Robotic Motion Planning for Mixed-Object Sortation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic and sortation systems struggle to efficiently and effectively automate the sortation and handling of a variety of objects in both structured and cluttered environments, particularly in changing environments where objects are arranged in homogenous and heterogeneous arrangements.
Innovation Solution
A processing system that includes a programmable motion device with an end effector, a perception system for identifying object identity, location, and orientation, a grasp acquisition system for acquiring objects, and a motion planning system that determines trajectory paths with changing and unchanging portions to efficiently sort objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual sortation is used, then flexibility in handling various objects is maintained, but productivity and processing efficiency are low
Solution Approach 1:
The system enables automated self-service sortation where the robotic system independently identifies, grasps, and places objects without continuous manual intervention. The perception system autonomously detects object properties, the motion planning system automatically generates trajectories, and the end effector autonomously executes grasping and placement actions, replacing manual sortation while maintaining flexibility.
Solution Approach 2:
The patent replaces manual mechanical sortation with an automated robotic system comprising a programmable motion device, perception system, grasp acquisition system, and motion planning system. This substitution maintains the flexibility of handling diverse objects while dramatically improving productivity through automated control and execution.
2Productivity
If a programmable motion device is introduced to automate sortation, then productivity increases, but the system must accommodate a wide variety of objects of different sizes, shapes and weights increasing device complexity
Solution Approach 1:
The system employs dynamic motion planning that adapts trajectories based on real-time perception of object properties. The motion planning system generates changing portions of trajectories specific to each object's location and orientation, while using unchanging portions for standard paths. This dynamic adaptation allows handling of diverse objects without requiring completely different systems for each object type.
Solution Approach 2:
The robotic system is designed with universal components that can handle multiple object types. The end effector can grasp various sizes and shapes, the perception system can identify different objects, and the motion planning system can generate appropriate trajectories for diverse objects. This multi-functionality reduces the need for multiple specialized systems while maintaining high productivity.
3Manufacturing precision
If trajectory paths are customized for each object's location and orientation, then processing accuracy improves, but computation time and system response increase
Solution Approach 1:
The trajectory is segmented into changing portions and unchanging portions. The changing portions are specifically customized for each object's location and orientation to ensure precision, while the unchanging portions represent standard paths that can be pre-planned or reused. This segmentation allows the system to achieve high accuracy for critical segments while minimizing computation time by reusing standard segments.
Solution Approach 2:
The system performs preliminary perception and identification of object properties before generating trajectories. By acquiring object location and orientation information in advance, the motion planning system can efficiently generate accurate trajectories without excessive computation time during execution. The perception system prepares the necessary data beforehand, enabling faster trajectory generation.
Data Source
AI summary
A processing system is disclosed for providing processing of objects that include 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