Indoor navigation with wearable passive sensors

• US 6,323,807 B1
• Filed: 02/17/2000
• Issued: 11/27/2001
• Est. Priority Date: 02/17/2000
• Status: Expired due to Fees

• Current Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Original Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Inventors: Golding, Andrew R., Lesh, Neal B.
• Primary Examiner(s): Blum, Theodore M.
• Application Number:
  US09/506,480
• Time in Patent Office: 649 Days
• Field of Search: 342/419, 342/457, 701/207
• US Class Current: 342/419
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01S 2205/02 Indoor
• CPC Class Codes: G01S 5/02 using radio waves using satellite radio beacon systems for determining position G01S19/00

Abstract

A wearable device is configured for navigating in an indoor environment. The device includes passive sensors for measuring environmental physical conditions at known locations in the indoor environment and at an unknown locations in the indoor environment. A wearable computer is coupled to passive sensors. The computer is configured to construct a first statistical model of the environment according to the measured physical conditions at the known locations and a second statistical model of the environment according to the measured physical conditions at the unknown locations. Processing means of the computer determines a probability that the unknown locations correspond to the known locations by comparing the second statistical model to the first statistical model.

Claims

1. A method for navigating in an indoor environment using a weareable computer device having a plurality of sensors, comprising the steps of:

measuring a plurality of environmental physical conditions with passive sensors at a plurality of known locations in the environment;

constructing a first statistical model of the environment according to the measured physical conditions;

measuring the plurality of environmental physical conditions at unknown locations in the environment;

constructing a second statistical model of the environment according to the measured physical conditions;

determining a probability that the unknown location corresponds to any of the known locations by comparing the second statistical model to the first statistical model.

2. The method of claim 1 wherein the plurality of passive sensors include an accelerometer, a magnetometer, a light detector, and a temperature sensor.

3. The method of claim 1 wherein the statistical model represents the measured physical conditions as Gaussian probability distribution functions.

4. The method of claim 1 wherein navigation is performed by determining a probability of transitioning between the locations according to the statistical model.

5. The method of claim 1 wherein the measured physical conditions at each location l are given as readings are S={s_l, . . . , s_n}, and a posterior probability that the unknown location is the known location l is estimated using Baye'"'"'s rule with a conditional independence assumption:

$P<br><br>\left(l|〈<br><br>s_1,\mathrm{\dots <br><br>}<br><br>\text{\hspace{1em}<br><br>},s_n〉<br><br>\right)=\left(\underset{1\le <br><br>i\le <br><br>n}{\prod <br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>P<br><br>\left(s_i|l\right)\right)<br><br>\frac{P<br><br>\left(l\right)}{P<br><br>\left(〈<br><br>s_1,\mathrm{\dots <br><br>}<br><br>\text{\hspace{1em}<br><br>},s_n〉<br><br>\right)}$

where P(s_i|l) terms are determined from the first statistical model.

6. The method of claim 4 wherein the probability of transitioning between locations uses dead-reckoning information obtained from an accelerometer.

7. The method of claim 1 further comprising the step of:

extracting, high level features from the measured physical conditions.

8. The method of claim 1 wherein the plurality of passive sensors are non-directional.

9. The method of claim 1 wherein the environment includes radio frequency transponders, and wherein the passive sensors include a radio receiver.

10. The method of claim 1 wherein the first and second statistical models only consider measured physical conditions within a predetermined range.

11. An apparatus for navigating in an indoor environment, comprising:

a plurality of passive sensors for measuring a plurality of environmental physical conditions at a plurality of known locations in the indoor environment, and at an unknown location in the indoor environment;

a wearable computer device coupled to the plurality of passive sensors configured to construct a first statistical model of the environment according to the measured physical conditions at the plurality of known locations and a second statistical model of the environment according to the measured physical conditions at the unknown locations; and

means for determining a probability that the unknown location corresponds to one of the known locations by comparing the second statistical model to the first statistical model.