Robotic Task Planning With Temporal Logic for Fast Reconfiguration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies require significant economic costs for reconfiguring robotic systems require significant economic costs for reconfiguring robotic systems, such as manufacturing robots, due to the need for external third-party intervention and lengthy downtimes when changing tasks.

Innovation Solution

A closed-loop motion planning and contextual reasoning system with AI-based software framework that enables robots to adapt tasks in real-time, using probabilistic machine learning models and closed-loop autonomy, allowing for efficient task modification and execution without extensive training or shutdowns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional robot reconfiguration methods are used with external third-party intervention, then task change capability is achieved, but reconfiguration cost and downtime increase significantly

Engineering Contradiction:

Improvetask change capabilityVSAvoidreconfiguration downtime

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The robot system performs self-reconfiguration through autonomous learning and adaptation. The robot uses its own sensors, processors, and stored task plans to independently modify and adjust its task execution without requiring external third-party intervention, thereby eliminating reconfiguration downtime and reducing costs

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Multiple task plans are pre-stored in the robot's memory during manufacturing. When a task change is needed, the system selectively activates pre-existing task plans rather than creating new ones from scratch, enabling rapid task switching without reconfiguration downtime

Inventive Principle:

Principle #10Preliminary action

2Adaptability or versatility

If traditional robot reconfiguration methods are used with external third-party intervention, then task change capability is achieved, but reconfiguration cost increases significantly

Engineering Contradiction:

Improvetask change capabilityVSAvoidreconfiguration cost

Core Design Contradiction:

Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses pre-stored task plans as templates that can be selectively activated and adapted. Instead of creating entirely new task programs, the robot copies and modifies existing task plan structures from its memory, reducing the complexity and cost of task reconfiguration

Inventive Principle:

Principle #26Copying

3Ease of manufacture

If fixed task programming is used in robots, then initial setup is simple, but adaptability to changing manufacturing needs deteriorates

Engineering Contradiction:

Improveinitial setup simplicityVSAvoidadaptability to changing tasks

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The robot system transitions from static fixed programming to dynamic adaptive task execution. Multiple task plans are stored in memory and can be selectively activated based on current manufacturing needs. The system continuously monitors task execution and can switch between different task plans dynamically, providing both ease of initial setup and adaptability to changing requirements

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The robot is designed with multi-functionality by storing diverse task plans covering various manufacturing operations. A single robot system can perform multiple different tasks by selecting appropriate pre-stored task plans, eliminating the need for separate specialized robots for each task while maintaining simple initial setup

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20260001224A1Determination of Task Plans for Robotic Devices

Publication Date: 2026.01.01 SARCOS CORP

AI summary

Technology is described for determining a task plan that is usable by a robotic device in a workspace. The method can include converting instructions received for the robotic device into temporal logic (TL) statements and to a non-deterministic Buchi Automaton. A task probabilistic machine learning model can be generated with feasible task plans using the non-deterministic Buchi Automaton. A plurality of task plans can also be created or generated using the task probabilistic machine learning model. A sensor probabilistic machine learning model of the workspace can be constructed using information from sensors of the robotic device. The task plans from the task probabilistic machine learning model can be compared with the sensor probabilistic machine learning model to select the task plan with a high probability of correlation to the workspace.