Robotic Motion Planning for Mixed-Object Sortation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sorting systems in order fulfillment operations rely heavily on manual handling and are inefficient in processing a variety of objects of different sizes, shapes, and weights, lacking an automated solution for efficient and effective sortation and handling in both structured and cluttered environments.
Innovation Solution
A programmable motion control system equipped with an end effector, perception system for object recognition, and a motion planning system that determines specific and unchanging trajectory paths to efficiently move objects from input locations to processing destinations, accommodating both homogenous and non-homogenous objects in structured and cluttered environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual handling is used for sorting objects, then the system can accommodate a wide variety of objects of different sizes, shapes and weights, but the processing efficiency is low and labor-intensive
Solution Approach 1:
The patent replaces manual mechanical sorting with an automated robotic system that uses computer vision for object recognition and robotic arms for manipulation. The system captures images of objects, processes them to identify characteristics, and automatically determines sorting destinations and gripping strategies, eliminating manual labor while maintaining versatility through adaptive algorithms
Solution Approach 2:
The system enables objects to be automatically identified and sorted without human intervention. The computer vision system autonomously detects object properties, the motion planning system automatically generates trajectories, and the robotic end effector self-adjusts gripping forces based on detected object characteristics, creating a fully autonomous sorting process
2Productivity
If automated motion control system is implemented, then processing efficiency is improved, but the system complexity increases due to need for perception, grasp acquisition, and motion planning systems
Solution Approach 1:
The patent employs a multi-functional integrated system where a single robotic platform performs object recognition, grasp planning, motion trajectory generation, and physical manipulation. The computer vision system serves multiple purposes including object identification, location detection, and orientation assessment, while the motion planning system handles both trajectory generation and collision avoidance, reducing the need for separate specialized systems
Solution Approach 2:
The patent introduces a computer vision system as an intermediary between the physical objects and the robotic manipulation system. This intermediary captures visual information, processes it to extract meaningful characteristics, and translates it into actionable data for the motion planning and grasp acquisition systems, bridging the gap between perception and action
3Manufacturing precision
If trajectory paths are customized for each object's location and orientation, then sorting precision is improved, but the computation time increases
Solution Approach 1:
The patent performs preliminary computation of trajectory paths and gripping strategies based on object characteristics detected by the vision system. The motion planning system pre-calculates feasible trajectories and selects optimal paths before execution, and the grasp acquisition system pre-determines gripping forces and end effector configurations, reducing real-time computation requirements while maintaining precision
Solution Approach 2:
The patent applies different levels of computational detail to different aspects of the sorting process. Critical parameters such as trajectory accuracy and gripping force are computed with high precision, while less critical aspects use simplified models or pre-determined strategies, optimizing the balance between computation time and sorting precision
Data Source
AI summary
A processing system is disclosed for providing processing of objects that includes a programmable motion device including an end effector, a perception system for recognizing any of the identity, location, and orientation of an object presented in a plurality of objects at an input location, a grasp acquisition system for acquiring the object using the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination bins, and a motion planning system for determining a changing portion of a trajectory path of the end effector from the object to a base location proximate to the input location, and determining an unchanging portion of a trajectory path of the end effector from the base location to a destination bin location proximate to a destination bin.