Robot Skill Footprints for Conflict-Free Concurrent Planning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional robotic movement planning requires extensive manual programming, which is time-consuming, error-prone, and not adaptable across different workcells, leading to conflicts and inefficiencies in multi-robot operations.

Innovation Solution

A system that generates conflict-free skill plans by using skill footprints for deconfliction evaluation, allowing concurrent execution of skills across multiple robots in a workcell, and automatically adapting to local conditions through modular and reusable skill templates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual programming is used to schedule robotic movements, then the robotic system can perform tasks with detailed control, but the programming process becomes tedious, time-consuming, and error-prone

Engineering Contradiction:

Improvecontrol accuracyVSAvoidprogramming time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables robots to automatically generate their own motion plans by providing planning algorithms and constraints, eliminating the need for extensive manual programming while maintaining detailed control accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system pre-defines workcells, their physical properties, and robot capabilities, allowing automatic plan generation without time-consuming manual programming for each new task

Inventive Principle:

Principle #10Preliminary action

2Reliability

If manual programming is used to create schedules, then detailed control is achieved, but the schedules cannot be adapted to other workcells with different robots or dimensions

Engineering Contradiction:

Improvecontrol accuracyVSAvoidworkcell adaptability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system creates universal workcell models that can represent different physical configurations, allowing the same planning algorithms to adapt to various workcells with different robots, dimensions, and constraints without requiring separate manual programming

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system dynamically adapts motion plans based on the specific characteristics of each workcell, automatically adjusting to different robots, dimensions, and physical constraints while maintaining control accuracy

Inventive Principle:

Principle #15Dynamics

3Reliability

If sequential execution of skills is used, then conflicts are avoided, but the overall execution time increases

Engineering Contradiction:

Improveconflict avoidanceVSAvoidexecution speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary conflict analysis by evaluating skill footprints before execution, identifying which skills can safely run concurrently, thereby enabling parallel execution without actual conflicts while improving productivity

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors skill execution and dynamically adjusts the plan based on real-time feedback, allowing concurrent execution of non-conflicting skills while maintaining conflict avoidance through active management

Inventive Principle:

Principle #23Feedback

4Productivity

If concurrent execution of multiple skills is attempted, then productivity improves, but conflicts may occur between skills or robots

Engineering Contradiction:

Improveexecution speedVSAvoidconflict avoidance

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system proactively prevents conflicts by evaluating skill footprints and spatial constraints before concurrent execution begins, blocking potentially conflicting skills from running simultaneously rather than resolving conflicts after they occur

Inventive Principle:

Principle #9Preliminary anti-action

Data Source

PatentUS12105492B2Robot planning for concurrent execution of actions

Publication Date: 2024.10.01 INTRINSIC INNOVATION LLC

AI summary

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for robotics planning. One of the methods comprises obtaining, for each of multiple skills to be performed by one or more robots in an operating environment, a skill footprint and a segmentation subset of the skill footprint that identifies one or more entities in the operating environment for performing the skill and that specifies requested permissions for the one or more entities; initiating execution of the skill; while the skill is executing, receiving a read or write request that references an entity that does not occur in the segmentation subset of the skill footprint; and in response, denying the read or write request that references the entity that does not occur in the segmentation subset of the skill footprint.