Apparatus and method for estimating a physical state of a movable object

Patent metadata

Field	Value
Publication number	US-11922330-B2
Application number	US-202016990440-A
Country	US
Kind code	B2
Filing date	Aug 11, 2020
Priority date	Feb 15, 2018
Publication date	Mar 5, 2024
Grant date	Mar 5, 2024

Abstract

An apparatus for estimating a physical state of a movable object includes a processor receiving or determining a probability mass function including probabilities for each of a first group of at least two movement classes, wherein the movement models of the first group being determined using sensor data from the inertial measurement unit. The processor receives at least one additional probability mass function associated with a second group of at least two movement classes, wherein the additional probability mass function has been obtained using additional information different from the sensor data. The processor combines the probability mass function and the at least one additional probability mass function to obtain a combined probability mass function over the movement classes of the first group and the second group, selects a movement class having the highest probability from the combined probability mass function, and estimates the physical state of the movable object using a movement model of the selected movement class. Each movement class is either a movement state or a movement model.

First claim

The invention claimed is:

1. An apparatus for estimating a physical state of a movable object, the apparatus comprising a processor, wherein the processor is configured to receive or determine a probability mass function comprising probabilities for each movement class of a first group of at least two movement classes, wherein the movement classes of the first group being determined using sensor data from the inertial measurement unit of the movable object;
receive at least one additional probability mass function associated with a second group of at least two movement classes, wherein the additional probability mass function has been acquired using additional information different from the sensor data; combine the probability mass function and the at least one additional probability mass function to acquire a combined probability mass function over the movement classes of the first group and the second group;
select a movement class comprising the highest probability from the combined probability mass function; and estimate the physical state of the movable object using a movement model of the selected movement class, wherein each movement class is either a movement state or a movement model, and wherein the additional information different from the sensor data concerns information from other devices in the vicinity of the object determined via device to device (D2D) data exchanged directly with the other devices.

2. The apparatus of claim 1 , wherein sensor data additionally comprise data acquired from at least one of a magnetometer, a barometer, a temperature sensor, a microphone, a GPS receiver, a wireless local area network receiver, and a Bluetooth receiver.

3. The apparatus of claim 1 , wherein the processor is configured to acquire one or more quality measures each indicating a quality of one the probability mass functions, and wherein the processor is configured to use the quality measure in combining the probability mass function and the additional probability mass function such that a probability mass function comprising a higher quality is weighted higher than a probability mass function comprising a lower quality.

4. The apparatus of claim 3 , wherein the processor is configured to estimate the physical state to reveal a variance of the physical state, wherein the variance depends on the quality measure, wherein a larger variance is achieved for a lower quality measure and a smaller variance is achieved for higher quality measures.

5. The apparatus of claim 3 , wherein the processor is configured to combine the probability mass functions by calculating a weighted normalized sum of the probability mass functions.

6. The apparatus of claim 3 , wherein the processor is configured to receive each quality measure from an entity different of the movable object.

7. The apparatus of claim 3 , wherein at least one of the quality measures depends on at least one of the type of the movable object and the type of the information source.

8. A system comprising an apparatus for estimating a physical state of a movable object, the apparatus comprising a processor, wherein the processor is configured to receive or determine a probability mass function comprising probabilities for each movement class of a first group of at least two movement classes, wherein the movement classes of the first group being determined using sensor data from the inertial measurement unit, receive at least one additional probability mass function associated with a second group of at least two movement classes, wherein the additional probability mass function has been acquired using additional information different from the sensor data; combine the probability mass function and the at least one additional probability mass function to acquire a combined probability mass function over the movement classes of the first group and the second group; select a movement class comprising the highest probability from the combined probability mass function; and estimate the physical state of the movable object using a movement model of the selected movement class, wherein each movement class is either a movement state or a movement model, and wherein the additional information different from the sensor data concerns information from other devices in the vicinity of the object determined via device to device (D2D) data exchanged directly with the other devices; and at least one information source, wherein the at least one information source is configured to transmit the probability mass function, the additional probability mass function or the at least one additional probability mass function to the apparatus.

9. A method for estimating a physical state of a movable object, the movable object comprising an inertial measurement unit, the method comprising: receiving a probability mass function comprising probabilities for each movement class of a first group of at least two movement classes, wherein the movement classes of the first group being determined using sensor data from the inertial measurement unit; receiving at least one additional probability mass function associated with a second group of at least two movement classes, wherein the additional probability mass function has been acquired using additional information different from the sensor data; combining the probability mass function and the additional probability mass function to acquire a combined probability mass function over the movement classes of the first group and the second group; selecting a movement class comprising the highest probability from the combined probability mass function; and
estimating the physical state of the movable object using a movement model of the selected movement class, wherein each movement class is either a movement state or a movement model, and wherein the additional information different from the sensor data concerns information from other devices in the vicinity of the object determined via device to device (D2D) data exchanged directly with the other devices.

10. The method of claim 9 , wherein sensor data additionally comprise data acquired from at least of a magnetometer, a barometer, a temperature sensor, a microphone, a GPS receiver, a wireless local area network receiver, and a Bluetooth receiver.

11. The method of claim 9 , further comprising transmitting the probability mass function, the additional probability mass function or the at least one additional probability mass function via a radio communication link.

12. The method of claim 9 , further comprising: receiving one or more quality measures each indicating a quality of one the probability mass functions, wherein the quality measure is used in combining the probability mass function and the additional probability mass function such that a probability mass function comprising a higher quality is weighted higher than a probability mass function comprising a lower quality.

13. The method of claim 12 , wherein estimating the physical state reveals a variance of the physical state, wherein the variance depends on the quality measure, wherein a larger variance is achieved for a lower quality measure and a smaller variance is achieved for higher quality measures.

14. The method of claim 12 , wherein combining the probability mass functions comprises calculating a weighted normalized sum of the probability mass functions.

15. The method of claim 12 , wherein each quality measure is received from an entity different of the movable object.

16. The method of claim 12 , wherein at least one of the quality measures depends on at least one of the type of the movable object and the type of the information sour

Assignees

• Fraunhofer Ges Forschung

Inventors

• Franke Norbert
• Kram Sebastian
• Nickel Christian
• Seitz Jochen
• Alawieh Mohammad

Classifications

• G06N5/04 Primary

  Inference or reasoning models · CPC title

• G01C21/28

  with correlation of data from several navigational instruments · CPC title

• G01S19/25

  involving aiding data received from a cooperating element, e.g. assisted GPS · CPC title

• G01S19/252

  Employing an initial estimate of location in generating assistance data · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title