Systems and methods for sidewalk detection for personal mobility vehicles

Patent metadata

Field	Value
Publication number	US-11797089-B2
Application number	US-201916588408-A
Country	US
Kind code	B2
Filing date	Sep 30, 2019
Priority date	Jul 29, 2019
Publication date	Oct 24, 2023
Grant date	Oct 24, 2023

Abstract

The disclosed system may include a non-transitory memory and one or more hardware processors configured to execute instructions from the non-transitory memory to perform operations including (1) determining one or more vibration signals detected by a personal mobility vehicle, (2) determining that the one or more vibration signals correspond to a particular type of pathway for the personal mobility vehicle, (3) generating a feedback signal corresponding to the particular type of pathway, and (4) transmitting the feedback signal corresponding to the particular type of pathway. Various other methods, systems, and computer-readable media are also disclosed.

First claim

What is claimed is:

1. A system comprising:
a non-transitory memory comprising computer-readable instructions; and
one or more hardware processors configured to execute the instructions from the non-transitory memory to perform operations comprising:
determining one or more vibration signals detected by a personal mobility vehicle;
determining that the one or more vibration signals correspond to a particular type of pathway for the personal mobility vehicle, wherein the determining comprises:
calculating, based on the one or more vibration signals and a weight or position of a user operating the personal mobility vehicle, a probability that the one or more vibration signals correspond to a sidewalk; and
determining whether the probability exceeds a threshold probability;

generating a feedback signal corresponding to the particular type of pathway; and
transmitting the feedback signal corresponding to the particular type of pathway.

2. The system of claim 1 , wherein determining the one or more vibration signals comprises determining:
frequencies of the one or more vibration signals detected by the personal mobility vehicle; and
magnitudes of the one or more vibration signals detected by the personal mobility vehicle.

3. The system of claim 2 , wherein:
a seam between two sections of the sidewalk introduces at least one particular vibration signal, of the one or more vibration signals detected by the personal mobility vehicle, into the personal mobility vehicle when the personal mobility vehicle moves over the seam; and
determining that the one or more vibration signals correspond to the sidewalk based on a magnitude of the particular vibration signal within the personal mobility vehicle exceeding a threshold magnitude.

4. The system of claim 3 , wherein determining that the one or more vibration signals correspond to the sidewalk further comprises determining that the particular vibration signal is introduced into the personal mobility vehicle on a periodic basis.

5. The system of claim 1 , wherein the operations further comprise:
using a power spectrum analysis with the one or more vibration signals; and
isolating the one or more vibration signals that correspond to the particular type of pathway from other vibration signals that correspond to pathways different from the particular type of pathway.

6. The system of claim 1 , wherein the operations further comprise isolating the one or more vibrations signals that correspond to the particular type of pathway from other vibration signals that correspond to a resonant frequency of the personal mobility vehicle.

7. The system of claim 1 , wherein determining that the one or more vibration signals correspond to the particular type of pathway further comprises providing, to a machine learning algorithm trained to identify various types of pathways, at least a portion of the vibration signals detected by the personal mobility vehicle and the weight or position of the user.

8. The system of claim 7 , wherein determining that the one or more vibration signals correspond to the particular type of pathway further comprises implementing at least a portion of the machine learning algorithm within hardware integrated into the personal mobility vehicle.

9. The system of claim 8 , wherein determining that the one or more vibration signals correspond to the particular type of pathway further comprises:
extracting, by the portion of the machine learning algorithm, a set of features from the one or more vibration signals detected by the personal mobility vehicle and the weight or position of the user; and
sending the set of features to a remote server that implements an additional portion of the machine learning algorithm.

10. The system of claim 1 , wherein:
determining the one or more vibration signals detected by the personal mobility vehicle comprises determining vibration signals detected by the personal mobility vehicle during a plurality of time intervals while the personal mobility vehicle is moving from a starting location to a destination; and
determining that the one or more vibration signals correspond to the particular type of pathway further comprises detecting, based on a real-time analysis of the one or more vibration signals, that the one or more vibration signals correspond to the sidewalk during at least one of the plurality of time intervals.

11. The system of claim 1 , wherein the one or more hardware processors are further configured to execute the instructions from the non-transitory memory to perform operations comprising:
collecting information corresponding to a plurality of classifications of pathways as sidewalks made using the threshold probability;
calculating a rate of inaccurate classifications made using the threshold probability; and
increasing the threshold probability based at least in part on determining that the rate of inaccurate classifications exceeds a threshold rate.

12. The system of claim 1 , wherein:
determining that the one or more vibration signals correspond to the particular type of pathway further comprises determining that the one or more vibration signals correspond to the sidewalk;
generating the feedback signal comprises generating an audiovisual display that prompts a user operating the personal mobility vehicle to move the personal mobility vehicle to a road that is intended for use by personal mobility vehicles; and
transmitting the feedback signal comprises rendering the audiovisual display within a user interface displayed to the user.

13. The system of claim 1 , wherein:
determining that the one or more vibration signals correspond to the particular type of pathway further comprises determining that the one or more vibration signals correspond to the sidewalk;
generating the feedback signal comprises generating an instruction that prevents a velocity of the personal mobility vehicle from exceeding a threshold velocity; and
transmitting the feedback signal comprises transmitting the instruction to a processing unit that controls the velocity of the personal mobility vehicle.

14. The system of claim 1 , wherein:
determining that the one or more vibration signals correspond to the particular type of pathway further comprises determining that the one or more vibration signals correspond to the sidewalk;
generating the feedback signal comprises identifying a geographic location of at least a portion of the sidewalk; and
transmitting the feedback signal comprises transmitting the geographic location to a database that provides maps for users operating personal mobility vehicles.

15. A non-transitory computer-readable medium comprising computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:
determine one or more vibration signals detected by a personal mobility vehicle;
determine that the one or more vibration signals correspond to a particular type of pathway for the personal mobility vehicle, wherein the determining comprises:
calculating, based on the one or more vibration signals and a weight or position of a user operating the personal mobility vehicle, a probability that the one or more vibration signals correspond to a sidewalk; and
determining whether the probability exceeds a threshold probability;

generate a feedback signal corresponding to the particular type of pathway; and
transmit the feedback signal corresponding to the particular type of pathway.

16. A method comprising:
determining one or more vibration signals detected by a personal mobility vehicle;
determining t

Assignees

• Lyft Inc

Inventors

• Drayna Garrett Korda

Classifications

• G06F3/016 Primary

  Input arrangements with force or tactile feedback as computer generated output to the user · CPC title

• B62K5/007

  power-driven · CPC title

• B62K5/025

  power-driven · CPC title

• G06F3/017

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G08B6/00

  Tactile signalling systems, e.g. tactile personal calling systems · CPC title