Robotic Motion Planning for Sorting Heterogeneous Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sorting processes in order fulfillment operations rely heavily on manual handling and are inefficient in accommodating a variety of objects of different sizes, shapes, and weights, necessitating a need for an automated sortation and motion planning system that can efficiently and effectively handle heterogeneous objects.
Innovation Solution
A programmable motion control system utilizing a robotic system with an articulated arm, perception unit, and central computing system that identifies objects using 2D/3D imagery and algorithms to generate candidate grasp locations, and employs motion planning with a dynamically updated trajectory database to efficiently route objects to specific destinations, reducing the need for operator assistance and improving system performance over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual sorting is used, then flexibility in handling various objects is maintained, but productivity and efficiency deteriorate
Solution Approach 1:
The system enables automated self-service sorting where the robotic system independently identifies objects, determines destinations, and executes sorting actions without continuous human intervention. The perception unit autonomously captures images, the processor automatically generates motion plans, and the robotic system self-corrects based on feedback from vision systems throughout the sorting process.
Solution Approach 2:
Manual mechanical sorting operations are replaced with an automated robotic system that uses computer vision for object identification, algorithmic motion planning for trajectory generation, and robotic actuators for physical object manipulation. This substitution eliminates the need for human operators to manually handle each object while maintaining adaptability to various object types.
2Adaptability or versatility
If a programmable motion device accommodates a wide variety of objects, then versatility is improved, but device complexity increases
Solution Approach 1:
The robotic system is designed with universal end-effectors and motion planning algorithms that can handle multiple object types, sizes, and weights through a single integrated platform. The perception unit captures various object configurations, and the processor generates appropriate motion plans for diverse sorting scenarios, eliminating the need for multiple specialized devices.
Solution Approach 2:
The system employs dynamic motion planning that adapts trajectories in real-time based on object characteristics detected by the perception unit. The robotic system can dynamically adjust grasp forces, motion speeds, and path configurations to accommodate different object properties, providing versatility through adaptive control rather than fixed mechanical configurations.
3Productivity
If automated sortation is implemented, then productivity increases, but the ability to handle heterogeneous objects with different properties deteriorates
Solution Approach 1:
The system incorporates continuous feedback loops where perception units capture real-time images of objects and their positions, the processor analyzes this data to adjust motion plans, and the robotic system executes corrected trajectories. This feedback mechanism enables the automated system to adapt to heterogeneous objects while maintaining high sorting throughput through iterative optimization.
Solution Approach 2:
The motion planning system dynamically changes operational parameters such as trajectory coordinates, grasp forces, and motion velocities based on object properties detected by the perception unit. By adjusting these parameters in real-time, the system maintains high productivity while adapting to diverse object characteristics including size, shape, and weight variations.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A processing system is disclosed for providing processing of homogenous and nonhomogenous objects in both structured and cluttered environments. The processing system 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.