Systems and methods for robotic behavior around moving bodies
Systems and methods for detection of people are disclosed. In some exemplary implementations, a robot can have a plurality of sensor units. Each sensor unit can be configured to generate sensor data indicative of a portion of a moving body at a plurality of times. Based on at least the sensor data, the robot can determine that the moving body is a person by at least detecting the motion of the moving body and determining that the moving body has characteristics of a person. The robot can then perform an action based at least in part on the determination that the moving body is a person.
1. A system for detecting motion of a moving body, comprising:
at least one processor coupled to a non-transitory memory and at least one sensor, the non-transitory memory comprising computer readable instructions stored thereon, the at least one processor configured to execute the computer readable instructions to,
measure, using a first sensor of the at least one sensor, a distance from the first sensor to a moving body along a horizontal plane, the moving body comprises first and second objects, wherein each of the first and second objects are represented by substantially tubular portions on the horizontal plane, and the first and second objects are separated by less than or equal to a threshold distance;
detect a gait pattern of the moving body based on the first object being in motion and the second object being stationary along the horizontal plane at a first instance in time, and when the second object is in motion and the first object is stationary along the horizontal plane at a different second instance in time;
determine the moving body corresponds to a human upon detecting the gait pattern of the substantially tubular portions of each of the first and second objects; and
transmit a signal to at least one actuator on a robotic device upon determining the moving body corresponds to the human, the signal corresponding to the robotic device performing an action;
wherein, the first sensor comprises a light detection and ranging sensor (“LiDAR”).
2. The system of claim 1 , wherein the at least one processor is further configured to execute the computer readable instructions to,
determine a first intersection point on the moving body by the first sensor and a second intersection point on the moving body by a second sensor, and
determine the first intersection point and second intersection point both correspond to a continuous body based on horizontal distance from the robotic device to the first intersection point and horizontal distance from the robotic device to the second intersection point are similar.
3. The system of claim 2 , wherein the second sensor is separated apart from the first sensor, the second sensor comprises a planar LIDAR positioned at an angle with respect to the horizontal plane of the first sensor.
4. The system of claim 1 , wherein the at least one processor is further configured to execute the computer readable instructions to,
distinguish the moving body from stationary objects at least in part on a map of the environment, the stationary objects corresponds to walls, floors and other stationary objects in a field of view of the robotic device.
5. The system of claim 1 , wherein the action includes at least one of the robotic device stopping, slowing down, or adjusting its trajectory.
6. A method for detecting motion of a moving body, comprising:
measuring, using a first sensor of the at least one sensor, a distance from the first sensor to a moving body along a horizontal plane, the moving body comprises first and second objects, wherein each of the first and second objects are represented by substantially tubular portions on the horizontal plane, and the first and second objects are separated by less than or equal to a threshold distance;
detecting a gait pattern of the moving body based on the first object being in motion and the second object being stationary along the horizontal plane at a first instance in time, and when the second object is in motion and the first object is stationary along the horizontal plane at a different second instance in time;
determining the moving body corresponds to a human upon detecting the gait pattern of the substantially tubular portions of each of the first and second objects; and
transmitting a signal to at least one actuator on a robotic device upon determining the moving body corresponds to the human, the signal corresponding to the robotic device performing an action;
wherein, the first sensor includes a light detection and ranging sensor (“LiDAR”).
7. The method of claim 6 , further comprising:
determining a first intersection point on the moving body by the first sensor and a second intersection point on the moving body by a second sensor, and
determining the first intersection point and second intersection point both correspond to a continuous body based on horizontal distance from the robotic device to the first intersection point and horizontal distance from the robotic device to the second intersection point are similar.
8. The method of claim 6 , further comprising:
distinguishing the moving body from stationary objects at least in part on a map of the environment, the stationary objects corresponds to walls, floors and other stationary objects in a field of view of the robotic device.
9. The method of claim 6 , further comprising:
determining the moving body corresponds to a column shape body based on receiving data simultaneously from both the first sensor and a second sensor.
10. A non-transitory computer readable medium having computer readable instructions stored thereon, that when executed by at least one processor configure the at least one processor to,
measure, using a first sensor of the at least one sensor, a distance from the first sensor to a moving body along a horizontal plane, the moving body comprises first and second objects, wherein each of the first and second objects are represented by substantially tubular points on the horizontal plane, and the first and second objects are separated by less than or equal to a threshold distance;
detect a gait pattern of the moving body based on the first object being in motion and the second object being stationary along the horizontal plane at a first instance in time, and when the second object is in motion and the first object is stationary along the horizontal plane at a different second instance in time;
determine the moving body corresponds to a human upon detecting the gait pattern of the substantially tubular portions of each of the first and second objects; and
transmit a signal to at least one actuator on a robotic device upon determining the moving body corresponds to the human, the signal corresponding to the robotic device performing an action;
wherein, the first sensor includes a light detection and ranging sensor (“LiDAR”).
11. The non-transitory computer readable medium of claim 10 , wherein the instructions further configure the at least one processor to:
determine a first intersection point on the moving body by the first sensor and a second intersection point on the moving body by a second sensor, and
determine the first intersection point and second intersection point both correspond to a continuous body based on horizontal distance from the robotic device to the first intersection point and horizontal distance from the robotic device to the second intersection point are similar.
12. The non-transitory computer readable medium of claim 10 , wherein the instructions further configure the at least one processor to:
distinguish the moving body from stationary objects at least in part on a map of the environment, the stationary objects corresponds to walls, floors and other stationary objects in a field of view of the robotic device.
13. The non-transitory computer readable medium of claim 10 , wherein the instructions further configure the at least one processor to:
determine the moving body corresponds to a column shape body based on receiving data simultaneously from both the first sensor and a second sensor.