Robotic Sortation With Perception-Guided Grasp and Motion Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sorting systems rely on manual processes and are inefficient in handling a variety of objects in dynamic environments, particularly in identifying and sorting heterogeneous objects with obscured or non-visible identification markers.
Innovation Solution
A robotic sortation system that includes a programmable motion device with a perception system for object identification, a grasp selection system to determine secure grasp locations, and a motion planning system for efficient transport of objects to destination locations, utilizing cameras and sensors to recognize object orientation and environment constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual sorting processes are used, then flexibility in handling various objects is maintained, but sorting efficiency and speed deteriorate
Solution Approach 1:
The system enables automated self-service sorting through perception systems that automatically identify objects and their destinations, grasp selection systems that autonomously determine optimal grasp points, and motion planning systems that automatically generate transport paths, eliminating the need for manual sorting operations
Solution Approach 2:
The patent replaces manual mechanical sorting operations with an automated robotic system comprising a programmable motion device, perception system, grasp selection system, and motion planning system that work together to perform sorting tasks automatically
2Productivity
If automated robotic systems are implemented, then sorting speed and efficiency improve, but the ability to handle heterogeneous objects with obscured identification markers deteriorates
Solution Approach 1:
The perception system is designed with multi-functionality to handle various object types and identification scenarios, including objects with obscured or non-visible identification markers, by integrating multiple sensing capabilities and advanced image processing algorithms
Solution Approach 2:
The system introduces an intermediary perception and recognition layer between the robotic gripper and the objects, which includes advanced image processing and object recognition algorithms that can identify objects even when identification markers are obscured or not visible
3Device complexity
If simple grasp mechanisms are used, then device complexity is reduced, but the ability to securely grasp objects in cluttered environments deteriorates
Solution Approach 1:
The system performs preliminary actions by using the perception system to identify objects and their characteristics before grasping, and the grasp selection system to pre-determine optimal grasp points and approaches, ensuring secure grasps even in cluttered environments
Solution Approach 2:
The motion planning system adds temporal dimension to the grasping process by planning approach paths and grasp execution sequences, allowing the robotic system to navigate around obstacles and achieve secure grasps on objects in cluttered environments
4Loss of time
If direct transport paths are used, then motion time is reduced, but collision risks with obstacles in cluttered environments increase
Solution Approach 1:
The motion planning system dynamically adjusts transport paths based on real-time environmental perception and obstacle detection, generating collision-free trajectories that adapt to the cluttered environment while minimizing transport time
Solution Approach 2:
The system implements feedback through the perception system that continuously monitors the environment during object transport, allowing the motion planning system to adjust paths in real-time to avoid obstacles and ensure safe delivery to destination locations
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A sortation system is disclosed for providing processing of homogenous and non-homogenous objects in both structured and cluttered environments. The sortation 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, a grasp selection system for selecting a grasp location on the object, the grasp location being chosen to provide a secure grasp of the object by the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination locations, and a motion planning system for providing a motion path for the transport of the object when grasped by the end effector from the plurality of objects to the one of the plurality of destination locations, wherein the motion path is chosen to provide a path from the plurality of objects to the one of the plurality of destination locations.