Methods and systems for reducing false alarms in a robotic device by sensor fusion

Abstract

The present technology generally relates to robotics. More specifically, the present technology relates to systems and methods for reducing false alarms by a mobile robotic device using data collected by sensors in the robotic device. An example of the technology may include receiving sensor data at one or more sensors; determining a first portion of the sensor data that matches one or more positive logic patterns of the set of positive logic patterns; determining a second portion of the sensor data that matches one or more negative logic patterns of the set of negative logic patterns; determining a third portion of sensor data that does not match any positive logic patterns of the set of positive logic patterns or negative logic patterns of the set of negative logic patterns; generating an alarm decision; receiving an input indicating that the alarm decision was incorrect; linking the alarm decision and the input to each other; and transmitting the linked alarm decision and input to the second pattern library based on the input.

1 . (canceled) 
     
     
         2 . A computer-implemented method, the method comprising:
 receiving, at one or more sensors of a robotic device, a first set of data associated with an environment;   analyzing the received first set of data to determine if the data indicates that a person is within a predetermined range of the robotic device;   identifying that the person is a target of the robotic device in response to determining that the data indicates that the person is within the predetermined range, wherein a target includes an object that the robotic device intends to follow;   determining a first location of the person using the received first set of data;   determining a second location of the person using a second set of data captured by the one or more sensors;   determining, using the first location and the second location, that the person has moved more than a predetermined threshold distance;   adjusting at least one of a direction and a speed of the robotic device based on the second location of the person;   analyzing the first set of data and the second set of data to identify one or more objects within the environment; and   applying the one or more objects to a map of the environment.