Robot Grasp Primitive Library for Autonomous Multi-Task Operation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robots require complex tele-operation systems and significant training, leading to wear and tear before they can autonomously perform tasks, limiting their accessibility and efficiency in completing multiple work objectives.

Innovation Solution

A robot system equipped with a library of reusable work primitives and processor-executable instructions that allows it to autonomously initiate and execute workflows for various work objectives, using a combination of physically actuatable components and sensors to perform tasks like grasping objects, without the need for extensive training.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If robots are trained to operate autonomously by repeatedly performing physical tasks in the real world, then the robot can learn to complete work objectives, but significant wear and tear occurs on the robot components before deployment

Engineering Contradiction:
Improveautonomous operation capabilityVSAvoidcomponent durability
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The patent creates virtual copies of the robot and its environment in a simulated training environment. The robot learns autonomous operation through repeated tasks in this virtual copy, eliminating physical wear and tear while maintaining training effectiveness. The simulation accurately replicates physics, sensor inputs, and actuator responses to provide realistic training without compromising component durability.

Inventive Principle:
Principle #26Copying

2Ease of operation

If tele-operation systems are used to control robots, then the robot can perform physical actions emulating a human operator, but the interface becomes very elaborate and complicated requiring full operator attention

Engineering Contradiction:
Improverobot control capabilityVSAvoidtele-operation interface complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The robot performs self-service by autonomously completing work objectives without requiring complex tele-operation interfaces. The robot independently processes sensor data, plans actions, executes workflows, and adapts to environmental changes, eliminating the need for elaborate control systems and full operator attention while maintaining operational effectiveness.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If a robot is designed to complete multiple different work objectives, then the robot's versatility increases, but the system complexity increases

Engineering Contradiction:
Improvework objective rangeVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments complex work objectives into reusable atomic actions that can be independently learned and combined. The robot maintains a library of segmented actions (e.g., grasp, move, place, manipulate) that can be recombined through workflow composition to complete diverse work objectives, reducing system complexity while maintaining versatility.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements universality by creating a unified autonomous operation system that handles multiple work objectives through common processing pipelines. The robot uses the same sensor processing, workflow planning, and action execution mechanisms across different tasks, eliminating the need for separate specialized systems and reducing overall complexity while maintaining adaptability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11717963B2Systems, devices, and methods for grasping by multi-purpose robots
Publication Date: 2023.08.08 SANCTUARY COGNITIVE SYST CORP
  • US11717963B2 patent drawing
  • US11717963B2 patent drawing
  • US11717963B2 patent drawing

AI summary

Systems, devices, and methods for training and operating (semi-)autonomous robots to complete multiple different work objectives are described. A robot control system stores a library of reusable work primitives each corresponding to a respective basic sub-task or sub-action that the robot is operative to autonomously perform. A work objective is analyzed to determine a sequence (i.e., a combination and/or permutation) of reusable work primitives that, when executed by the robot, will complete the work objective. The robot executes the sequence of reusable work primitives to complete the work objective. The reusable work primitives may include one or more reusable grasp primitives that enable(s) a robot's end effector to grasp objects. Simulated instances of real physical robots may be trained in simulated environments to develop control instructions that, once uploaded to the real physical robots, enable such real physical robots to autonomously perform reusable work primitives.