propagation before the transformation and the line-of-sight propagation after the transformation, and the signal propagation between the positioning base station and the positioning tag is the line-of-sight propagation before the transformation and the transformation.
  • the signal propagation change applicable to the prediction of the other prediction model of the two prediction models is one of the following two cases: the signal propagation between the positioning base station and the positioning label is non-line-of-sight before the transformation Distance propagation and non-line-of-sight propagation after transformation, and signal propagation between the positioning base station and the positioning tag are non-line-of-sight propagation before transformation and line-of-sight propagation after transformation.
  • FIG. 3 shows a flowchart of a method for detecting a signal propagation type according to an embodiment of the present invention.
  • the method 300 shown in FIG. 3 may be implemented by any computing device having computing capabilities.
  • the method 300 may include, at block 302, when a positioning base station of an ultra-wideband positioning system currently receives an impulse response from a positioning tag, at least the received impulse response is used to calculate a specified feature. As the actual value of the specified characteristic of the received impulse response.
  • the method 300 may further include, in block 304, selecting, for the specified feature for use based on the specified feature, based on a signal propagation type determined between the certain positioning base station and the certain positioning tag last time.
  • a prediction model that uses values at historical times to predict values at future times.
  • the method 300 may further include, at block 306, by treating the actual value of the specified feature of the historical impulse response received from the certain positioning tag previously received by the certain positioning base station as the historical time of the specified feature.
  • the value of is the prediction value selected for the specified feature to obtain the value of the specified feature at a future time as the predicted value of the specified feature of the received impulse response.
  • the method 300 may further include, in block 308, determining, based on the actual and predicted values of the specified feature of the received impulse response and the prediction model selected for the specified feature, currently determining the Describe the type of signal propagation between a certain positioning tag.
  • the specified characteristic includes only a single characteristic
  • the received impulse response includes only a single impulse response
  • block 308 includes: obtaining a first judgment result indicating an all-impulse response of the single impulse response. Whether the difference between the actual value and the predicted value of the single feature is less than a specified threshold; obtaining a second judgment result indicating whether the signal propagation change applicable to the prediction of the prediction model selected for the single feature is between the positioning base station and the positioning tag Of the signal propagation before and after the transformation are signal propagation types determined between the certain positioning base station and the certain positioning tag last time; and based on the first judgment result and the second judgment As a result, a signal propagation type currently between the certain positioning base station and the certain positioning tag is determined.
  • the specified feature includes a plurality of specific features
  • the received impulse response includes only a single impulse response
  • the selected prediction model includes a plurality of prediction models
  • each prediction model is for the plurality of specific characteristics
  • a specific feature of one of the features is selected and used to predict the value of a specific future feature at a single future moment based on the value of one of the specific features at a historical moment
  • block 308 includes: A first judgment result, wherein the first judgment result of each specific feature indicates whether a difference between an actual value and a predicted value of the specific feature of the single impulse response is less than a specified threshold; obtaining a second of each of the plurality of specific features A judgment result, wherein the second judgment result of each specific feature indicates whether the signal propagation change applicable to the prediction of the prediction model selected for the specific feature is the signal propagation between the positioning base station and the positioning label before and after transformation Is the signal propagation type between the certain positioning base station and the certain positioning label determined last time Obtaining a plurality of candidate signal propagation types, wherein each
  • the specified feature includes only a single feature
  • the received impulse response includes multiple impulse responses
  • a prediction model selected for the single feature is used to predict based on a value of the single feature at a historical moment Its value is taken at multiple future moments
  • block 306 includes: treating the actual value of the single feature of the historical impulse response from the certain positioning tag previously received by the certain positioning base station as the single The value of the feature at the historical moment, using the prediction model selected for the single feature to obtain the value of the single feature at multiple future times, as the predicted value of the single feature of the multiple impulse responses
  • Block 308 includes: obtaining respective first indication values of the plurality of impulse responses, wherein the first indication value of each impulse response represents a difference between an actual value and a predicted value of the single characteristic of the impulse response; obtaining A second indication value, which is calculated based on the first indication values of the plurality of impulse responses; obtaining a first judgment result, which indicates whether the second indication value is less than Threshold value; obtaining a second judgment result, which
  • the specified characteristic includes a plurality of specific characteristics
  • the received impulse response includes a plurality of impulse responses
  • the selected prediction model includes a plurality of prediction models
  • each prediction model is for the plurality of specific characteristics
  • a specific feature of one of the features is selected and used to predict its value at multiple future moments based on the value of the one of the particular features at historical times.
  • Block 306 includes: The actual value of any one of the plurality of specific features from the historical impulse response of the certain positioning label is regarded as the value of the any particular feature at the historical moment, and is used as the value of the any particular feature A feature selection prediction model to obtain the value of the any particular feature at multiple future moments as the predicted value of the any particular feature of the plurality of impulse responses, and block 308 includes: obtaining the A first indication value of each of the plurality of specific characteristics of any one of the plurality of impulse responses, wherein An indication value indicates a difference between an actual value and a predicted value of the specific characteristic of any one of the impulse responses; obtaining a respective second instruction value of the plurality of specific characteristics, wherein the second instruction value of each specific characteristic is based on The plurality of pulses are calculated in response to respective first indication values of the specific feature; a respective first judgment result of the plurality of specific features is obtained, and the first judgment result of each specific feature indicates a second indication of the specific feature Whether the value is less than a specified threshold; and obtaining a
  • FIG. 4 shows a schematic diagram of an apparatus for detecting a type of signal propagation according to an embodiment of the present invention.
  • the apparatus 400 shown in FIG. 4 may be implemented by using software, hardware, or a combination of software and hardware.
  • the apparatus 400 shown in FIG. 4 may be installed in any computing device having computing capabilities, for example.
  • the apparatus 400 may include a calculation module 402, a selection module 404, an acquisition module 406, and a determination module 408.
  • the calculation module 402 is configured to calculate a value of a specified feature by using at least the received impulse response when a certain positioning base station of the ultra-wideband positioning system currently receives an impulse response from a certain positioning tag, and use it as a factor of the received impulse response. The actual value of the specified feature is described.
  • the selection module 404 is configured to select, for the specified feature, a value based on the specified feature at a historical time based on a signal propagation type determined between the certain positioning base station and the certain positioning tag last time. A prediction model to predict its value in the future.
  • the obtaining module 406 is configured to consider the actual value of the specified feature of the historical impulse response received from the certain positioning tag previously received by the certain positioning base station as the value of the specified feature at the historical moment, and use as The prediction model of the specified feature selection obtains a value of the specified feature at a future time, as the predicted value of the specified feature of the received impulse response.
  • the determining module 408 is configured to determine a current location between the certain positioning base station and the certain positioning tag based on the actual value and predicted value of the specified feature of the received impulse response and the prediction model selected for the specified feature. The type of signal transmission.
  • the specified characteristic includes only a single characteristic
  • the received impulse response includes only a single impulse response
  • the determination module 408 includes: for obtaining a first judgment result, which indicates the single impulse response
  • the signal propagation between the base station and the positioning tag is a module that determines the type of signal propagation between the certain positioning base station and the certain positioning tag before and after the transformation; and is based on the module
  • the first determination result and the second determination result determine a module of a signal propagation type currently between the certain positioning base station and the certain positioning label.
  • the specified feature includes a plurality of specific features
  • the received impulse response includes only a single impulse response
  • the selected prediction model includes a plurality of prediction models
  • each prediction model is for the plurality of specific characteristics
  • One of the specific features of the feature is selected and used to predict the value of a specific future moment based on the value of the one of the specific features at the historical moment
  • the determining module 408 includes: acquiring the multiple specific features A module of a respective first judgment result, wherein the first judgment result of each specific feature indicates whether a difference between an actual value and a predicted value of the specific feature of the single impulse response is less than a specified threshold; A module of a respective second judgment result of a specific feature, wherein the second judgment result of each specific feature indicates whether a signal propagation change applicable to prediction of a prediction model selected for the specific feature is a signal between a positioning base station and a positioning tag The propagation is determined before the transformation and after the transformation.
  • Signal propagation type between bit tags a module for obtaining multiple candidate signal propagation types, wherein each candidate signal propagation type indicates a first judgment result and a second judgment result based on one of the plurality of specific features
  • a signal propagation type currently determined between the certain positioning base station and the certain positioning label determined by the judgment result and used to determine, based on the plurality of candidate signal propagation types, the current location between the positioning base station and the The module describing the type of signal propagation between positioning tags.
  • the specified feature includes only a single feature
  • the received impulse response includes multiple impulse responses
  • a prediction model selected for the single feature is used to predict based on a value of the single feature at a historical moment Its value is taken at multiple future moments
  • the obtaining module 404 is further configured to: by considering the actual value of the single feature of the historical impulse response received from the certain positioning tag previously received by the certain positioning base station as The value of the single feature at the historical time is used, and the prediction model selected for the single feature is used to obtain the value of the single feature at multiple future times as the predicted value of the single feature of the multiple impulse responses
  • the determining module 408 includes: a module for obtaining respective first indication values of the plurality of impulse responses, wherein the first indication value of each impulse response represents an actual value of the single characteristic of the impulse response and Difference between predicted values; a module for obtaining a second indication value, the second indication value being calculated based on the first indication values of the plurality of impulse responses; A module for obtaining a first judgment result, where
  • the specified characteristic includes a plurality of specific characteristics
  • the received impulse response includes a plurality of impulse responses
  • the selected prediction model includes a plurality of prediction models
  • each prediction model is for the plurality of specific characteristics
  • One of the specific features of the feature is selected and used to predict the value of one of the specific features at multiple future moments based on the value of the particular feature at the historical moment.
  • the obtaining module 404 is further configured to: The actual value of any specific feature among the plurality of specific features that was previously received from the historical impulse response of the certain positioning tag is regarded as the value of any specific feature at the historical moment, and is used as the A specific feature selection prediction model is used to obtain the value of the specific feature at multiple future times as the predicted value of the specific feature of the multiple impulse responses, and the determining module 408 includes: A module for obtaining a first indication value of each of the plurality of specific characteristics of any one of the plurality of impulse responses, wherein the any of the impulse responses A first indication value of each specific characteristic of the response represents a difference between an actual value and a predicted value of the specific characteristic of the any impulse response; a module for obtaining a respective second indication value of the plurality of specific characteristics, wherein , The second indication value of each specific feature is calculated based on the first indication value of the specific feature of each of the plurality of impulse responses; a module for obtaining the respective first judgment results of the plurality of specific features, each A first judgment result of
  • FIG. 5 shows a schematic diagram of a computing device according to one embodiment of the invention.
  • the computing device 500 may include a processor 502 and a memory 504.
  • the memory 504 stores executable instructions that, when executed, cause the processor 502 to execute the foregoing method.
  • An embodiment of the present invention also provides a machine-readable storage medium having executable instructions thereon, and when the executable instructions are executed, the machine is caused to execute the foregoing method.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Electromagnetism (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本发明涉及一种用于检测信号传播类型的方法和装置，该方法包括：当超宽带定位系统的定位基站当前接收到来自定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算所接收的脉冲响应的指定特征的实际值；为指定特征选择用于基于指定特征在历史时刻的取值来预测其在未来时刻的取值的预测模型；利用为指定特征选择的预测模型来获取指定特征在未来时刻的取值，作为所接收的脉冲响应的指定特征的预测值；基于所接收的脉冲响应的指定特征的实际值和预测值以及为指定特征选择的预测模型，确定当前在定位基站与定位标签之间的信号传播类型。利用该方法和装置，能够检测UWB定位系统的定位基站与定位标签之间的信号传播类型。

Description

用于检测信号传播类型的方法和装置 技术领域
本发明涉及超宽带(UWB)定位领域，尤其涉及用于检测信号传播类型的方法和装置以及计算设备和机器可读存储介质。
背景技术
UWB定位是一种利用极窄的脉冲响应和1GHz以上带宽在室内对物体进行定位的技术。UWB定位系统包括多个定位基站和放置在要定位的对象上的定位标签。定位标签发送脉冲信号，该脉冲信号经过信道调制到达定位基站时变成脉冲响应。UWB定位系统利用定位基站接收的来自定位标签的脉冲响应来确定对象的定位。
当定位基站与定位标签之间的信号传播是没有障碍物阻挡的视距传播时，UWB定位系统可以获得对象的准确定位，然而，如果定位基站与定位标签之间的信号传播是有障碍物阻挡的非视距传播，那么UWB定位系统获得的定位通常是不准确的。
因此，在UWB定位中，识别定位基站与定位标签之间的信号传播类型是非常重要的。
发明内容
本发明的实施例提供用于检测信号传播类型的方法和装置以及计算设备和机器可读存储介质，其能够检测UWB定位系统的定位基站与定位标签之间的信号传播类型。
按照本发明的实施例的一种用于检测信号传播类型的方法，包括：当超宽带定位系统的某一定位基站当前接收到来自某一定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算指定特征的值，作为所接收的脉冲响应的所述指定特征的实际值；根据上一次确定的在 所述某一定位基站与所述某一定位标签之间的信号传播类型，为所述指定特征选择用于基于所述指定特征在历史时刻的取值来预测其在未来时刻的取值的预测模型；通过将所述定位基站以前接收的来自所述定位标签的历史脉冲响应的所述指定特征的实际值视为所述指定特征在历史时刻的取值，利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值，作为所接收的脉冲响应的所述指定特征的预测值；以及，基于所接收的脉冲响应的所述指定特征的实际值和预测值以及为所述指定特征选择的预测模型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
按照本发明的实施例的一种用于检测信号传播类型的装置，包括：计算模块，用于当超宽带定位系统的某一定位基站当前接收到来自某一定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算指定特征的值，作为所接收的脉冲响应的所述指定特征的实际值；选择模块，用于根据上一次确定的在所述某一定位基站与所述某一定位标签之间的信号传播类型，为所述指定特征选择用于基于所述指定特征在历史时刻的取值来预测其在未来时刻的取值的预测模型；获取模块，用于通过将所述定位基站以前接收的来自所述定位标签的历史脉冲响应的所述指定特征的实际值视为所述指定特征在历史时刻的取值，利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值，作为所接收的脉冲响应的所述指定特征的预测值；以及，确定模块，用于基于所接收的脉冲响应的所述指定特征的实际值和预测值以及为所述指定特征选择的预测模型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
按照本发明的实施例的一种计算设备，包括：处理器；以及，存储器，其存储有可执行指令，所述可执行指令当被执行时使得所述处理器执行前述的方法。
按照本发明的实施例的一种机器可读存储介质，其上具有可执行指令，当所述可执行指令被执行时，使得机器执行前述的方法。
本发明的实施例的方案在UWB定位系统的定位基站当前接收的来自定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算所接 收的脉冲响应的指定特征的实际值，利用预测模型来获取所接收的脉冲响应的指定特征的预测值，以及，利用所接收的脉冲响应的指定特征的实际值和预测值以及所使用的预测模型，来确定当前在该定位基站与该定位标签之间的信号传播类型，因此，本发明的实施例的方案能够检测UWB定位系统的定位基站与定位标签之间的信号传播类型。
附图说明
本发明的其它特征、特点、益处和优点通过以下结合附图的详细描述将变得更加显而易见。其中：
图1示出了按照本发明的一个实施例的用于训练预测模型的方法的总体流程图；
图2示出了按照本发明的一个实施例的用于检测信号传播类型的方法的总体流程图；
图3示出了按照本发明的一个实施例的用于检测信号传播类型的方法的流程图；
图4示出了按照本发明的一个实施例的用于检测信号传播类型的装置的示意图；以及
图5示出了按照本发明的一个实施例的计算设备的示意图。
具体实施方式
下面将参考附图详细描述本发明的各个实施例。
图1示出了按照本发明的一个实施例的用于创建预测模型的方法的总体流程图。图1所示的方法100可以由具有计算能力的任何计算设备来实现。该计算设备可以是但不局限于台式计算机、笔记本电脑、平板电脑、服务器或智能手机等。
如图1所示，在方框102，收集四个脉冲响应集合。
所收集的四个脉冲响应集合包括第一脉冲响应集合C1、第二脉 冲响应集合C2、第三脉冲响应集合C3和第四脉冲响应集合C4。第一脉冲响应集合C1是在UWB定位系统的信号传播从视距传播变换为视距传播的情况下收集的。第二脉冲响应集合C2是在UWB定位系统的信号传播从视距传播变换为非视距传播的情况下收集的。第三脉冲响应集合C3是在UWB定位系统的信号传播从非视距传播变换为非视距传播的情况下收集的。第四脉冲响应集合C4是在UWB定位系统的信号传播从非视距传播变换为视距传播的情况下收集的。
第一脉冲响应集合C1包括多个脉冲响应组。第一脉冲响应集合C1中的每一个脉冲响应组包括多个第一脉冲响应和一个第二脉冲响应，其中，该多个第一脉冲响应是在位于某种场合(例如但不限于，学校、机场、火车站、停车场、商场、剧院或电影院等)中的UWB定位系统的某一定位基站与某一定位标签之间的信号传播是视距传播的情况下该某一定位基站先后接收的来自该某一定位标签的脉冲响应，而该第二脉冲响应是在该某一定位基站与该某一定位标签之间的信号传播变换为视距传播之后该某一定位基站接收的来自该某一定位标签的脉冲响应。
第二脉冲响应集合C2包括多个脉冲响应组。第二脉冲响应集合C2中的每一个脉冲响应组包括多个第一脉冲响应和一个第二脉冲响应，其中，该多个第一脉冲响应是在位于某种场合中的UWB定位系统的某一定位基站与某一定位标签之间的信号传播是视距传播的情况下该某一定位基站先后接收的来自该某一定位标签的脉冲响应，而该第二脉冲响应是在该某一定位基站与该某一定位标签之间的信号传播变换为非视距传播之后该某一定位基站接收的来自该某一定位标签的脉冲响应。
第三脉冲响应集合C3包括多个脉冲响应组。第三脉冲响应集合C3中的每一个脉冲响应组包括多个第一脉冲响应和一个第二脉冲响应，其中，该多个第一脉冲响应是在位于某种场合中的UWB定位系统的某一定位基站与某一定位标签之间的信号传播是非视距传播的情况下该某一定位基站先后接收的来自该某一定位标签的脉冲响应，而该第二脉冲响应是在该某一定位基站与该某一定位标签之间的信 号传播变换为非视距传播之后该某一定位基站接收的来自该某一定位标签的脉冲响应。
第四脉冲响应集合C4包括多个脉冲响应组。第四脉冲响应集合C4中的每一个脉冲响应组包括多个第一脉冲响应和一个第二脉冲响应，其中，该多个第一脉冲响应是在位于某种场合中的UWB定位系统的某一定位基站与某一定位标签之间的信号传播是非视距传播的情况下该某一定位基站先后接收的来自该某一定位标签的脉冲响应，而该第二脉冲响应是在该某一定位基站与该某一定位标签之间的信号传播变换为视距传播之后该某一定位基站接收的来自该某一定位标签的脉冲响应。
在方框106，计算该四个脉冲响应集合中的每一个脉冲响应的单个指定特征SF的值。
指定特征SF可以是其的值仅利用一个脉冲响应就能计算得到的特征。这样的特征例如可以是但不局限于，定位基站与定位标签之间的距离，接收信号能量，最大幅度，最大幅度的上升时间，标准差，第一路径和最强路径的功率差，第一路径和最强路径的功率比，信噪比(SNR)、波形因数，接收脉冲峰值至开始时间延迟，平均超额延迟，均方时延扩展，峰度，波峰因数，峰值与平均功率比，或者，偏斜度等。
指定特征SF也可以是其的值需利用多个脉冲响应才能计算得到的特征。这样的特征例如可以是但不局限于，欧式距离，动态时间规整(DTW)，最长公共子序列，编辑距离，切比雪夫距离，曼哈顿距离，豪斯多夫距离，旋轮距离，单向距离，余弦相似度，折线之间的局部性，或者，线索感知轨迹相似性。在指定特征SF是其的值需利用多个脉冲响应才能计算得到的特征的情况下，该四个脉冲响应集合中的任一脉冲响应的指定特征SF的值利用该任一脉冲响应所处的那个脉冲响应组中的在该任一脉冲响应之前被接收的那些脉冲响应和该任一脉冲响应计算得到。例如但不局限于，假设指定特征SF是欧式距离，脉冲响应Tk位于脉冲响应组T中，以及，在脉冲响应组T中在脉冲响应Tk之前被接收的脉冲响应是脉冲响应Tc、Te和Tf， 那么脉冲响应Tk的欧式距离的值等于脉冲响应Tk与Tc之间的欧式距离、脉冲响应Tk与Te之间的欧式距离和脉冲响应Tk与Tf之间的欧式距离这三者的平均值。
在方框110，利用该四个脉冲响应集合来训练得到四个预测模型M1-M4。
其中，利用第一脉冲响应集合C1所包含的各个脉冲响应组来训练得到预测模型M1，其用于基于指定特征SF在历史时刻的取值来预测指定特征SF在单个未来时刻的取值。在训练预测模型M1时，对于第一脉冲响应集合C1中的每一个脉冲响应组C1-i，脉冲响应组C1-i所包括的那些第一脉冲响应的指定特征SF的值被视为指定特征SF在历史时刻的取值，而脉冲响应组C1-i所包括的第二脉冲响应的指定特征SF的值被视为指定特征SF在单个未来时刻的取值。由于第一脉冲响应集合C1中的每一个脉冲响应组C1-i所包括的第一脉冲响应和第二脉冲响应分别是在定位基站与定位标签之间的信号传播是视距传播和定位基站与定位标签之间的信号传播是视距传播的情况下收集的，因此，预测模型M1的预测适用的信号传播变化情形是定位基站与定位标签之间的信号传播在变换前为视距传播和在变换后为视距传播。
利用第二脉冲响应集合C2所包含的各个脉冲响应组来训练得到预测模型M2，其用于基于指定特征SF在历史时刻的取值来预测指定特征SF在单个未来时刻的取值。在训练预测模型M2时，对于第二脉冲响应集合C2中的每一个脉冲响应组C2-i，脉冲响应组C2-i所包括的那些第一脉冲响应的指定特征SF的值被视为指定特征SF在历史时刻的取值，而脉冲响应组C2-i所包括的第二脉冲响应的指定特征SF的值被视为指定特征SF在单个未来时刻的取值。由于第二脉冲响应集合C2中的每一个脉冲响应组C2-i所包括的第一脉冲响应和第二脉冲响应分别是在定位基站与定位标签之间的信号传播是视距传播和定位基站与定位标签之间的信号传播是非视距传播的情况下收集的，因此，预测模型M2的预测适用的信号传播变化情形是定位基站与定位标签之间的信号传播在变换前为视距传播和在变换 后为非视距传播。
利用第三脉冲响应集合C3所包含的各个脉冲响应组来训练得到预测模型M3，其用于基于指定特征SF在历史时刻的取值来预测指定特征SF在单个未来时刻的取值。在训练预测模型M3时，对于第三脉冲响应集合C3中的每一个脉冲响应组C3-i，脉冲响应组C3-i所包括的那些第一脉冲响应的指定特征SF的值被视为指定特征SF在历史时刻的取值，而脉冲响应组C3-i所包括的第二脉冲响应的指定特征SF的值被视为指定特征SF在单个未来时刻的取值。由于第三脉冲响应集合C3中的每一个脉冲响应组C3-i所包括的第一脉冲响应和第二脉冲响应分别是在定位基站与定位标签之间的信号传播是非视距传播和定位基站与定位标签之间的信号传播是非视距传播的情况下收集的，因此，预测模型M3的预测适用的信号传播变化情形是定位基站与定位标签之间的信号传播在变换前为非视距传播和在变换后为非视距传播。
利用第四脉冲响应集合C4所包含的各个脉冲响应组来训练得到预测模型M4，其用于基于指定特征SF在历史时刻的取值来预测指定特征SF在单个未来时刻的取值。在训练预测模型M4时，对于第四脉冲响应集合C4中的每一个脉冲响应组C4-i，脉冲响应组C4-i所包括的那些第一脉冲响应的指定特征SF的值被视为指定特征SF在历史时刻的取值，而脉冲响应组C4-i所包括的第二脉冲响应的指定特征SF的值被视为指定特征SF在单个未来时刻的取值。由于第四脉冲响应集合C4中的每一个脉冲响应组C4-i所包括的第一脉冲响应和第二脉冲响应分别是在定位基站与定位标签之间的信号传播是非视距传播和定位基站与定位标签之间的信号传播是视距传播的情况下收集的，因此，预测模型M4的预测适用的信号传播变化情形是定位基站与定位标签之间的信号传播在变换前为非视距传播和在变换后为视距传播。
预测模型M1-M4可以使用任何合适的预测算法来实现，所使用的预测算法例如可以是但不局限于时间序列分析方法(例如，移动平均法，或者，自回归移动平均法等)、机器学习算法或拟合算法等。
图2示出了按照本发明的第一实施例的用于检测信号传播类型的方法的总体流程图。图2所示的方法200可以由具有计算能力的任何计算设备来实现。该计算设备可以是但不局限于台式计算机、笔记本电脑、平板电脑、服务器或智能手机等。
如图2所示，在方框202，当UWB定位系统中的某一定位基站BSi当前接收到来自某一定位标签TGj的一个脉冲响应Pn时，至少利用脉冲响应Pn来计算指定特征SF的值，作为脉冲响应Pn的指定特征SF的实际值。
如上面所提到的，指定特征SF既可以是其的值仅利用一个脉冲响应就能计算得到的特征，也可以是其的值需利用多个脉冲响应才能计算得到的特征。这里，如果指定特征SF是其的值仅利用一个脉冲响应就能计算得到的特征，则仅利用脉冲响应Pn来计算指定特征SF的值。如果如果指定特征SF是其的值需利用多个脉冲响应才能计算得到的特征，则利用脉冲响应Pn和定位基站BSi以前(即，在接收指定特征SF之前)接收的来自定位标签TGj的一个或多个脉冲响应，计算指定特征SF的值。
在方框206，从预测模型M1-M4中，选择在其预测适用的信号传播变化情形中定位基站与定位标签之间的信号传播在变换前与上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型相同的预测模型。
这里，如果上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型是视距传播，则选择预测模型M1或M2，因为在预测模型M1和M2的预测适用的信号传播变化情形中定位基站与定位标签之间的信号传播在变换前是视距传播。如果上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型是非视距传播，则选择预测模型M3或M4，因为在预测模型M3和M3的预测适用的信号传播变化情形中定位基站与定位标签之间的信号传播在变换前是非视距传播。
在方框210，找出定位基站BSi以前(即，在接收脉冲响应Pn 之前)接收的来自定位标签TGj的若干历史脉冲响应HP各自的指定特征SF的实际值。
在方框214，将该若干历史脉冲响应HP各自的指定特征SF的实际值视为指定特征SF在历史时刻的取值，输入到在方框206选择的预测模型，获得指定特征SF在单个未来时刻的取值。
在方框218，将在方框214获得的指定特征SF在单个未来时刻的取值，作为脉冲响应Pn的指定特征SF的预测值。
在方框222，获取第一判断结果，其指示脉冲响应Pn的指定特征SF的实际值和预测值之差是否小于指定阈值。
在方框226，获取第二判断结果，其指示在方框206选择的预测模型的预测适用的信号传播变换情形是否为定位基站与定位标签之间的信号传播在变换前和在变换后都是特定信号传播类型，其中，所述特定信号传播类型是上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型。
在方框230，根据所获取的第一判断结果和第二判断结果，确定当前在定位基站BSi与定位标签TGj之间的信号传播类型。
这里，当第一判断结果和第二判断结果都是肯定，或者，第一判断结果和第二判断结果都是否定时，确定当前在定位基站BSi与定位标签TGj之间的信号传播类型是所述特定信号传播类型。
当第一判断结果为肯定且第二判断结果为否定，或者，第一判断结果为否定且第二判断结果为肯定时，确定当前在定位基站BSi与定位标签TGj之间的信号传播类型是与所述特定信号传播类型不同的另一信号传播类型。
在本实施例中，当UWB定位系统的定位基站当前接收的来自定位标签的一个脉冲响应时，至少利用所接收的脉冲响应来计算所接收的脉冲响应的指定特征的实际值，然后利用预测模型来获取所接收的脉冲响应的指定特征的预测值，最后利用所接收的脉冲响应的指定特征的实际值和预测值以及所使用的预测模型，来确定当前在该定位基站与该定位标签之间的信号传播类型，因此，本实施例的方案能够检 测UWB定位系统的定位基站与定位标签之间的信号传播类型。
其它变型
(1)单个脉冲响应和多个指定特征
本领域技术人员将理解，虽然在上面的实施例中，在检测当前在定位基站BSi与定位标签TGj之间的信号传播类型时仅利用定位基站BSi当前接收的来自定位标签TGj的单个脉冲响应Pn的单个指定特征SF，然而，本发明并不局限于此。在本发明的其它一些实施例中，在检测当前在定位基站BSi与定位标签TGj之间的信号传播类型时也可以利用定位基站BSi当前接收的来自定位标签TGj的单个脉冲响应Pn的多个指定特征MSF。
在利用定位基站BSi当前接收的来自定位标签TGj的单个脉冲响应Pn的多个指定特征MSF来检测当前在定位基站BSi与定位标签TGj之间的信号传播类型的情况下，该多个指定特征MSF中的每一个指定特征MSFi与指定特征SF一样，既可以是其的值仅利用一个脉冲响应就能计算得到的特征，也可以是其的值需利用多个脉冲响应才能计算得到的特征。与指定特征SF一样，为每一个指定特征MSFi训练四个预测模型，每一个预测模型用于基于指定特征MSFi在历史时刻的取值来预测指定特征MSFi在单个未来时刻的取值，并且，每一个预测模型的预测适用的信号传播变化情形是以下四种情形之一：定位基站与定位标签之间的信号传播在变换前为视距传播和在变换后为视距传播，定位基站与定位标签之间的信号传播在变换前为视距传播和在变换后为非视距传播，定位基站与定位标签之间的信号传播在变换前为非视距传播和在变换后为非视距传播，以及，定位基站与定位标签之间的信号传播在变换前为非视距传播和在变换后为视距传播。
当定位基站BSi当前接收来自定位标签TGj的单个脉冲响应Pn时，与方框202描述的类似，至少基于脉冲响应Pn来计算脉冲响应Pn的该多个指定特征MSF各自的实际值。然后，为该多个指定特征MSF中的每一个指定特征MSFi，选择在其预测适用的信号传播变化 情形中定位基站与定位标签之间的信号传播在变换前与上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型相同的预测模型。接着，与方框210-218一样，获取脉冲响应Pn的该多个指定特征MSF各自的预测值。接下来，获取该多个指定特征MSF各自的第一判断结果，每一个指定特征MSFi的第一判断结果指示脉冲响应Pn的指定特征MSFi的实际值和预测值之差是否小于指定阈值。获取该多个指定特征MSF各自的第二判断结果，每一个指定特征MSFi的第二判断结果指示为指定特征MSFi选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是特定信号传播类型，该特定信号传播类型是上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型。接着，获取多个候选信号传播类型，每一个候选信号传播类型指示基于脉冲响应Pn的该多个指定特征MSF的其中一个指定特征的第一判断结果和第二判断结果而确定的当前在定位基站BSi与定位标签TGj之间的信号传播类型。最后，利用该多个候选信号传播类型，来确定当前在定位基站BSi与定位标签TGj之间的信号传播类型。例如但不局限于，假设在该多个候选信号传播类型中超过一半的候选信号传播类型属于某一种信号传播(视距传播或非视距传播)，则将当前在定位基站BSi与定位标签TGj之间的信号传播类型确定为该某一种信号传播。
(2)多个脉冲响应和单个指定特征
本领域技术人员将理解，虽然在上面的实施例中，在检测当前在定位基站BSi与定位标签TGj之间的信号传播类型时仅利用定位基站BSi当前接收的来自定位标签TGj的单个脉冲响应Pn的单个指定特征SF，然而，本发明并不局限于此。在本发明的其它一些实施例中，在检测当前在定位基站BSi与定位标签TGj之间的信号传播类型时也可以利用定位基站BSi当前接收的来自定位标签TGj的多个脉冲响应MPn各自的单个指定特征SF。
在利用定位基站BSi当前接收的来自定位标签TGj的多个脉冲响应MPn的单个指定特征SF来检测当前在定位基站BSi与定位标签 TGj之间的信号传播类型的情况下，第一至第四脉冲响应集合C1-C4中的每一个脉冲响应组包括多个第二脉冲响应，并且在训练预测模型时，每一个脉冲响应集合中的每一个脉冲响应组所包括的该多个第二脉冲响应的指定特征SF的值被视为指定特征SF在多个未来时刻的取值，以使得训练得到的预测模型M1-M4中的每一个预测模型用于基于指定特征SF在历史时刻的取值来预测指定特征SF在多个未来时刻的取值。
当定位基站BSi当前接收来自定位标签TGj的该多个脉冲响应MPn时，与方框202描述的类似，至少基于该多个脉冲响应MPn中的每一个脉冲响应MPn-i来计算脉冲响应MPn-i的指定特征SF的实际值，以得到该多个脉冲响应MPn各自的指定特征SF的实际值。接着，将定位基站BSi以前接收的来自定位标签TGj的若干历史脉冲响应HP各自的指定特征SF的实际值视为指定特征SF在历史时刻的取值，输入到在方框206选择的预测模型，获得指定特征SF在多个未来时刻的取值，作为该多个脉冲响应MPn的指定特征SF的预测值。例如，假设该多个脉冲响应MPn包括依次接收到的三个脉冲响应MP1、MP2和MP3，以及，利用预测模型获得指定特征SF在第一未来时刻的取值V1、指定特征SF在第二未来时刻的取值V2和指定特征SF在第三未来时刻的取值V3，那么脉冲响应MP1的指定特征SF的预测值是V1，脉冲响应MP2的指定特征SF的预测值是V2，以及，脉冲响应MP3的指定特征SF的预测值是V3。接下来，获取该多个脉冲响应MPn各自的第一指示值，每一个脉冲响应MPn-i的第一指示值表示脉冲响应MPn-i的指定特征SF的实际值和预测值之差。然后，基于该多个脉冲响应MPn的第一指示值，计算第二指示值。例如，可以计算该多个脉冲响应MPn的第一指示值的绝对值的平均值，作为该第二指示值。又例如，可以计算该多个脉冲响应MPn的第一指示值的均方根值，作为该第二指示值。接着，获取第一判断结果，其指示该第二指示值是否小于指定阈值。获取第二判断结果，其示为指定特征SF选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是特定信 号传播类型，该特定信号传播类型是上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型。最后，基于该第一判断结果和该第二判断结果，来确定当前在定位基站BSi与定位标签TGj之间的信号传播类型。具体地，当该第一判断结果和该第二判断结果都是肯定，或者，该第一判断结果和该第二判断结果都是否定时，确定当前在定位基站BSi与定位标签TGj之间的信号传播类型是上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型。当该第一判断结果为肯定且该第二判断结果为否定，或者，该第一判断结果为否定且该第二判断结果为肯定时，确定当前在定位基站BSi与定位标签TGj之间的信号传播类型是与上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型不同的另一信号传播类型。。
(3)多个脉冲响应和多个指定特征
本领域技术人员将理解，虽然在上面的实施例中，在检测当前在定位基站BSi与定位标签TGj之间的信号传播类型时仅利用定位基站BSi当前接收的来自定位标签TGj的单个脉冲响应Pn的单个指定特征SF，然而，本发明并不局限于此。在本发明的其它一些实施例中，在检测当前在定位基站BSi与定位标签TGj之间的信号传播类型时也可以利用定位基站BSi当前接收的来自定位标签TGj的多个脉冲响应PMP各自的多个指定特征FSF。
在利用定位基站BSi当前接收的来自定位标签TGj的该多个脉冲响应PMP各自的该多个指定特征FSF来检测当前在定位基站BSi与定位标签TGj之间的信号传播类型的情况下，为该多个指定特征FSF中的每一个指定特征FSFi训练四个预测模型，为指定特征FSFi训练的每一个预测模型用于基于指定特征FSFi在历史时刻的取值来预测指定特征FSFi在多个未来时刻的取值，并且，为指定特征FSFi训练的每一个预测模型的预测适用的信号传播变化情形是以下四种情形之一：定位基站与定位标签之间的信号传播在变换前为视距传播和在变换后为视距传播，定位基站与定位标签之间的信号传播在变换前为视距传播和在变换后为非视距传播，定位基站与定位标签之间的信号 传播在变换前为非视距传播和在变换后为非视距传播，以及，定位基站与定位标签之间的信号传播在变换前为非视距传播和在变换后为视距传播。
当定位基站BSi当前接收来自定位标签TGj的该多个脉冲响应PMP时，与方框202描述的类似，至少基于该多个脉冲响应PMP中的每一个脉冲响应PMP-i来计算脉冲响应PMP-i的该多个指定特征FSF各自的实际值，以得到该多个脉冲响应PMP中的每一个脉冲响应PMP-i的该多个指定特征FSF各自的实际值。然后，为该多个指定特征FSF中的每一个指定特征FSFi选择一个预测模型，其中，在所选择的预测模型的预测适用的信号传播变化情形中定位基站与定位标签之间的信号传播在变换前与上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型相同。接着，将定位基站BSi以前接收的来自定位标签TGj的若干历史脉冲响应HP各自的每一个指定特征FSFi的实际值视为指定特征FSFi在历史时刻的取值，输入到为指定特征FSFi选择的预测模型，获得指定特征FSFi在多个未来时刻的取值，作为该多个脉冲响应PMP各自的指定特征FSFi的预测值。然后，获取该多个脉冲响应PMP中的每一个脉冲响应PMP-i的该多个指定特征FSF各自的第一指示值，其中，脉冲响应PMP-i的每一个指定特征FSFi的第一指示值表示脉冲响应PMP-i的指定特征FSFi的实际值和预测值之差。接着，获取该多个指定特征FSF各自的第二指示值，其中，每一个指定特征FSFi的第二指示值是基于该多个脉冲响应PMP的指定特征FSFi的第一指示值计算的。例如，可以计算该多个脉冲响应PMP的指定特征FSFi的第一指示值的绝对值的平均值，作为指定特征FSFi的第二指示值。又例如，可以计算该多个脉冲响应PMP的指定特征FSFi的第一指示值的均方根值，作为指定特征FSFi的第二指示值。然后，获取该多个指定特征FSF各自的第一判断结果，其中，每一个指定特征FSFi的第一判断结果表示指定特征FSFi的第二指示值是否小于指定阈值。获取该多个指定特征FSF各自的第二判断结果，其中，每一个指定特征FSFi的第二判断结果指示为指定特征FSFi选择的预测模型的预测适用的信号传播变化情 形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是特定信号传播类型，该特定信号传播类型是上一次确定的定位基站BSi与定位标签TGj之间的信号传播类型。接着，获取多个候选信号传播类型，其中，每一个候选信号传播类型指示基于该多个指定特征FSF的其中一个指定特征FSFj的第一判断结果和第二判断结果而确定的当前在定位基站BSi与定位标签TGj之间的信号传播类型。最后，基于该多个候选信号传播类型，判定当前在定位基站BSi与定位标签TGj之间的信号传播类型。例如但不局限于，假设在该多个候选信号传播类型中超过一半的候选信号传播类型属于某一特定信号传播(视距传播或非视距传播)，则将当前在定位基站BSi与定位标签TGj之间的信号传播类型确定为该某一特定信号传播。
本领域技术人员将理解，虽然在上面的实施例中，为每一个指定特征训练四个预测模型，然而，本发明并不局限于此。在本发明的其它一些实施例中，也可以为每一个指定特征仅训练两个预测模型，其中，该两个预测模型的其中一个预测模型的预测适用的信号传播变化情形是以下两种情形之一：定位基站与定位标签之间的信号传播在变换前为视距传播和在变换后为视距传播，以及，定位基站与定位标签之间的信号传播在变换前为视距传播和在变换后为非视距传播，而该两个预测模型的另一个预测模型的预测适用的信号传播变化情形是以下两种情形之一：定位基站与定位标签之间的信号传播在变换前为非视距传播和在变换后为非视距传播，以及，定位基站与定位标签之间的信号传播在变换前为非视距传播和在变换后为视距传播。
图3示出了按照本发明的一个实施例的用于检测信号传播类型的方法的流程图。如图3所示的方法300可以由具有计算能力的任何计算设备来实现。
如图3所示，方法300可以包括，在方框302，当超宽带定位系统的某一定位基站当前接收到来自某一定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算指定特征的值，作为所接收的脉冲响应 的所述指定特征的实际值。
方法300还可以包括，在方框304，根据上一次确定的在所述某一定位基站与所述某一定位标签之间的信号传播类型，为所述指定特征选择用于基于所述指定特征在历史时刻的取值来预测其在未来时刻的取值的预测模型。
方法300还可以包括，在方框306，通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述指定特征的实际值视为所述指定特征在历史时刻的取值，利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值，作为所接收的脉冲响应的所述指定特征的预测值。
方法300还可以包括，在方框308，基于所接收的脉冲响应的所述指定特征的实际值和预测值以及为所述指定特征选择的预测模型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
在第一方面，所述指定特征仅包括单个特征，以及，所述接收的脉冲响应仅包括单个脉冲响应，其中，方框308包括：获取第一判断结果，其指示所述单个脉冲响应的所述单个特征的实际值和预测值之差是否小于指定阈值；获取第二判断结果，其指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；以及，基于所述第一判断结果和所述第二判断结果，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
在第二方面，所述指定特征包括多个特定特征，所述接收的脉冲响应仅包括单个脉冲响应，所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并用于基于所述其中一个特定特征在历史时刻的取值来预测其在单个未来时刻的取值，以及，方框308包括：获取所述多个特定特征各自的第一判断结果，其中，每一个特定特征的第一判断结果指示所述单个脉冲响应的该特定特征的实际值和预测值之差是否小于指定阈 值；获取所述多个特定特征各自的第二判断结果，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；获取多个候选信号传播类型，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及，基于所述多个候选信号传播类型，确定当前在所述定位基站与所述定位标签之间的信号传播类型。
在第三方面，所述指定特征仅包括单个特征，所述接收的脉冲响应包括多个脉冲响应，为所述单个特征选择的预测模型用于基于所述单个特征在历史时刻的取值来预测其在多个未来时刻的取值，方框306包括：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述单个特征的实际值视为所述单个特征在历史时刻的取值，利用为所述单个特征选择的预测模型来获取所述单个特征在多个未来时刻的取值，作为所述多个脉冲响应的所述单个特征的预测值，以及，方框308包括：获取所述多个脉冲响应各自的第一指示值，其中，每一个脉冲响应的第一指示值表示该脉冲响应的所述单个特征的实际值和预测值之差；获取第二指示值，其是基于所述多个脉冲响应的第一指示值计算的；获取第一判断结果，其指示所述第二指示值是否小于指定阈值；获取第二判断结果，其指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；以及，基于所述第一判断结果和所述第二判断结果，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
在第四方面，所述指定特征包括多个特定特征，所述接收的脉冲响应包括多个脉冲响应，所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并 用于基于所述其中一个特定特征在历史时刻的取值来预测其在多个未来时刻的取值，方框306包括：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述多个特定特征中的任一特定特征的实际值视为所述任一特定特征在历史时刻的取值，利用为所述任一特定特征选择的预测模型来获取所述任一特定特征在多个未来时刻的取值，作为所述多个脉冲响应的所述任一特定特征的预测值，以及，方框308包括：获取所述多个脉冲响应中的任一脉冲响应的所述多个特定特征各自的第一指示值，其中，所述任一脉冲响应的每一个特定特征的第一指示值表示所述任一脉冲响应的该特定特征的实际值和预测值之差；获取所述多个特定特征各自的第二指示值，其中，每一个特定特征的第二指示值是基于所述多个脉冲响应各自的该特定特征的第一指示值计算的；获取所述多个特定特征各自的第一判断结果，每一个特定特征的第一判断结果指示该特定特征的第二指示值是否小于指定阈值；获取所述多个特定特征各自的第二判断结果，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；获取多个候选信号传播类型，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及，基于所述多个候选信号传播类型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
图4示出了按照本发明的一个实施例的用于检测信号传播类型的装置的示意图。图4所示的装置400可以利用软件、硬件或软硬件结合的方式来执行。图4所示的装置400例如可以安装在具有计算能力的任何计算设备中。
如图4所示，装置400可以包括计算模块402、选择模块404、获取模块406和确定模块408。计算模块402用于当超宽带定位系统 的某一定位基站当前接收到来自某一定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算指定特征的值，作为所接收的脉冲响应的所述指定特征的实际值。选择模块404用于根据上一次确定的在所述某一定位基站与所述某一定位标签之间的信号传播类型，为所述指定特征选择用于基于所述指定特征在历史时刻的取值来预测其在未来时刻的取值的预测模型。获取模块406用于通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述指定特征的实际值视为所述指定特征在历史时刻的取值，利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值，作为所接收的脉冲响应的所述指定特征的预测值。确定模块408用于基于所接收的脉冲响应的所述指定特征的实际值和预测值以及为所述指定特征选择的预测模型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
在第一方面，所述指定特征仅包括单个特征，以及，所述接收的脉冲响应仅包括单个脉冲响应，其中，确定模块408包括：用于获取第一判断结果，其指示所述单个脉冲响应的所述单个特征的实际值和预测值之差是否小于指定阈值的模块；用于获取第二判断结果，其指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型的模块；以及，用于基于所述第一判断结果和所述第二判断结果，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型的模块。
在第二方面，所述指定特征包括多个特定特征，所述接收的脉冲响应仅包括单个脉冲响应，所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并用于基于所述其中一个特定特征在历史时刻的取值来预测其在单个未来时刻的取值，以及，确定模块408包括：用于获取所述多个特定特征各自的第一判断结果的模块，其中，每一个特定特征的第一判断结果指示所述单个脉冲响应的该特定特征的实际值和预测值之差 是否小于指定阈值；用于获取所述多个特定特征各自的第二判断结果的模块，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；用于获取多个候选信号传播类型的模块，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及，用于基于所述多个候选信号传播类型，确定当前在所述定位基站与所述定位标签之间的信号传播类型的模块。
在第三方面，所述指定特征仅包括单个特征，所述接收的脉冲响应包括多个脉冲响应，为所述单个特征选择的预测模型用于基于所述单个特征在历史时刻的取值来预测其在多个未来时刻的取值，获取模块404进一步用于：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述单个特征的实际值视为所述单个特征在历史时刻的取值，利用为所述单个特征选择的预测模型来获取所述单个特征在多个未来时刻的取值，作为所述多个脉冲响应的所述单个特征的预测值，以及，确定模块408包括：用于获取所述多个脉冲响应各自的第一指示值的模块，其中，每一个脉冲响应的第一指示值表示该脉冲响应的所述单个特征的实际值和预测值之差；用于获取第二指示值的模块，所述第二指示值是基于所述多个脉冲响应的第一指示值计算的；用于获取第一判断结果的模块，所述第一判断结果指示所述第二指示值是否小于指定阈值；用于获取第二判断结果的模块，所述第二判断结果指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；以及，用于基于所述第一判断结果和所述第二判断结果，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型的模块。
在第四方面，所述指定特征包括多个特定特征，所述接收的脉冲 响应包括多个脉冲响应，所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并用于基于所述其中一个特定特征在历史时刻的取值来预测其在多个未来时刻的取值，获取模块404进一步用于：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述多个特定特征中的任一特定特征的实际值视为所述任一特定特征在历史时刻的取值，利用为所述任一特定特征选择的预测模型来获取所述任一特定特征在多个未来时刻的取值，作为所述多个脉冲响应的所述任一特定特征的预测值，以及，确定模块408包括：用于获取所述多个脉冲响应中的任一脉冲响应的所述多个特定特征各自的第一指示值的模块，其中，所述任一脉冲响应的每一个特定特征的第一指示值表示所述任一脉冲响应的该特定特征的实际值和预测值之差；用于获取所述多个特定特征各自的第二指示值的模块，其中，每一个特定特征的第二指示值是基于所述多个脉冲响应各自的该特定特征的第一指示值计算的；用于获取所述多个特定特征各自的第一判断结果的模块，每一个特定特征的第一判断结果指示该特定特征的第二指示值是否小于指定阈值；用于获取所述多个特定特征各自的第二判断结果的模块，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；用于获取多个候选信号传播类型的模块，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及，用于基于所述多个候选信号传播类型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型的模块。
图5示出了按照本发明的一个实施例的计算设备的示意图。如图5所示，计算设备500可以包括处理器502和存储器504。其中，存储器504存储有可执行指令，所述可执行指令当被执行时使得处理器 502执行前述的方法。
本发明实施例还提供一种机器可读存储介质，其上具有可执行指令，当所述可执行指令被执行时，使得机器执行前述的方法。
本领域技术人员应当理解，上面所公开的各个实施例可以在不偏离发明实质的情况下做出各种变形、修改和改变，这些变形、修改和改变都应当落入在本发明的保护范围之内。因此，本发明的保护范围由所附的权利要求书来限定。

Claims (12)

  1. 一种用于检测信号传播类型的方法，包括：
    当超宽带定位系统的某一定位基站当前接收到来自某一定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算指定特征的值，作为所接收的脉冲响应的所述指定特征的实际值；
    根据上一次确定的在所述某一定位基站与所述某一定位标签之间的信号传播类型，为所述指定特征选择用于基于所述指定特征在历史时刻的取值来预测其在未来时刻的取值的预测模型；
    通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述指定特征的实际值视为所述指定特征在历史时刻的取值，利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值，作为所接收的脉冲响应的所述指定特征的预测值；以及
    基于所接收的脉冲响应的所述指定特征的实际值和预测值以及为所述指定特征选择的预测模型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
  2. 如权利要求1所述的方法，其中
    所述指定特征仅包括单个特征，以及，所述接收的脉冲响应仅包括单个脉冲响应，
    其中，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型包括：
    获取第一判断结果，其指示所述单个脉冲响应的所述单个特征的实际值和预测值之差是否小于指定阈值；
    获取第二判断结果，其指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；以及
    基于所述第一判断结果和所述第二判断结果，确定当前在所述某 一定位基站与所述某一定位标签之间的信号传播类型。
  3. 如权利要求1所述的方法，其中
    所述指定特征包括多个特定特征，
    所述接收的脉冲响应仅包括单个脉冲响应，
    所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并用于基于所述其中一个特定特征在历史时刻的取值来预测其在单个未来时刻的取值，以及
    确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型包括：
    获取所述多个特定特征各自的第一判断结果，其中，每一个特定特征的第一判断结果指示所述单个脉冲响应的该特定特征的实际值和预测值之差是否小于指定阈值；
    获取所述多个特定特征各自的第二判断结果，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；
    获取多个候选信号传播类型，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及
    基于所述多个候选信号传播类型，确定当前在所述定位基站与所述定位标签之间的信号传播类型。
  4. 如权利要求1所述的方法，其中
    所述指定特征仅包括单个特征，
    所述接收的脉冲响应包括多个脉冲响应，
    为所述单个特征选择的预测模型用于基于所述单个特征在历史时刻的取值来预测其在多个未来时刻的取值，
    利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值包括：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述单个特征的实际值视为所述单个特征在历史时刻的取值，利用为所述单个特征选择的预测模型来获取所述单个特征在多个未来时刻的取值，作为所述多个脉冲响应的所述单个特征的预测值，以及
    确定当前在所述某一定位基站与所述定位标签之间的信号传播类型包括：
    获取所述多个脉冲响应各自的第一指示值，其中，每一个脉冲响应的第一指示值表示该脉冲响应的所述单个特征的实际值和预测值之差；
    获取第二指示值，其是基于所述多个脉冲响应的第一指示值计算的；
    获取第一判断结果，其指示所述第二指示值是否小于指定阈值；
    获取第二判断结果，其指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；以及
    基于所述第一判断结果和所述第二判断结果，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
  5. 如权利要求1所述的方法，其中
    所述指定特征包括多个特定特征，
    所述接收的脉冲响应包括多个脉冲响应，
    所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并用于基于所述其中一个特定特征在历史时刻的取值来预测其在多个未来时刻的取值，
    利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值包括：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述多个特定特征中的任一特定特征 的实际值视为所述任一特定特征在历史时刻的取值，利用为所述任一特定特征选择的预测模型来获取所述任一特定特征在多个未来时刻的取值，作为所述多个脉冲响应的所述任一特定特征的预测值，以及
    确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型包括：
    获取所述多个脉冲响应中的任一脉冲响应的所述多个特定特征各自的第一指示值，其中，所述任一脉冲响应的每一个特定特征的第一指示值表示所述任一脉冲响应的该特定特征的实际值和预测值之差；
    获取所述多个特定特征各自的第二指示值，其中，每一个特定特征的第二指示值是基于所述多个脉冲响应各自的该特定特征的第一指示值计算的；
    获取所述多个特定特征各自的第一判断结果，每一个特定特征的第一判断结果指示该特定特征的第二指示值是否小于指定阈值；
    获取所述多个特定特征各自的第二判断结果，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；
    获取多个候选信号传播类型，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及
    基于所述多个候选信号传播类型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
  6. 一种用于检测信号传播类型的装置，包括：
    计算模块，用于当超宽带定位系统的某一定位基站当前接收到来自某一定位标签的脉冲响应时，至少利用所接收的脉冲响应来计算指定特征的值，作为所接收的脉冲响应的所述指定特征的实际值；
    选择模块，用于根据上一次确定的在所述某一定位基站与所述某一定位标签之间的信号传播类型，为所述指定特征选择用于基于所述指定特征在历史时刻的取值来预测其在未来时刻的取值的预测模型；
    获取模块，用于通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述指定特征的实际值视为所述指定特征在历史时刻的取值，利用为所述指定特征选择的预测模型来获取所述指定特征在未来时刻的取值，作为所接收的脉冲响应的所述指定特征的预测值；以及
    确定模块，用于基于所接收的脉冲响应的所述指定特征的实际值和预测值以及为所述指定特征选择的预测模型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型。
  7. 如权利要求6所述的装置，其中
    所述指定特征仅包括单个特征，以及，所述接收的脉冲响应仅包括单个脉冲响应，
    其中，所述确定模块包括：
    用于获取第一判断结果，其指示所述单个脉冲响应的所述单个特征的实际值和预测值之差是否小于指定阈值的模块；
    用于获取第二判断结果，其指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型的模块；以及
    用于基于所述第一判断结果和所述第二判断结果，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型的模块。
  8. 如权利要求6所述的装置，其中
    所述指定特征包括多个特定特征，
    所述接收的脉冲响应仅包括单个脉冲响应，
    所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并用于基于所述其中一 个特定特征在历史时刻的取值来预测其在单个未来时刻的取值，以及
    所述确定模块包括：
    用于获取所述多个特定特征各自的第一判断结果的模块，其中，每一个特定特征的第一判断结果指示所述单个脉冲响应的该特定特征的实际值和预测值之差是否小于指定阈值；
    用于获取所述多个特定特征各自的第二判断结果的模块，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；
    用于获取多个候选信号传播类型的模块，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及
    用于基于所述多个候选信号传播类型，确定当前在所述定位基站与所述定位标签之间的信号传播类型的模块。
  9. 如权利要求6所述的装置，其中
    所述指定特征仅包括单个特征，
    所述接收的脉冲响应包括多个脉冲响应，
    为所述单个特征选择的预测模型用于基于所述单个特征在历史时刻的取值来预测其在多个未来时刻的取值，
    所述获取模块进一步用于：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述单个特征的实际值视为所述单个特征在历史时刻的取值，利用为所述单个特征选择的预测模型来获取所述单个特征在多个未来时刻的取值，作为所述多个脉冲响应的所述单个特征的预测值，以及
    所述确定模块包括：
    用于获取所述多个脉冲响应各自的第一指示值的模块，其中，每一个脉冲响应的第一指示值表示该脉冲响应的所述单个特征的实际 值和预测值之差；
    用于获取第二指示值的模块，所述第二指示值是基于所述多个脉冲响应的第一指示值计算的；
    用于获取第一判断结果的模块，所述第一判断结果指示所述第二指示值是否小于指定阈值；
    用于获取第二判断结果的模块，所述第二判断结果指示为所述单个特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；以及
    用于基于所述第一判断结果和所述第二判断结果，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型的模块。
  10. 如权利要求6所述的装置，其中
    所述指定特征包括多个特定特征，
    所述接收的脉冲响应包括多个脉冲响应，
    所述选择的预测模型包括多个预测模型，每一个预测模型是为所述多个特定特征的其中一个特定特征选择的并用于基于所述其中一个特定特征在历史时刻的取值来预测其在多个未来时刻的取值，
    所述获取模块进一步用于：通过将所述某一定位基站以前接收的来自所述某一定位标签的历史脉冲响应的所述多个特定特征中的任一特定特征的实际值视为所述任一特定特征在历史时刻的取值，利用为所述任一特定特征选择的预测模型来获取所述任一特定特征在多个未来时刻的取值，作为所述多个脉冲响应的所述任一特定特征的预测值，以及
    所述确定模块包括：
    用于获取所述多个脉冲响应中的任一脉冲响应的所述多个特定特征各自的第一指示值的模块，其中，所述任一脉冲响应的每一个特定特征的第一指示值表示所述任一脉冲响应的该特定特征的实际值和预测值之差；
    用于获取所述多个特定特征各自的第二指示值的模块，其中，每 一个特定特征的第二指示值是基于所述多个脉冲响应各自的该特定特征的第一指示值计算的；
    用于获取所述多个特定特征各自的第一判断结果的模块，每一个特定特征的第一判断结果指示该特定特征的第二指示值是否小于指定阈值；
    用于获取所述多个特定特征各自的第二判断结果的模块，其中，每一个特定特征的第二判断结果指示为该特定特征选择的预测模型的预测适用的信号传播变化情形是否是定位基站与定位标签之间的信号传播在变换前和变换后都是上一次确定的所述某一定位基站与所述某一定位标签之间的信号传播类型；
    用于获取多个候选信号传播类型的模块，其中，每一个候选信号传播类型指示基于所述多个特定特征的其中一个特定特征的第一判断结果和第二判断结果而确定的当前在所述某一定位基站与所述某一定位标签之间的信号传播类型；以及
    用于基于所述多个候选信号传播类型，确定当前在所述某一定位基站与所述某一定位标签之间的信号传播类型的模块。
  11. 一种计算设备，包括：
    处理器；以及
    存储器，其存储有可执行指令，所述可执行指令当被执行时使得所述处理器执行权利要求1-5中的任意一个所述的方法。
  12. 一种机器可读存储介质，其上具有可执行指令，当所述可执行指令被执行时，使得机器执行权利要求1-5中的任意一个所述的方法。
PCT/CN2018/100389 2018-08-14 2018-08-14 用于检测信号传播类型的方法和装置 WO2020034085A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN201880096605.1A CN112567834B (zh) 2018-08-14 2018-08-14 用于检测信号传播类型的方法和装置
PCT/CN2018/100389 WO2020034085A1 (zh) 2018-08-14 2018-08-14 用于检测信号传播类型的方法和装置
EP18930106.2A EP3840490A4 (en) 2018-08-14 2018-08-14 METHOD AND APPARATUS FOR DETECTING THE TYPE OF PROPAGATION OF A SIGNAL
US17/268,760 US11791911B2 (en) 2018-08-14 2018-08-14 Method and apparatus for detecting signal propagation type

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/100389 WO2020034085A1 (zh) 2018-08-14 2018-08-14 用于检测信号传播类型的方法和装置

Publications (1)

Publication Number Publication Date
WO2020034085A1 true WO2020034085A1 (zh) 2020-02-20

Family

ID=69524952

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/100389 WO2020034085A1 (zh) 2018-08-14 2018-08-14 用于检测信号传播类型的方法和装置

Country Status (4)

Country Link
US (1) US11791911B2 (zh)
EP (1) EP3840490A4 (zh)
CN (1) CN112567834B (zh)
WO (1) WO2020034085A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020010558A1 (zh) * 2018-07-12 2020-01-16 罗伯特·博世有限公司 检测方法和检测装置
CN117056818B (zh) * 2023-10-08 2024-02-02 广东工业大学 一种基于cir第一路径的超宽带nlos信号识别方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101526605A (zh) * 2009-03-31 2009-09-09 江苏大学 一种具有非视距误差消除功能的鲁棒定位方法
CN103399297A (zh) * 2013-08-16 2013-11-20 哈尔滨工业大学深圳研究生院 一种基于机器学习的超宽带非视距鉴别方法
EP3079381A1 (en) * 2015-04-09 2016-10-12 Datalogic IP TECH S.r.l. High accuracy indoor locating system
CN106162555A (zh) * 2016-09-26 2016-11-23 湘潭大学 室内定位方法及系统
CN106455059A (zh) * 2016-12-09 2017-02-22 北京邮电大学 一种室内定位的方法及装置

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10350362B4 (de) * 2003-10-29 2008-06-19 Infineon Technologies Ag Verfahren zum Vorhersagen eines Kanalkoeffizienten
JP4567093B2 (ja) * 2006-08-03 2010-10-20 株式会社エヌ・ティ・ティ・ドコモ マルチパスチャネル統計データを用いて見通し線（ｌｏｓ）と非ｌｏｓ（ｎｌｏｓ）とを識別する方法
US7577445B2 (en) 2006-08-03 2009-08-18 Ntt Docomo, Inc. Line-of-sight (LOS) or non-LOS (NLOS) identification method using multipath channel statistics
GB2445385B (en) * 2006-12-29 2011-08-31 Nokia Corp Improvements in or relating to distance estimation
US9002286B2 (en) * 2009-03-30 2015-04-07 Massachusetts Institute Of Technology Method and system for identification and mitigation of errors in non-line-of-sight distance estimation
CN101883426B (zh) * 2010-06-19 2012-07-25 中国海洋大学 高精度的超宽带无线定位方法
CN105911539B (zh) * 2016-04-19 2018-04-13 北京邮电大学 一种到达时间差的误差补偿值确定方法及装置
CN107333232B (zh) * 2016-04-29 2020-02-21 华为技术有限公司 一种终端定位方法及网络设备
CN107037402A (zh) 2017-05-24 2017-08-11 南京图贝斯韦智能技术有限公司 一种基于uwb测距的室内非视距环境下的定位方法
US10466345B1 (en) * 2017-06-01 2019-11-05 Apple Inc. Time-of-arrival estimation with subspace methods
CN107817469B (zh) * 2017-10-18 2020-11-24 上海理工大学 基于非视距环境下超宽频测距实现室内定位方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101526605A (zh) * 2009-03-31 2009-09-09 江苏大学 一种具有非视距误差消除功能的鲁棒定位方法
CN103399297A (zh) * 2013-08-16 2013-11-20 哈尔滨工业大学深圳研究生院 一种基于机器学习的超宽带非视距鉴别方法
EP3079381A1 (en) * 2015-04-09 2016-10-12 Datalogic IP TECH S.r.l. High accuracy indoor locating system
CN106162555A (zh) * 2016-09-26 2016-11-23 湘潭大学 室内定位方法及系统
CN106455059A (zh) * 2016-12-09 2017-02-22 北京邮电大学 一种室内定位的方法及装置

Also Published As

Publication number Publication date
CN112567834A (zh) 2021-03-26
US20210325523A1 (en) 2021-10-21
CN112567834B (zh) 2023-11-24
EP3840490A1 (en) 2021-06-23
US11791911B2 (en) 2023-10-17
EP3840490A4 (en) 2022-03-30

Similar Documents

Publication Publication Date Title
Jang et al. Geomagnetic field based indoor localization using recurrent neural networks
US11500055B2 (en) Detection method and detection apparatus
JP6032469B2 (ja) 発信源推定方法およびそれを利用した発信源推定装置
CN105334495B (zh) 一种无线网络中基于信号到达时间的非视距稳健定位方法
CN109756842B (zh) 基于注意力机制的无线室内定位方法及系统
CN111830463A (zh) 一种基于tdoa的定位系统、方法及存储介质
KR20140098283A (ko) 신뢰도 기반 격자형 핑거프린트 맵을 이용한 위치 추적 장치 및 방법
CN107205226B (zh) 基于信道分类的室内定位跟踪方法及系统
US7050652B2 (en) Methods and arrangements to enhance correlation
WO2020034085A1 (zh) 用于检测信号传播类型的方法和装置
CN104865570A (zh) 一种快速的动态规划检测前跟踪方法
Narzullaev et al. Novel calibration algorithm for received signal strength based indoor real-time locating systems
CN108152789A (zh) 利用rss信息的无源多站多目标数据关联与定位方法
KR101627419B1 (ko) 이동 노드의 위치 추정 방법 및 그 장치
CN109001706A (zh) 基于特征值最大化的多个辐射源目标被动直接定位方法
KR101582404B1 (ko) Uwb 레이더를 이용하여 목표물의 수를 카운팅 방법 및 장치
KR102150099B1 (ko) Fm 신호 기반의 pcl 시스템에서 표적 데이터를 추출하는 방법 및 장치
CN111770528A (zh) 基于信道参数萃取方法的视距与非视距识别方法及装置
Abdi et al. A hybrid RSSI based localization algorithm for WSN using a mobile anchor node
CN114745779A (zh) 一种基于异步到达时间的无线传感器网络目标定位方法
CN112534293B (zh) 用于检测信号传播类型的方法和装置
WO2020042144A1 (zh) 用于检测信号传播类型的方法和装置
Ou et al. Gaussian Processes Based Indoor Visible Light Positioning
Yi Exploring and Evaluating the Key Technologies in TDOA-Based Indoor Positioning
Utama et al. An End-to-End Deep Learning Model based on Channel Impulse Response Measurement for 2D Indoor Positioning

Legal Events

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

Ref document number: 18930106

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018930106

Country of ref document: EP

Effective date: 20210315