Robot Control Training for Faster Autonomous Task Transition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current robotic systems require significant time to transition from human-operated to autonomous control, as they need to learn and adapt by recording traces of human-directed tasks and sensor data, which limits their efficiency and adaptability in dynamic environments.

Innovation Solution

A method and system that enable a robotic system to autonomously generate and execute control instructions based on sensor data and initial human-operated instructions, allowing for real-time adaptation and task execution without extensive training, by using a processor to receive and process sensor data and generate autonomous control signals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If the robot records and learns traces of human-directed tasks and sensor data to transition to autonomous control, then the robot's autonomous operation capability is improved, but the transition time and training duration increase significantly

Engineering Contradiction:

Improveautonomous operation capabilityVSAvoidtransition time

Core Design Contradiction:

Extent of automationVSLoss of time

Solution Approach 1:

The system performs preliminary recording of human-operated tasks and sensor data during a training phase before autonomous operation is needed. This preliminary action allows the robot to learn task patterns and environmental characteristics in advance, so that when autonomous operation is required, the transition can occur more quickly without extensive real-time learning.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of human-operated task sequences and sensor data traces during training. These copied traces are stored and reused to generate autonomous control instructions, eliminating the need for the robot to relearn tasks during deployment. The copying process captures essential task patterns that can be replicated autonomously.

Inventive Principle:

Principle #26Copying

2Manufacturing precision

If the robot extensively trains by recording traces of human-directed tasks, then the robot's task performance accuracy is improved, but the training complexity and resource requirements increase

Engineering Contradiction:

Improvetask performance accuracyVSAvoidtraining complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system extracts only the essential task patterns and critical sensor data from extensive human-operated traces during training. Rather than storing and processing all raw data, the system identifies and extracts key task sequences, decision points, and environmental features that are most important for autonomous performance. This extraction reduces training complexity while maintaining task performance accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system transforms raw sensor data and task traces into processed representations with optimized parameters for autonomous control. By changing the parameter representation from raw data to extracted features and patterns, the system reduces the complexity of training data while preserving the essential information needed for accurate task execution.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If the robot uses human-operated instructions and sensor data to generate autonomous control instructions, then the robot's adaptability to dynamic environments is improved, but the processing requirements and computational load increase

Engineering Contradiction:

Improveadaptability to dynamic environmentsVSAvoidcomputational load

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary processing of sensor data and human-operated instructions during the training phase to create optimized autonomous control instructions. By doing this preparation work in advance when computational resources can be allocated, the system reduces the real-time processing requirements during autonomous operation, thereby reducing energy consumption while maintaining adaptability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces complex real-time sensor processing and decision-making mechanisms with pre-computed autonomous control instructions generated during training. Instead of continuously processing raw sensor data and human inputs during operation, the robot executes pre-generated control sequences that have already been optimized for adaptability, significantly reducing computational load and energy consumption.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11772266B2Systems, devices, articles, and methods for using trained robots

Publication Date: 2023.10.03 OCADO INNOVATION LTD

AI summary

Robotic systems, methods of operation of robotic systems, and storage media including processor-executable instructions are disclosed herein. The system may include a robot, at least one processor in communication with the robot, and an operator interface in communication with the robot and the at least one processor. The method may include executing a first set of autonomous robot control instructions which causes a robot to autonomously perform the at least one task in an autonomous mode, and generating a second set of autonomous robot control instructions from the first set of autonomous robot control instructions and a first set of environmental sensor data received from a senor. Execution of the second set of autonomous robot control instructions causes the robot to autonomously perform the at least one task. The method may include producing at least one signal that represents the second set of autonomous robot control instructions.