Robotic Item Handler Control for Picking vs Sweeping Decisions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In material handling environments, manual loading and unloading of vehicles is costly, inefficient, and physically demanding, necessitating an automated system for quickly and effectively handling bulk quantities of stacked cases and cargo.
Innovation Solution
A robotic item handler system that uses sensor devices to capture three-dimensional images, generates combined point cloud data, and employs a machine learning model to decide between operating modes, such as picking or sweeping, to optimize item handling operations based on probability distributions and pre-defined heuristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual labor is used to load or unload vehicles, then flexibility and adaptability are maintained, but productivity is low and labor costs are high
Solution Approach 1:
The robotic item handler autonomously performs loading and unloading operations without continuous human intervention. The system uses machine learning models to independently decide between picking and sweeping modes, evaluates decisions using heuristics, and executes operations automatically, enabling the system to serve itself and eliminating the need for manual labor while maintaining high productivity
Solution Approach 2:
The patent replaces manual mechanical operations with an automated robotic system that uses sensors, machine learning models, and automated decision-making algorithms. The robotic item handler substitutes human operators and manual labor with an integrated system combining computer vision, probability-based decision models, and automated mechanical execution, achieving both high productivity and full automation
2Adaptability or versatility
If a single operating mode is used for item handling, then device complexity is reduced, but adaptability to different item configurations decreases
Solution Approach 1:
The system dynamically selects between picking and sweeping operating modes based on real-time evaluation of item configurations. The machine learning model continuously assesses probability distributions for different modes and adapts its behavior according to the specific situation, allowing the system to be versatile without requiring complex hardware changes for each mode
Solution Approach 2:
The robotic item handler is designed with universal capabilities to perform both picking and sweeping operations using the same physical platform. The system uses a unified machine learning framework that evaluates multiple operating modes and selects the most appropriate one, enabling a single device to handle diverse item configurations without requiring separate specialized mechanisms for each operation type
Data Source
AI summary
A method for controlling a robotic item handler is described. The method includes obtaining first point cloud data related to a first three-dimensional (3D) image and second point cloud data related to a second 3D image, captured by a first sensor device and a second sensor device respectively. Further, the method can include transforming the first point cloud data and the second point cloud data to combined point cloud data that is used as an input to a convolutional neural network, to construct a machine learning model. The machine learning model can output a decision classification indicative of a first probability associated with a first operating mode and a second probability associated with a second operating mode. Furthermore, the method can include operating the robotic item handler according to the first operating mode or the second operating mode based on a comparison of the first probability and the second probability.