Geometric State Estimation for Accurate Robotic Palletizing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic systems struggle with accurately stacking heterogeneous items on pallets due to inaccuracies in sensor data and reliance on high-precision robotics, leading to unstable and inefficient palletization processes.
Innovation Solution
A robotic system that combines geometric data and sensor data to estimate the state of a workspace, using interpolation and noise adjustment to improve the accuracy of item placement, allowing for lower-precision robotics and vision systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-precision robotics and vision systems are used, then item placement accuracy is improved, but system cost and complexity increase
Solution Approach 1:
The patent introduces a geometric model as an intermediary representation that mediates between the vision system data and the robotic control system. This geometric model serves as a simplified intermediate representation that captures essential spatial relationships without requiring high-precision direct measurement, thereby reducing system complexity while maintaining placement accuracy
Solution Approach 2:
The patent creates a geometric copy or model of the physical workspace and items, which can be manipulated and analyzed without requiring the physical system to be highly precise. This virtual geometric representation allows for accurate planning and simulation using lower-precision hardware
2Device complexity
If sensor data is used directly for item placement, then system simplicity is maintained, but placement accuracy deteriorates due to noise and inaccuracies
Solution Approach 1:
The geometric model acts as an intermediary processing layer between the noisy sensor data and the placement decision-making process. It filters and structures the information, transforming raw sensor readings into meaningful geometric relationships that guide accurate item placement without requiring complex noise filtering algorithms
Solution Approach 2:
The patent performs preliminary geometric modeling and state estimation before actual item placement occurs. By pre-processing the sensor data into a geometric model and using it to plan placements in advance, the system achieves high accuracy without needing complex real-time control mechanisms
3Productivity
If items are stacked without state estimation, then palletization speed is improved, but stack stability deteriorates
Solution Approach 1:
The system performs preliminary state estimation of the pallet and items using geometric models before making placement decisions. This advance planning based on estimated states allows for stable stacking configurations to be determined beforehand, enabling fast execution without compromising stability
Solution Approach 2:
The geometric model provides continuous feedback about the estimated state of the pallet and items being stacked. This feedback loop allows the system to adjust placement decisions to maintain stability while operating at high speeds, as the system constantly updates its understanding of the current configuration
Data Source
AI summary
A robotic system is disclosed. The system includes a communication interface that receives, from a sensor(s) deployed in a workspace, sensor data indicative of a current state of the workspace, the workspace comprising a pallet or other receptacle and a plurality of items stacked on or in the receptacle. The system includes one or more processors that control a robotic arm to place a first set of items on or in, or remove the first set of items from, the pallet or other receptacle, update a geometric model based on the first set of items placed on or in a receptacle, use the geometric model in combination with the sensor data to estimate a stack of one or more items on or in the receptacle, and use the estimated state to generate or update a plan to control the robotic arm to place a second set of items.