Multi-Robot Object Gripping With AI Task Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In industrial automation, particularly in packaging systems, the varying number of products on conveyor belts leads to downtimes and unproductive phases for robots, as they follow a first-in-first-out principle based solely on detected position, without considering the spatial arrangement and arrival times of objects.
Innovation Solution
A method utilizing an automated learning algorithm to detect objects, determine priority characteristics, and assign them to robots, taking into account optimization criteria such as energy consumption, throughput, and minimizing robot downtimes, thereby optimizing the selection and gripping process across multiple robots.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If robots follow the first-in-first-out principle based solely on detected position, then the control logic is simple, but robot downtimes increase and productivity decreases
Solution Approach 1:
The patent transforms the control approach from simple position-based FIFO to an optimized assignment system that considers multiple parameters including spatial arrangement, arrival times, robot capacities, and trajectory speeds. This parameter expansion resolves the contradiction by enabling better productivity while maintaining manageable complexity through systematic optimization.
Solution Approach 2:
The patent replaces the mechanical FIFO control logic with an automated learning algorithm that processes spatial and temporal data to optimize robot assignments. This substitution allows the system to handle complex coordination scenarios that would be impractical with simple rule-based control, thereby improving productivity without excessive complexity increase.
2Ease of operation
If robots operate without considering spatial arrangement and arrival times, then the operation is straightforward, but unproductive phases and downtimes occur
Solution Approach 1:
The system performs preliminary detection and analysis of object spatial arrangements and arrival times before assigning tasks to robots. This advance planning enables optimized trajectory generation and coordinated robot operations, reducing idle waiting time while maintaining operational simplicity through automated decision-making.
Solution Approach 2:
The automated learning algorithm continuously receives feedback from sensor systems about object positions, arrival times, and robot states, dynamically adjusting assignments to minimize downtimes. This feedback mechanism maintains ease of operation by automating the complex coordination while systematically reducing unproductive phases.
3Device complexity
If multiple robots are coordinated without optimization algorithms, then the system is simpler, but energy consumption increases and throughput decreases
Solution Approach 1:
The optimization algorithm considers robot capacities, trajectory speeds, and energy consumption characteristics as key parameters when assigning objects to robots. This parameter-based optimization enables energy-efficient coordination and maximized throughput while keeping system complexity manageable through systematic evaluation criteria.
4Device complexity
If robots pick objects based only on position in conveying direction, then the selection process is simple, but throughput is reduced due to ignoring spatial arrangement
Solution Approach 1:
The patent extends the object selection criteria from one-dimensional position along the conveying direction to multi-dimensional spatial arrangement considerations. By incorporating Y-coordinates and spatial relationships, the system optimizes robot picking sequences to maximize throughput while maintaining manageable selection complexity through automated processing.
Data Source
AI summary
A method for optimizing an automated process to select and grip an object by a robot in an arrangement that includes a plurality of robots with regard to a specifiable optimization criterion, wherein the objects to be potentially gripped irregularly occur with respect to their spatial position and a time of their arrival, where detection of objects to be potentially gripped by robots is performed, detection of a priority characteristic as well as an assignment to one of the robots for the objects to be potentially gripped via an automated learning algorithm, taking the optimization criterion into account, and where selection and gripping depending on the assignment and the priority characteristic is implemented.