Selecting robot poses to account for cost

Patent metadata

Field	Value
Publication number	US-9682476-B1
Application number	US-201514724178-A
Country	US
Kind code	B1
Filing date	May 28, 2015
Priority date	May 28, 2015
Publication date	Jun 20, 2017
Grant date	Jun 20, 2017

Abstract

Methods, apparatus, systems, and computer-readable media are provided for selecting robot poses to account for cost. In various implementations, a plurality of candidate instruction sets may be determined. Each candidate instruction set may be configured to cause a robot to assume a different respective set of poses while traversing a reference point along a path. In various implementations, a cost incurred while the robot implements the candidate instruction set to traverse the reference point along the path may be calculated. A candidate instruction set associated with an incurred cost that satisfies a first criterion may be selected from the plurality of candidate instruction sets. In some implementations, the selected candidate instruction set and incurred cost may be associated with the path.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
defining, by one or more processors, a reference path in Cartesian space between a sequence of two or more sites that is traversable by a reference point associated with an end effector of a robot;
determining, by the one or more processors, a plurality of candidate instruction sets, each candidate instruction set configured to cause the robot to assume a different respective sequence of poses in joint space while traversing the reference point along the reference path in Cartesian space, wherein each candidate instruction set is implementable by the robot to operate one or more operational components of the robot in joint space;
calculating, by the one or more processors for one or more of the plurality of candidate instruction sets, a cost that would be incurred while the robot implements the candidate instruction set to traverse the reference point along the reference path;
selecting, by the one or more processors from the plurality of candidate instruction sets, a candidate instruction set associated with a calculated cost that satisfies a criterion; and
causing, by the one or more processors, the robot to implement the selected candidate instruction set to traverse the reference point along the reference path through the two or more sites.

2. The computer-implemented method of claim 1 , wherein determining the reference path comprises receiving, by the one or more processors via a graphical user interface, an indication of the reference path.

3. The computer-implemented method of claim 1 , wherein determining the reference path comprises receiving, by the one or more processors, an indication of the reference path recorded by the robot while the robot is manually manipulated along the reference path.

4. The computer-implemented method of claim 1 , wherein determining the reference path comprises calculating, by the one or more processors based on input from an environmental detection device, an indication of the reference path.

5. The computer-implemented method of claim 1 , wherein the criterion is a minimum calculated cost.

6. The computer-implemented method of claim 1 , wherein the cost that would be incurred while the robot implements the candidate instruction set comprises excessive motion or overlong execution by the robot.

7. The computer-implemented method of claim 1 , wherein the cost that would be incurred while the robot implements the candidate instruction set comprises a cost that would be incurred by a particular operational component of the robot.

8. The computer-implemented method of claim 7 , wherein traversing the reference point along the reference path causes the end effector to be in a first configuration at a given site of the sequence of two or more sites, the plurality of candidate instruction sets comprises a first plurality of candidate instruction sets, and the method further comprises:
determining, by the one or more processors, a potential second configuration of the end effector at the given site, the second configuration being different than the first configuration;
determining, by the one or more processors, an alternative path in Cartesian space to the given site that is traversable by the reference point and that results in the end effector being in the second configuration;
determining, by the one or more processors, a second plurality of candidate instruction sets, each candidate instruction set of the second plurality of candidate instruction sets configured to cause the robot to assume a different respective sequence of poses in joint space while traversing the reference point along the alternative path in Cartesian space;
calculating, by the one or more processors for each of the second plurality of candidate instruction sets, a cost that would be incurred by the particular operational component of the robot while implementing the candidate instruction set to traverse the reference point along the alternative path; and
selecting, by the one or more processors from the first and second pluralities of candidate instruction sets, a candidate instruction set associated with a calculated cost that satisfies the criterion.

9. The computer-implemented method of claim 7 , wherein the particular operational component comprises a plurality of operational components, and the cost calculated for each of the plurality of candidate instruction sets comprises an average calculated cost incurred across the plurality of operational components.

10. The computer-implemented method of claim 9 , wherein the criterion is a minimum average calculated cost.

11. The computer-implemented method of claim 7 , wherein the particular operational component of the robot comprises an actuator or joint of the robot.

12. The computer-implemented method of claim 11 , wherein calculating the cost includes calculating a measure of motion or torque implemented by the actuator or joint during traversal of the reference point along the reference path.

13. The computer-implemented method of claim 11 , wherein calculating the cost includes calculating a measure of proximity of the actuator or joint to an associated actuator or joint operational limit during traversal of the reference point along a reference path.

14. The computer-implemented method of claim 11 , wherein calculating the cost includes calculating a measure of proximity of the actuator or joint to a preferred actuator or joint configuration during traversal of the reference point along a reference path.

15. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a computing system, cause the computing system to perform the following operations:
defining a plurality of candidate paths in Cartesian space between a sequence of two or more sites that are traversable by a reference point associated with an end effector of a robot;
for one or more of the plurality of candidate paths:
determining a plurality of candidate instruction sets, each candidate instruction set configured to cause the robot to assume a different respective sequence of poses in joint space while traversing the reference point along the candidate path in Cartesian space, wherein each candidate instruction set is implementable by the robot to operate one or more operational components of the robot in joint space;
calculating, for one or more of the plurality of candidate instruction sets, a cost that would be incurred by a particular operational component of the robot while implementing the candidate instruction set to traverse the reference point along the candidate path;
selecting, from the plurality of candidate instruction sets, a candidate instruction set associated with an associated incurred cost that satisfies a first criterion;
associating the selected candidate instruction set and incurred cost with the candidate path;

selecting, as a task path from the plurality of candidate paths, a candidate path associated with an incurred cost that satisfies a second criterion; and
causing the robot to traverse the reference point along the task path.

16. A system comprising one or more processors and memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to:
define a reference path in Cartesian space between a sequence of two or more sites that is traversable by a reference point associated with an end effector of a robot;
determine a plurality of candidate instruction

Assignees

• X Dev Llc

Inventors

• Prats Mario

Classifications

• Y10S901/02

  Arm motion controller · CPC title

• G05B2219/40465

  Criteria is lowest cost function, minimum work path · CPC title

• Y10S901/46

  Sensing device · CPC title

• B25J9/1664 Primary

  characterised by motion, path, trajectory planning · CPC title