Integrated communication kit for autonomous robots
A method is disclosed for controlling an autonomous robot. The method detects one or more signals received from one or more sensors on a user. The one or more signals can correspond to gestures associated with the user. The method determines a derivate of a signal of the one or more signals associated with a sensor of the one or more sensors. The method further determines a motion epoch associated with the gestures based on a filtered version of the derivative of the signal. The method further determines a predicted gesture corresponding to the motion epoch using a gesture prediction model. And the method sends one or more control signals to the autonomous robot in response to the predicted gesture.
1 . A wearable remote-control apparatus comprising:
one or more sensors configured to detect motion of the wearable remote-control apparatus;
a memory storing computer readable instructions, the computer readable instructions comprising:
gesture prediction module instructions, and
encoding the gesture prediction module instructions; and
at least one processor configured to execute one or more computer executable instructions to:
detect one or more signals received from the one or more sensors wherein the one or more signals correspond to gestures associated with a user;
determine a derivative of a magnitude of acceleration of a signal of the one or more signals associated with a sensor of the one or more sensors, wherein the magnitude of acceleration is based on an output of an accelerometer on each axis of a cartesian coordinate system;
determine a motion epoch associated with the gestures based on a filtered version of the derivative of the signal;
determine a predicted gesture corresponding to the motion epoch using a gesture prediction model; and
send one or more control signals to an autonomous robot in response to the predicted gesture, wherein the control signals are configured to cause the autonomous robot to perform physical movements.
2 . The wearable remote-control apparatus of claim 1 , wherein the one or more sensors comprise a gyroscope, and magnetometer.
3 . The wearable remote-control apparatus of claim 2 , wherein the signal is an accelerometer signal generated by the accelerometer.
4 . The wearable remote-control apparatus of claim 1 , wherein the gestures comprise a plurality of motion epochs.
5 . The wearable remote-control apparatus of claim 1 , wherein the filtered version of the derivative of the signal is an output of a Gaussian low pass filter.
6 . A method controlling an autonomous robot, the method comprising:
detecting one or more signals received from one or more sensors on a user, wherein the one or more signals correspond to gestures associated with the user;
determining a derivative of a magnitude of acceleration of a signal of the one or more signals associated with a sensor of the one or more sensors, wherein the magnitude of acceleration is based on an output of an accelerometer on each axis of a cartesian coordinate system;
determining a motion epoch associated with the gestures based on a filtered version of the derivative of the signal;
determining a predicted gesture corresponding to the motion epoch using a gesture prediction model; and
sending one or more control signals to the autonomous robot in response to the predicted gesture, wherein the control signals are configured to cause the autonomous robot to perform physical movements.
7 . The method of claim 6 , wherein the one or more sensors comprise a gyroscope, and magnetometer.
8 . The method of claim 7 , wherein the signal is an accelerometer signal generated by the accelerometer.
9 . The method of claim 6 , wherein the gestures comprise a plurality of motion epochs.
10 . The method of claim 6 , wherein the filtered version of the derivative of the signal is an output of a Gaussian low pass filter.
11 . A system for controlling an autonomous robot, the system comprising:
the autonomous robot;
a wearable device on a user comprising:
one or more sensors embedded in the wearable device,
at least one memory storing instructions for detecting one or more gestures, and at least one processor configured to execute the instructions thereby causing the at least one processor to:
detect one or more signals received from the one or more sensors wherein the one or more signals correspond to gestures associated with a user;
determine a derivative of a magnitude of acceleration of a signal of the one or more signals associated with a sensor of the one or more sensors, wherein the magnitude of acceleration is based on an output of an accelerometer on each axis of a cartesian coordinate system;
determine a motion epoch associated with the gestures based on a filtered version of the derivative of the signal;
determine a predicted gesture corresponding to the motion epoch using a gesture prediction model; and
send one or more control signals to the autonomous robot in response to the predicted gesture, wherein the control signals are configured to cause the autonomous robot to perform physical movements.
12 . System of claim 11 , wherein the one or more sensors comprise a gyroscope, and magnetometer.
13 . The system of claim 12 , wherein the signal is an accelerometer signal generated by the accelerometer.
14 . The system of claim 11 , wherein the gestures comprise a plurality of motion epochs.
15 . The system of claim 11 , wherein the filtered version of the derivative of the signal is an output of a Gaussian low pass filter.