Robotic Fleet Mapping with Predicted Locations for Task Coordination

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems for managing robotic fleets in physical environments, such as warehouses, lack dynamic and efficient coordination of robotic devices, leading to suboptimal energy, time, and space usage.

Innovation Solution

A system that dynamically manages a fleet of robotic devices by maintaining a collaboratively updated map of their predicted locations and tasks, allowing for real-time adjustments based on task progress data to optimize coordination and resource allocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a static map is used for fleet management, then system complexity is reduced, but coordination efficiency and resource utilization deteriorate

Engineering Contradiction:
Improvecoordination efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements a dynamic map that is continuously updated with predicted future locations of robotic devices. Instead of using a static floor plan, the system maintains a living representation of the environment that evolves as robots move and complete tasks. This dynamic approach enables real-time coordination and optimizes resource allocation without requiring overly complex centralized control.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system predicts future locations of robotic devices before they actually reach those positions. By anticipating where robots will be in the future based on their current tasks and movement patterns, the system can proactively optimize coordination and resource allocation, reducing idle time and improving overall productivity.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If real-time tracking of all robotic devices is implemented, then coordination accuracy improves, but energy consumption and computational load increase

Engineering Contradiction:
Improvelocation tracking accuracyVSAvoidenergy consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system implements selective tracking by only monitoring and updating the locations of robotic devices that are relevant to current tasks or may soon be involved in coordinated activities. Instead of continuously tracking every robot at all times, the system focuses computational resources on devices that matter for upcoming coordination events, reducing overall energy and computational consumption while maintaining necessary precision.

Inventive Principle:
Principle #16Partial or excessive action

3Speed

If frequent map updates are performed, then coordination responsiveness improves, but communication overhead and processing time increase

Engineering Contradiction:
Improvecoordination responsivenessVSAvoidprocessing time
Core Design Contradiction:
SpeedVSLoss of time

Solution Approach 1:

The system performs map updates at periodic intervals rather than continuously, and only updates the portions of the map that have changed. This periodic update strategy maintains coordination responsiveness by ensuring the map is refreshed frequently enough to be useful, while avoiding the excessive processing overhead of continuous full-map updates. The system balances responsiveness with efficiency by updating at the minimum necessary frequency.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3451097B1Dynamically maintaining a map of a fleet of robotic devices in an environment to facilitate robotic action
Publication Date: 2024.05.15 GOOGLE LLC
  • EP3451097B1 patent drawingFigure 1A
  • EP3451097B1 patent drawingFigure 1B
  • EP3451097B1 patent drawingFigure 2A

AI summary

Methods and systems for dynamically managing operation of robotic devices in an environment on the basis of a dynamically maintained map of the robotic devices are provided herein. A map of robotic devices may be determined, where the map includes predicted future locations of at least some of the robotic devices. One or more robotic devices may then be caused to perform a task. During a performance of the task by the one or more robotic devices, task progress data may be received from the robotic devices, indicative of which of the task phases have been performed. Based on the data, the map may be updated to include a modification to the predicted future locations of at least some of the robotic devices. One or more robotic devices may then be caused to perform at least one other task in accordance with the updated map.