Virtual Safety Cages For Robotic Devices

• US 20160207199A1
• Filed: 01/25/2016
• Published: 07/21/2016
• Est. Priority Date: 07/16/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kuffner, James J. Jr., Anderson-Sprecher, Peter Elving
• Granted Patent: US 9,522,471 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B25J 19/06 Safety devices
• CPC Class Codes: B25J 9/1676 Avoiding collision or forbidden zones
• CPC Class Codes: G05B 2219/40196 Projecting light on floor to delimit danger zone around robot
• CPC Class Codes: G05B 2219/40202 Human robot coexistence
• CPC Class Codes: G05B 2219/40203 Detect position of operator, create non material barrier to protect operator
• CPC Class Codes: Y10S 901/47 Optical
• CPC Class Codes: Y10S 901/49 Protective device

Abstract

Methods and systems for determining and presenting virtual safety cages are provided. An example method may involve receiving an instruction for a robotic device to perform a physical action in a physical environment occupied by the robotic device. The method may also involve, responsive to receiving the instruction, and based on one or more parameters of one or more physical components of the robotic device, determining one or more estimated trajectories along which the one or more physical components of the robotic device are estimated to move as the robotic device performs the physical action. The method may further involve, based on the one or more estimated trajectories, determining a virtual representation of a space that the robotic device is estimated to occupy in the physical environment while performing the physical action. The method may then involve providing, into the physical environment, an indication of a location of the space.

Claims

1. A method performed by a computing system, the method comprising:

receiving, by one or more processors of the computing system, an instruction requesting that a robotic device perform a physical action in a physical environment occupied by the robotic device;

in response to receiving the instruction, the one or more processors determining multiple estimated trajectories of one or more physical components of the robotic device, wherein the multiple estimated trajectories are multiple trajectories along which the one or more physical components are estimated to move as the robotic device performs the physical action;

the one or more processors associating respective probabilities to the robotic device moving along the multiple estimated trajectories;

based on the multiple estimated trajectories and further based on the associated respective probabilities, the one or more processors determining a virtual representation of space that the robotic device is estimated to occupy in the physical environment while performing the physical action; and

the one or more processors providing, into the physical environment, an indication of a location of the space in the physical environment, the indication visually depicting the multiple estimated trajectories and indications of the associated respective probabilities.

2. The method of claim 1, wherein the space comprises a superposition of multiple spaces corresponding to respective estimated trajectories of the multiple estimated trajectories, the multiple spaces including multiple different spaces that the robotic device is estimated to occupy in the physical environment while performing the physical action.

3. The method of claim 1, wherein the indication includes a two-dimensional (2D) image of the space projected on a surface in the physical environment, wherein the 2D image depicts multiple 2D paths representative of the multiple estimated trajectories.

4. The method of claim 1, wherein the indication includes a holographic three-dimensional (3D) indication of the space, wherein the holographic 3D indication depicts multiple 3D paths representative of the multiple estimated trajectories, and wherein the holographic 3D indication is provided within the space in the physical environment.

5. The method of claim 1, wherein providing the indication comprises providing the indication to at least one computing device located remotely from the robotic device, and

wherein the indication includes a three-dimensional (3D) model of the space, wherein the 3D model depicts multiple 3D paths representative of the multiple estimated trajectories.

6. The method of claim 1, wherein providing the indication comprises causing at least one projecting device communicatively linked to the computing system to project the indication into the physical environment.

7. The method of claim 1, wherein the instruction requesting that the robotic device perform the physical action includes an instruction requesting that the robotic device move a physical object, and

wherein the space represented by the virtual representation includes space that the physical object is estimated to occupy while the robotic device is moving the physical object.

8. The method of claim 7, further comprising:

after receiving the instruction requesting that the robotic device move the physical object, the one or more processors causing the at least one projecting device to project a light onto the physical object.

9. A method performed by a computing system, the method comprising:

receiving, by one or more processors of the computing system, an instruction requesting that a robotic device perform a physical action in a physical environment occupied by the robotic device;

in response to receiving the instruction, the one or more processors determining one or more estimated trajectories of one or more physical components of the robotic device, wherein the one or more estimated trajectories are one or more trajectories along which the one or more physical components are estimated to move as the robotic device performs the physical action;

the one or more processors identifying a moving object in the physical environment;

in response to identifying the moving object in the physical environment, determining an estimated trajectory of the moving object along which the moving object is estimated to travel over a predetermined period of time;

making a comparison between the estimated trajectory of the moving object and the one or more estimated trajectories of the one or more physical components of the robotic device;

based on the output of the comparison, the one or more processors adjusting the one or more estimated trajectories of the one or more physical components of the robotic device;

based on the adjusted one or more estimated trajectories of the one or more physical components of the robotic device, the one or more processors determining a virtual representation of a space that the robotic device is estimated to occupy in the physical environment while performing the physical action; and

the one or more processors providing, into the physical environment, an indication of a location of the space in the physical environment, the indication visually depicting the adjusted one or more estimated trajectories.

10. The method of claim 9, wherein the one or more estimated trajectories are based on one or more parameters of the one or more physical components, and

wherein the one or more parameters of the one or more physical components include one or more of:

a maximum torque of the one or more physical components, a maximum power output of the one or more physical components, and a momentum of the one or more physical components.

11. The method of claim 9, wherein determining the estimated trajectory of the moving object along which the moving object is estimated to travel over the predetermined period of time comprises:

determining a plurality of parameters associated with the moving object, wherein the plurality of parameters include at least a current velocity of the moving object and a current direction of movement of the moving object; and

based on the determined plurality of parameters associated with the moving object, determining the estimated trajectory of the moving object along which the moving object is estimated to travel over the predetermined period of time.

12. The method of claim 9, wherein the moving object includes a human.

13. The method of claim 9, wherein the indication includes a two-dimensional (2D) image of the space projected on a surface in the physical environment, wherein the 2D image depicts one or more 2D paths representative of the adjusted one or more estimated trajectories.

14. The method of claim 9, wherein the indication includes a holographic three-dimensional (3D) indication of the space, wherein the holographic 3D indication depicts one or more 3D paths representative of the adjusted one or more estimated trajectories, and wherein the holographic 3D indication is provided within the space in the physical environment.

15. The method of claim 9, wherein providing the indication comprises providing the indication to at least one computing device located remotely from the robotic device, and

wherein the indication includes a three-dimensional (3D) model of the space, wherein the 3D model depicts multiple 3D paths representative of the adjusted one or more estimated trajectories.

16. The method of claim 9, wherein providing the indication comprises causing at least one projecting device communicatively linked to the computing system to project the indication into the physical environment.

17. A system comprising:

a robotic device;

one or more optical devices;

a wireless communication interface;

at least one processor; and

data storage comprising instructions executable by the at least one processor to cause the system to perform functions comprising;

receiving an instruction requesting that a robotic device perform a physical action in a physical environment occupied by the robotic device;

in response to receiving the instruction, determining multiple estimated trajectories of one or more physical components of the robotic device, wherein the multiple estimated trajectories are multiple trajectories along which the one or more physical components are estimated to move as the robotic device performs the physical action;

associating respective probabilities to the robotic device moving along the multiple estimated trajectories;

based on the multiple estimated trajectories and further based on the associated respective probabilities, determining a virtual representation of space that the robotic device is estimated to occupy in the physical environment while performing the physical action; and

providing into the environment, by one or more of the wireless communication interface and the one or more optical devices, an indication of a location of the space in the physical environment, the indication visually depicting the multiple estimated trajectories and indications of the associated respective probabilities.

18. The system of claim 17, wherein determining the multiple estimated trajectories of the one or more physical components of the robotic device comprises determining multiple estimated trajectories of the one or more physical components along which the one or more physical components are estimated to move within a predetermined period of time, and

wherein the space includes space that the robotic device is estimated to occupy in the physical environment while performing the physical action during the predetermined period of time.

19. The system of claim 17, wherein the robotic device includes at least one robotic manipulator involved in performing the physical action, the method further comprising:

determining respective ranges of motion for the at least one robotic manipulator involved in performing the physical action,

wherein determining the virtual representation is further based on the determined respective ranges of motion for the at least one robotic manipulator involved in performing the physical action, and

wherein the indication further visually depicts the determined respective ranges of motion.

20. The system of claim 17, wherein the multiple estimated trajectories are based on one or more parameters of the one or more physical components, and

wherein the one or more parameters of the one or more physical components include one or more of:

a maximum torque of the one or more physical components, a maximum power output of the one or more physical components, and a momentum of the one or more physical components.