Target value detection for unmanned aerial vehicles

1 . A method, comprising:

receiving a first set of ultrasonic responses to first ultrasonic signals transmitted related to a position of an unmanned aerial vehicle with respect to an object using one or more transducers;

generating a confidence value of the position of the unmanned aerial vehicle with respect to the object based on a detection of a target value using the first set of ultrasonic responses;

receiving a second set of ultrasonic responses to second ultrasonic signals transmitted related to a second position of the unmanned aerial vehicle with respect to the object using the one or more transducers;

updating the confidence value using the second set of ultrasonic responses based upon the second position of the unmanned aerial vehicle with respect to the object; and

increasing the confidence value by changing the position of the unmanned aerial vehicle relative to the object.

2 . The method of claim 1 , wherein the one or more transducers includes a first transducer and a second transducer, wherein the first set of ultrasonic responses includes a first ultrasonic response received from the first transducer and a first ultrasonic response received from the second transducer, and wherein the second set of ultrasonic responses includes only a second ultrasonic response received from the second transducer.

3 . The method of claim 1 , further comprising:

using a modeling filter to identify and remove outliers in target value data included in the second set of ultrasonic responses;

responsive to removing the outliers in the target value data, determining average target value data by combining the target value data with other target value data included in the first set of ultrasonic responses; and

generating a prediction for a next target value based on the average target value data, wherein the confidence value is updated based on a comparison between the prediction and the next target value.

4 . The method of claim 1 , further comprising:

reducing a ring-down time for the one or more transducers based on a comparison of ultrasonic signal feedback to a saturation threshold.

5 . The method of claim 1 , wherein the confidence value indicates a likelihood that a position of an unmanned aerial vehicle is in an area relative to an object.

6 . The method of claim 1 , further comprising:

updating the confidence value according to a weight associated with a prediction that is generated for a next target value.

7 . The method of claim 3 , wherein the confidence value is updated with the second set of ultrasonic responses to generate a second confidence value.

8 . The method of claim 7 , wherein a third confidence value is created based on the comparison between the prediction and the next target value.

9 . An unmanned aerial vehicle comprising:

a first transducer configured to receive a first set of ultrasonic responses to first ultrasonic signals transmitted related to a position of the unmanned aerial vehicle with respect to an object using the first transducer;

a second transducer configured to receive a second set of ultrasonic responses to second ultrasonic signals transmitted related to a second position of the unmanned aerial vehicle with respect to the object using the second transducer; and

a processor that performs operations comprising:

generate a confidence value of the position of the unmanned aerial vehicle with respect to the object based on a detection of a target value using the first set of the ultrasonic responses;

update the confidence value using the second set of ultrasonic responses based upon the second position of the unmanned aerial vehicle with respect to the object; and

increase the confidence value by changing the position of the unmanned aerial vehicle relative to the object.

10 . The unmanned aerial vehicle of claim 9 , wherein the first transducer has a first beam pattern that detects a first range area and the second transducer has a second beam pattern that detects a second range area.

11 . The unmanned aerial vehicle of claim 9 , wherein the processor further performs the operations comprising:

use a modeling filter to identify and remove outliers in target value data included in the second set of ultrasonic responses;

responsive to removing the outliers in the target value data, determining average target value data by combining the target value data with other target value data included in the first set of ultrasonic responses; and

generating a prediction for a next target value based on the average target value data, wherein the confidence value is updated based on a comparison between the prediction and the next target value.

12 . The unmanned aerial vehicle of claim 10 , wherein the first range area and the second range area are overlapping.

13 . The unmanned aerial vehicle of claim 10 , wherein the second range area is larger than the first range area.

14 . The unmanned aerial vehicle of claim 11 , wherein the confidence value is updated with the second set of ultrasonic responses to generate a second confidence value, and a third confidence value is created based on the comparison of between the prediction and the next target value.

15 . A non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receive a first set of ultrasonic responses to first ultrasonic signals transmitted related to a position of an unmanned aerial vehicle with respect to an object using one or more transducers;

generate a confidence value of the position of the unmanned aerial vehicle with respect to the object based on a detection of a target value using the first set of ultrasonic responses;

receive a second set of ultrasonic responses to second ultrasonic signals transmitted related to a second position of the unmanned aerial vehicle with respect to the object using the one or more transducers;

update the confidence value using the second set of ultrasonic responses based upon the second position of the unmanned aerial vehicle with respect to the object; and

increase the confidence value by changing the position of the unmanned aerial vehicle relative to the object.

16 . The non-transitory computer-readable storage medium of claim 15 , wherein the one or more transducers includes a first transducer and a second transducer, wherein the first set of ultrasonic responses includes a first ultrasonic response received from the first transducer and a first ultrasonic response received from the second transducer, and wherein the second set of ultrasonic responses includes only a second ultrasonic response received from the second transducer.

17 . The non-transitory computer-readable storage medium of claim 15 , further comprising:

use a modeling filter to identify and remove outliers in target value data included in the second set of ultrasonic responses;

responsive to removing the outliers in the target value data, determining average target value data by combining the target value data with other target value data included in the first set of ultrasonic responses; and

generate a prediction for a next target value based on the average target value data, wherein the confidence value is updated based on a comparison between the prediction and the next target value.

18 . The non-transitory computer-readable storage medium of claim 15 , wherein if the confidence value indicated a high confidence the confidence value indicates detection with the first set of ultrasonic responses and the second set of ultrasonic responses.

19 . The non-transitory computer-readable storage medium of claim 18 , wherein the first set of ultrasonic responses are transmitted with a first transducer of the one or more transducers and the second set of ultrasonic responses are transmitted with a second transducer of the one or more transducers.

20 . The non-transitory computer-readable storage medium of claim 19 , wherein the first transducer has a first beam pattern that detects a first range area and the second transducer has a second beam pattern that detects a second range area.