Techniques for determination of a motion state of a mobile device

Patent metadata

Field	Value
Publication number	US-10539586-B2
Application number	US-201213619143-A
Country	US
Kind code	B2
Filing date	Sep 14, 2012
Priority date	Sep 16, 2011
Publication date	Jan 21, 2020
Grant date	Jan 21, 2020

Abstract

Systems and methods herein enable a mobile device to detect that a user is traveling in association with a vehicle based at least on motion data. In some embodiments, accelerometer data is used. Motion data is leveraged in combination with various observations regarding vehicular movement to determine whether or not a mobile device is located in or on the vehicle. For instance, before entering the state of vehicular movement, it can be determined that the user is first in a walking state (e.g., walking to the car, bus, etc., and entering it). Likewise, after exiting the state of vehicular movement, the user re-enters the walking state (e.g., after stepping out of the car, bus, etc., the user again begins walking). Further, it can be determined that when the user is in the walking state, the accelerometer signals appear different to any accelerometer signals seen in the vehicular movement state.

First claim

What is claimed is:

1. A method for detecting motion states of a mobile device in connection with vehicular travel comprising:
obtaining motion data from one or more motion-detecting devices of the mobile device; and
at the mobile device, filtering the motion data to determine motion states, the motion states comprising one or more pedestrian motion states and a plurality of vehicular motion states, the one or more pedestrian motion states comprising a walk state, and the plurality of vehicular motion states comprising a vehicular stop state and a vehicular move state;
wherein the walk state indicates that the mobile device is in motion indicative of a user walking with the mobile device, the vehicular stop state indicates that the mobile device is in motion indicative of the mobile device being in a stationary vehicle, and the vehicular move state indicates that the mobile device is in a moving vehicle;
wherein the motion states are obtained for respective time intervals during which the motion data is obtained from the one or more motion-detecting devices;
wherein, during the filtering, transitions from the one or more pedestrian motion states to the plurality of vehicular motion states are restricted to transitions from the walk state to the vehicular stop state and transitions from the plurality of vehicular motion states to the one or more pedestrian motion states are restricted to transitions from the vehicular stop state to the walk state;
determining, based on the filtering, that a present motion state of the mobile device is the vehicular move state; and
controlling, by a processor of the mobile device, an operation of a device or software application in response to the determining that the present motion state is the vehicular move state, wherein the device or software application is an application executing on the mobile device or a remote device communicatively coupled to the mobile device through a network.

2. The method of claim 1 further comprising computing respective likelihoods that the mobile device was in the one or more pedestrian motion states or the plurality of vehicular motion states for the respective time intervals.

3. The method of claim 2 wherein computing the respective likelihoods comprises computing likelihoods that the mobile device was in the one or more pedestrian motion states or the plurality of vehicular motion states for the respective time intervals based on a state machine that comprises the one or more pedestrian motion states and the plurality of vehicular motion states.

4. The method of claim 3 wherein the state machine includes an extended state machine comprising one or more sub-states for states of the one or more pedestrian motion states and states of the plurality of vehicular motion states, and computing the respective likelihoods further comprises transitioning the mobile device state through at least one sub-state of a particular pedestrian motion state or vehicular motion state prior to transitioning to a different pedestrian motion state or vehicular motion state.

5. The method of claim 4 wherein a number of sub-states associated with the one or more pedestrian motion states and the plurality of vehicular motion states is based, at least in part, on an anticipated time spent in a state of the one or more pedestrian motion states and the plurality of vehicular motion states.

6. The method of claim 2 wherein the filtering comprises filtering the computed respective likelihoods using at least one of a forward-backward algorithm or a Viterbi algorithm.

7. The method of claim 2 wherein computing the respective likelihoods comprises:
obtaining sensor data from at least one of a Wi-Fi receiver, an audio input device, and a GPS receiver; and
computing the respective likelihoods based on the motion data and the sensor data.

8. The method of claim 1 wherein the motion data includes accelerometer data, and the one or more motion-detecting devices includes one or more accelerometers.

9. The method of claim 8 wherein the motion data only includes the accelerometer data.

10. The method of claim 8 wherein the filtering is based on a probabilistic model including the one or more pedestrian states and the plurality of vehicular motion states.

11. The method of claim 1 wherein the filtering comprises:
identifying a first transition from the walk state to an interim state and a second transition from the interim state to one of the plurality of vehicular motion states; and
classifying the interim state as the vehicular stop state.

12. The method of claim 1 wherein the filtering comprises:
buffering the motion data for a buffer time interval; and
obtaining the motion states for the respective time intervals based at least in part on the buffered motion data.

13. The method of claim 1 wherein the determining the present motion state is based on a most likely state transition determined from a sequence of most likely state transitions between the respective time intervals.

14. The method of claim 1 wherein the determining the present motion state is based on an estimated probability determined from respective state transitions between the respective time intervals.

15. The method of claim 14 , wherein the determining the present motion state is based on further calculating a confidence score determined based on comparing two or more probabilities determined from a state transitions between two of the respective time intervals.

16. The method of claim 15 wherein:
calculating the confidence score further comprises identifying a difference between the two or more probabilities; and
the method further comprises:
comparing the difference to a confidence threshold; and
upon determining that the difference does not meet the confidence threshold, determining the present motion state as a default state or an unknown state.

17. A mobile device for detecting motion states of a mobile device in connection with vehicular travel comprising:
one or more motion detectors of the mobile device configured to generate motion data;
a state machine module comprising one or more pedestrian motion states and a plurality of vehicular motion states, the one or more pedestrian motion states comprising a walk state and the plurality of vehicular motion states comprising a vehicular stop state and a vehicular move state;
wherein the walk state indicates that the mobile device is in motion indicative of a user walking with the mobile device, the vehicular stop state indicates that the mobile device is in motion indicative of the mobile device being in a stationary vehicle, and the vehicular move state indicates that the mobile device is in a moving vehicle;
a filtering module communicatively coupled to the state machine module and configured to filter, at the mobile device, the motion data to determine motion states,
wherein the motion states are obtained for respective time intervals during which the motion data is obtained from the one or more motion detectors devices;
wherein, within the state machine module, transitions from the one or more pedestrian motion states to the plurality of vehicular motion states are restricted to transitions from the walk state to the vehicular stop state and transitions from the plurality of vehicular motion states to the one or more pedestrian motion states are restricted to transitions from the vehicular stop state to the walk state;
wherein the state machine module is further configured to determine, based on filtering by the filtering module, that a present motion state of the mobile device is the veh

Assignees

• Grokop Leonard Henry
• Dhingra Bhuwan
• Qualcomm Inc

Inventors

• Grokop Leonard Henry
• Dhingra Bhuwan

Classifications

• H04W4/027 Primary

  using movement velocity, acceleration information · CPC title

• H04M2250/12

  including a sensor for measuring a physical value, e.g. temperature or motion · CPC title

• G01P13/00 Primary

  Indicating or recording presence, absence, or direction, of movement (electric switches H01H; counting moving objects G06M7/00) · CPC title

• H04M1/72569

  Electricity · mapped topic

• H04M1/72454 Primary

  according to context-related or environment-related conditions · CPC title