Apparatus and method for deploying sensors

• US 9,798,327 B2
• Filed: 01/08/2016
• Issued: 10/24/2017
• Est. Priority Date: 01/08/2016
• Status: Active Grant

• Current Assignee: King Fahd University Of Petroleum And Minerals
• Original Assignee: King Fahd University Of Petroleum And Minerals
• Inventors: Albaghajati, Anas Mohammed, Nasir, Mohammad Tariq, Ghouti, Lahouari, El Ferik, Sami
• Primary Examiner(s): Bendidi, Rachid
• Application Number:
  US14/990,840
• Publication Number:
  US 20170199525A1
• Time in Patent Office: 655 Days
• CPC Class Codes: G01V 1/003 Seismic data acquisition in general, e.g. survey design G01V1/3808, G01V1/42 take precedence
• CPC Class Codes: G01V 1/166 Arrangements for coupling receivers to the ground
• CPC Class Codes: G01V 1/168 Deployment of receiver elements G01V1/3843 takes precedence
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs
• CPC Class Codes: H04B 7/18523 Satellite systems for providing broadcast service to terrestrial stations, i.e. broadcast satellite service arrangements specially adapted for satellite broadcast receiving H04H40/90; picture transmission via satellite H04N1/00103; television transmission via satellite H04N7/20
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/024 Guidance services
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

Described herein a robot assisted method of deploying sensors in a geographic region. The method of deploying sensors is posed as a Markovian decision process. The robot assigns each grid cell in a map of the geographic region a reward value based on a surface elevation of the geographic region and a soil hardness factor. Further, the robot determines an action for each grid cell of the plurality of grid cells, wherein the action corresponds to an expected direction of movement of the robot in the grid cell. The robot computes a global path as a concatenation of actions starting from a first grid cell and terminating at a second grid cell. The method monitors the movement of the robot on the computed global path and computes a second path based on a deviation of the robot from the global path.

Claims

1. A robot for automated deployment of a seismic sensor in a geographic region, the robot comprising:

a satellite receiver and a plurality of inertial sensors configured to determine at least one of a location and an orientation of the robot;

an imager configured to capture images; and

circuitry configured to;

generate a map of the geographic region, wherein the map includes a plurality of grid cells, a first grid cell including an initial starting point of the robot and a last grid cell including a target point corresponding to a location for deploying the seismic sensor,

assign each grid cell a reward value based on at least one of a surface elevation of the geographic region in the grid cell and a soil hardness factor of the geographic region in the grid cell,

compute iteratively, a plurality of utility values for each grid cell, an utility value of the plurality of utility values corresponding to a movement of the robot from the grid cell to an adjacent grid cell, each utility value being computed based on a corresponding reward value of the grid cell and a discount factor, wherein a magnitude of the plurality of utility values is equal to a number of neighboring grid cells of the grid cell,

determine an action for each grid cell of the plurality of grid cells based on the computed utility values of each grid cell, wherein the action is an expected direction of movement of the robot in the grid cell, the expected direction of movement in the grid cell maximizing a discounted sum of reward values of the grid cells,

compute, based on the determined actions, a global path as a concatenation of actions of each grid cell starting from the first grid cell and terminating at the last grid cell,

monitor a current location of the robot based on at least one of the satellite receiver and the plurality of inertial sensors, to determine whether a deviation of the robot from the global path exceeds a predetermined threshold deviation, and

compute a second path for the robot based on at least one of the monitored location of the robot when the deviation of the robot from the global path exceeds the predetermined threshold deviation and an obstacle being detected in the global path by the imager.

2. The robot of claim 1, wherein a magnitude of the reward value of the grid cell indicates a level of ease of movement of the robot in the grid cell.

3. The robot of claim 2, wherein the circuitry is further configured to

classify each grid cell of the plurality of grid cells as one of a passable grid cell and a non-passable grid cell based on the surface elevation of the geographic region of the grid cell.

4. The robot of claim 1, wherein the discounted reward value of the grid cell is computed by multiplying a discount parameter to the assigned reward value of the grid cell.

5. The robot of claim 4, wherein the circuitry is further configured to

apply the discount factor to the assigned reward values of each grid cell based on a battery life of the robot.

6. The robot of claim 1, wherein the circuitry is further configured to

calculate at least one of a surface normal to the map and a surface roughness of the map;

and

determine the second path based on one of an angle of the surface normal to the map and the surface roughness of the map.

7. The robot of claim 1, wherein the circuitry is further configured to

control a penetration of a soil test probe in the grid cell to determine the hardness factor of soil in the grid cell.

8. A method of automated deployment of a seismic sensor in a geographic region by a robot, the method comprising:

determining, by a satellite receiver and a plurality of inertial sensors, at least one of a location and an orientation of the robot;

capturing by an imager, images of the geographic region;

generating by circuitry, a map of the geographic region, wherein the map includes a plurality of grid cells, a first grid cell including an initial starting point of the robot and a last grid cell including a target point corresponding to a location for deploying the seismic sensor;

assigning each grid cell a reward value based on at least one of a surface elevation of the geographic region in the grid cell and a soil hardness factor of the geographic region in the grid cell,

computing iteratively, a plurality of utility values for each grid cell, an utility value of the plurality of utility values corresponding to a movement of the robot from the grid cell to an adjacent grid cell, each utility value being computed based on a corresponding reward value of the grid cell and a discount factor, wherein a magnitude of the plurality of utility values is equal to a number of neighboring grid cells of the grid cell,

determining an action for each grid cell of the plurality of grid cells based on the computed utility values of each grid cell, wherein the action is an expected direction of movement of the robot in the grid cell, the expected direction of movement in the grid cell maximizing a discounted sum of reward values of the grid cells,

computing, based on the determining, a global path as a concatenation of actions of each grid cell starting from the first grid cell and terminating at the last grid cell,

monitoring a current location of the robot based on at least one of the satellite receiver and the plurality of inertial sensors, to determine whether a deviation of the robot from the global path exceeds a predetermined threshold deviation, and

computing a second path for the robot based on at least one of the monitored location of the robot when the deviation of the robot from the global path exceeds the predetermined threshold deviation and an obstacle being detected in the global path by the imager.

9. The method of claim 8, further comprising:

classifying by circuitry, each grid cell of the plurality of grid cells as one of a passable grid cell and a non-passable grid cell based on the surface elevation of the geographic region of the grid cell.

10. The method of claim 8, further comprising:

calculating by circuitry, at least one of a surface normal to the map and a surface roughness of the map; and

determining the second path based on one of an angle of the surface normal to the map and the surface roughness of the map.

11. The method of claim 8, further comprising:

applying the discount factor to the assigned reward values of each grid cell based on a battery life of the robot.

12. A non-transitory computer readable medium having stored thereon a program that when executed by a computer causes the computer to execute a method of automatically deploying a seismic sensor in a geographic region by a robot, the method comprising:

determining at least one of a location and an orientation of the robot;

capturing images of the geographic region;

generating a map of the geographic region, wherein the map includes a plurality of grid cells, a first grid cell including an initial starting point of the robot and a last grid cell including a target point corresponding to a location for deploying the seismic sensor;

assigning each grid cell a reward value based on at least one of a surface elevation of the geographic region in the grid cell and a soil hardness factor of the geographic region in the grid cell,

computing iteratively, a plurality of utility values for each grid cell, an utility value of the plurality of utility values corresponding to a movement of the robot from the grid cell to an adjacent grid cell, each utility value being computed based on a corresponding reward value of the grid cell and a discount factor, wherein a magnitude of the plurality of utility values is equal to a number of neighboring grid cells of the grid cell,

determining an action for each grid cell of the plurality of grid cells based on the computed utility values of each grid cell, wherein the action is an expected direction of movement of the robot in the grid cell, the expected direction of movement in the grid cell maximizing a discounted sum of reward values of the grid cells,

computing, based on the determining, a global path as a concatenation of actions of each grid cell starting from the first grid cell and terminating at the last grid cell,

monitoring a current location of the robot based on at least one of the satellite receiver and the plurality of inertial sensors, to determine whether a deviation of the robot from the global path exceeds a predetermined threshold deviation, and

computing a second path for the robot based on at least one of the monitored location of the robot when the deviation of the robot from the global path exceeds the predetermined threshold deviation and an obstacle being detected in the global path by the imager.

13. The non-transitory computer readable medium of claim 12, wherein the method further comprises:

calculating at least one of a surface normal to the map and a surface roughness of the map; and

determining the second path based on one of an angle of the surface normal to the map and the surface roughness of the map.

14. The non-transitory computer readable medium of claim 12, wherein the method further comprises:

applying the discount factor to the assigned reward values of each grid cell based on a battery life of the robot.