Robot Skill Sequencing Using State Transitions for Assembly

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Complex assembly tasks using robotic automation require efficient methods to replicate human demonstrated skills, as existing kinesthetic teaching methods can be cumbersome and lack precision.

Innovation Solution

A method and device for operating a machine that involves providing a sequence of skills, selecting optimal state sequences based on transition probabilities, and using cascaded models and Viterbi algorithms to determine the most likely state sequence for achieving a desired task goal.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If kinesthetic teaching is used to teach robot skills, then the robot can learn human demonstrated skills, but the process is cumbersome and lacks precision

Engineering Contradiction:

Improveability to learn human demonstrated skillsVSAvoidcumbersome teaching process

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent uses motion capture technology to copy human movements and translates them into robot control commands. Instead of manual kinesthetic teaching, the system captures human demonstrator movements and automatically generates precise robot trajectories, eliminating the cumbersome teaching process while maintaining the ability to learn human skills

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces manual mechanical kinesthetic teaching with an automated system combining motion capture sensors, processing units, and algorithms. The mechanical interaction of manual teaching is substituted by optical/electronic motion capture and computational processing, improving both ease of operation and precision

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If a sequence of skills is provided for complex assembly tasks, then the task can be executed, but determining the optimal state sequence increases computational complexity

Engineering Contradiction:

Improveexecution of complex assembly tasksVSAvoidcomputational complexity of state sequence determination

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the complex assembly task into discrete skills, each with defined initial and final states. The overall task is divided into manageable skill components that can be independently modeled and executed, reducing the computational complexity of determining the optimal state sequence while maintaining productivity

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent pre-defines skill models with specified initial and final states before task execution. By preparing these skill representations in advance, the system reduces real-time computational complexity when determining the optimal state sequence, as the framework and transition probabilities are already established

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12304087B2Method and device for operating a machine

Publication Date: 2025.05.20 ROBERT BOSCH GMBH

AI summary

A device for and method of operating a machine. The method includes providing a sequence of skills of the machine for executing a task, selecting a sequence of states from a plurality of sequences of states, depending on a likelihood, wherein the likelihood is determined depending on a transition probability from a final state of a first sub-sequence of states of the sequence of states for a first skill in the sequence of skills to an initial state of a second sub-sequence of states of the sequence of states for a second skill in the sequence of skills.