Robotic Motion Planning for Risk-Aware Object Sortation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sorting systems in order fulfillment operations rely 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 that uses an end effector to acquire objects and determine a trajectory path with changing and unchanging portions, optimized by metrics such as time and risk, to efficiently move objects to specific processing locations, employing automated robotic systems with perception units and motion planning algorithms to handle heterogeneous objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual sorting is used to handle a variety of objects, then flexibility in handling different sizes, shapes, and weights is maintained, but productivity and efficiency deteriorate due to high labor intensity and slow processing speed
Solution Approach 1:
The patent replaces manual mechanical sorting operations with an automated robotic system that uses perception units (cameras, sensors) to detect objects and a programmable motion device with end effector to manipulate them. The system substitutes human labor with automated sensing, planning, and actuation mechanisms, achieving both high productivity and adaptability through software-controlled versatility.
Solution Approach 2:
The system employs dynamic motion planning that adapts trajectories in real-time based on object characteristics detected by perception units. The end effector dynamically adjusts its motion paths, grasp forces, and manipulation strategies according to each object's size, shape, and weight, enabling flexible handling of diverse objects while maintaining high-speed automated operation.
2Productivity
If automated robotic systems are implemented to improve productivity, then sorting efficiency increases, but device complexity and difficulty of accommodating various objects worsen
Solution Approach 1:
The patent implements a universal robotic system where a single programmable motion device with interchangeable end effectors can handle multiple object types. The perception units and motion planning algorithms are designed to recognize and adapt to various object characteristics, allowing one system to perform multiple sorting functions without requiring specialized equipment for each object type.
Solution Approach 2:
The system manages complexity by dynamically adjusting motion parameters (velocity, acceleration, trajectory points) and end effector parameters (grasp force, orientation) based on real-time object detection data. The motion planning software automatically computes appropriate parameters for each object, eliminating the need for manual programming of complex trajectories for every object variant.
3Productivity
If complex motion planning is used to optimize trajectories for minimum time or risk, then productivity improves, but computational requirements and system complexity increase
Solution Approach 1:
The system performs preliminary motion planning by pre-computing trajectories and storing them in a database before actual sorting operations. The motion planning software generates optimal paths considering time and risk metrics in advance, allowing the robotic system to execute pre-planned trajectories with minimal real-time computation, thus reducing operational complexity while maintaining high productivity.
Solution Approach 2:
The system uses perception units to continuously monitor object positions and trajectories during execution, providing feedback to the motion planning software. This feedback mechanism allows the system to adjust pre-planned trajectories in real-time based on actual object characteristics and environmental conditions, optimizing performance without requiring complex real-time recomputation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of processing objects is disclosed. The method comprises: storing in a trajectory database a plurality of predetermined path sections for moving an end effector of an articulated arm between a base location and a destination location, the trajectory database further storing a predetermined risk factor and a predetermined time factor for each of the plurality of predetermined path sections; obtaining identification information for an object presented in a plurality of objects at an input location; determining the destination location from among a plurality of destination locations based on the identification information obtained for the object; acquiring the object at the input location using the end effector; sorting the plurality of predetermined path sections for moving the end effector of the articulated arm from the base location to the destination location according to at least one of the predetermined risk factor and the predetermined time factor; selecting one of the plurality of predetermined path sections that satisfies at least one of a risk requirement and a time requirement; and moving the acquired object along a trajectory path from the input location to the destination location via the base location using the end effector of the articulated arm, the trajectory path including the selected one of the plurality of predetermined path sections from the base location to the destination location.