# US 2022/0019188 A1 · Method and system for preemptive planning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0019188 A1
- Document ID: US20220019188A1
- Status: Published application
- Kind: A1
- Application number: 17/361,658
- Filed: 2021-06-29
- Published: 2022-01-20
- Earliest claimed: 2020-07-14
- Assignees: Vicarious FPC, Inc.
- Applicants: Vicarious FPC, Inc.
- Inventors: Kenneth Alan Kansky
- Web page: https://patentgrep.com/patent/US20220019188A1

## CPC

- B25J 9/1664: {characterised by motion, path, trajectory planning}
- G05B 19/402: characterised by control arrangements for positioning, e.g. centring a tool relative to a hole in the workpiece, additional detection means to correct position (G05B19/19 takes precedence)
- G05B 19/4083: {Adapting program, configuration}
- G05B 2219/39001: Robot, manipulator control
- G05B 2219/39155: Motion skill, relate sensor data to certain situation and motion
- G05B 2219/39382: Level, organization and coordination or distribution of tasks and execution level
- B25J: MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES ({manipulators specially adapted for use in surgery A61B34/70; manipulators used in cleaning hollow articles B08B9/04}; manipulators associated with rolling mills B21B39/20; manipulators associated with forging machines B21J13/10; {manipulators associated with picking-up and placing mechanisms B23P19/007}; means for holding wheels or parts thereof B60B30/00; {vehicles with ground-engaging propulsion means, e.g. walking members B62D57/02, B62D57/032; devices for picking-up and depositing articles or materials between conveyors B65G47/90, B65G47/91; manipulators with gripping or holding means for transferring packages B65H67/065}; cranes B66C; {manipulators used in the protection or supervision of pipe-line installations F17D5/00; walking equipment adapted for nuclear steam-generators F22B37/006}; manipulators specially adapted for, or associated with, nuclear reactors G21C; {apparatus used for handling wafers during manufacture or treatment of semiconductor H10P72/50})
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)

## Abstract

A method for preemptive control planning can include: optionally determining a graph that defines dependencies between behaviors; executing an execution plan for an executing behavior; generating a set of predictions with the executing behavior; propagating the set of predictions to child behaviors of the executing behavior; determining child execution plans and child predictions with the child behaviors; repeating the above for descendant behaviors of each child behavior; determining a realized world state associated with completion of the execution plan; and executing a child execution plan associated with a world state prediction matching the realized world state.

## Claims

### Claim 1

A system, comprising:
a set of behaviors, each comprising a planning model and a prediction model;
a graph defining a set of hierarchical dependencies between the behaviors; and
a coordination module, configured to:
a) receive world state predictions associated with exit statuses that are output by the prediction models of parent behaviors;
b) propagate the world state predictions to child behaviors associated with the respective exit statuses, wherein the child behaviors determine execution plans and output child state predictions, associated with child exit statuses, based on the world state predictions; and
c) repeat a) and b) for descendants of the child behaviors;
wherein a child behavior executes a predetermined execution plan when a realized world state, effected by a parent behavior, substantially matches a world state prediction used to generate the predetermined execution plan.

### Claim 2 (depends on 1)

The system of claim 1, further comprising a sensor configured to measure a value of a variable of the world state, wherein the coordination module is further configured to update the variable, within a prediction of the world state propagated to a descendant behavior of an executing behavior, with the measured value.

### Claim 3 (depends on 1)

The system of claim 1, wherein the predetermined execution plan is a motion plan executable by a robot.

### Claim 4 (depends on 1)

The system of claim 1, wherein the child behavior comprises a planning model, wherein the planning model is configured to determine the predetermined execution plan based on the world state prediction propagated to the child behavior by the coordination module.

### Claim 5 (depends on 4)

The system of claim 4, wherein the child behavior is further configured to generate a child state prediction associated with execution of the predetermined execution plan.

### Claim 6 (depends on 1)

The system of claim 1, wherein a behavior within the graph comprises a sub-instance of the system, comprising a set of sub-behaviors and a sub-graph.

### Claim 7 (depends on 6)

The system of claim 6, wherein the world state predictions output by the sub-behaviors comprise encapsulated states accessible only by other sub-behaviors within the system sub-instance and shared states accessible by the behaviors within the system.

### Claim 8 (depends on 1)

The system of claim 1, wherein each world state prediction is associated with an occurrence probability, wherein the coordination module prioritizes world state prediction propagation based on the associated occurrence probability.

### Claim 9 (depends on 1)

The system of claim 1, wherein each child behavior outputs a set of child state predictions for a world state prediction propagated to said child behavior.

### Claim 10 (depends on 1)

The system of claim 1, wherein the world state is a state of a physical world.

### Claim 11 (depends on 1)

The system of claim 1, wherein the world state predictions and child state predictions each comprise:
shared memory propagated to other behaviors;
local memory propagated to subsequent instances of the parent and child behavior, respectively;
an exit status comprising a prediction of execution plan execution outcome; and
a probability of occurrence.

### Claim 12 (depends on 1)

The method of claim 1, wherein the set of behaviors comprise at least one of a grasping behavior or an insertion behavior.

### Claim 13

A method, comprising:
executing an execution plan for an executing behavior and changing a world state, wherein the executing behavior is a behavior within a graph defining hierarchical dependencies between a set of behaviors;
while executing the execution plan:
a) generating a set of world state predictions of the world state at execution plan completion;
b) propagating the world state predictions of the set to child behaviors of the executing behavior;
c) planning child execution plans with the child behaviors;
d) generating child state predictions of the world state with the child behaviors; and
e) repeating b)-d) for descendant behaviors of each child behavior; and
determining a realized world state associated with completion of the execution plan; and
executing a child execution plan associated with a world state prediction matching the realized world state.

### Claim 14 (depends on 13)

The method of claim 13, wherein the world state prediction matching the realized world state is determined based on predicted values of the world state prediction falling within predetermined ranges of real values of the realized world state.

### Claim 15 (depends on 13)

The method of claim 13, wherein the execution plan is executed by a robot.

### Claim 16 (depends on 13)

The method of claim 13, wherein each behavior comprises a planning model specific to the behavior, wherein the planning model generates a set of control instructions for a robot.

### Claim 17 (depends on 13)

The method of claim 13, further comprising, when multiple world state predictions are available to a child behavior, prioritizing the world state predictions for child execution plan planning and child state prediction generation.

### Claim 18 (depends on 17)

The method of claim 17, wherein the world state predictions are prioritized based on estimated planning time.

### Claim 19 (depends on 13)

The method of claim 13, wherein the hierarchical dependencies comprise exit statuses, wherein a first exit status is associated with a first edge from a first behavior to a second behavior within the graph, and wherein a second exit status is associated with a second edge from the second behavior to the first behavior.

### Claim 20 (depends on 13)

The method of claim 13, further comprising, passing shared memory up to a super-instance of the graph while locally operating based on encapsulated memory.
