Robotic Bin Picking With Air Perturbation for Hard-to-Reach Items
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic devices face challenges in picking items from bins due to physical constraints, varied item shapes and materials, and difficult locations, leading to frequent human intervention and incomplete task completion.
Innovation Solution
A robotic device equipped with both picking and perturbation elements, such as a robotic arm with suction-based and high-pressure air-based perturbation capabilities, uses computer vision and machine learning to reposition items for successful picking by rearranging them within the bin.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a robotic device uses only picking elements to retrieve items from a bin, then the device structure remains simple, but the device fails to pick items in difficult locations or with varied shapes and materials
Solution Approach 1:
The robotic device integrates multiple effectors (picking elements and perturbation elements) into a single system that can perform both direct picking and item rearrangement tasks. The perturbation elements (such as air blowers or pushing mechanisms) are coupled to the robotic arm, allowing the same device to adapt its function based on the item's characteristics and location, thereby achieving multi-functionality without requiring separate dedicated systems.
Solution Approach 2:
The robotic device dynamically switches between picking mode and perturbation mode based on real-time assessment of item accessibility. When computer vision detects that an item cannot be directly picked due to shape, material, or location constraints, the system dynamically transitions to using perturbation elements to rearrange items, then switches back to picking elements once favorable conditions are created. This dynamic adaptability resolves the contradiction between handling varied items and maintaining simple structure.
2Reliability
If a robotic device attempts to pick every item directly without rearrangement, then the operation process remains simple, but the device encounters frequent failures and requires human intervention
Solution Approach 1:
Before attempting to pick an item, the robotic device first assesses its accessibility using computer vision and machine learning models. When direct picking is deemed unlikely to succeed, the system performs preliminary perturbation actions (blowing air or pushing items) to rearrange objects in the bin, creating favorable conditions for subsequent successful picking. This preliminary action increases reliability by preventing failed picking attempts rather than reacting to them.
Solution Approach 2:
The system continuously monitors picking success and uses machine learning to learn from outcomes. When perturbation actions lead to successful picks, the system reinforces this behavior pattern. The feedback loop between computer vision assessment, perturbation execution, and picking outcome analysis enables the device to automatically improve its operation process, reducing human intervention while maintaining increasing reliability over time.
3Productivity
If perturbation elements are added to the robotic device to rearrange items, then the probability of successful picking increases, but the device complexity increases
Solution Approach 1:
The perturbation elements (air blowers, pushing mechanisms) are merged with the existing robotic arm structure, sharing common components such as the robotic arm for positioning, control systems, and power supply. This merging approach allows the device to gain perturbation capability without proportionally increasing overall complexity, as the same structural elements serve both picking and perturbation functions.
Solution Approach 2:
The robotic arm and control system serve dual purposes: positioning picking elements for item retrieval and positioning perturbation elements for item rearrangement. This multi-functionality means that while the device structure becomes more capable, the base structure remains shared, preventing linear increases in complexity proportional to the increase in productivity capability.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The robotic device effectively increases the probability of picking items by rearranging them using perturbation strategies, reducing the need for human intervention and improving task completion rates in repetitive and challenging environments.
Implementation Method 1
One specific implementation of a perturbation element can blow high-pressure air in a desired direction
Data Source
AI summary
Various embodiments of the present technology generally relate to robotic devices and artificial intelligence. More specifically, some embodiments relate to a robotic device for picking items from a bin and perturbing items in a bin. The robotic device may include one or more picking elements and one or more perturbation elements for disturbing a present arrangement of items in the bin. In an exemplary embodiment, a perturbation element comprises a compressed air valve. In some implementations, the robotic device may also include one or more computer-vision systems. Based on image data from the one or more computer-vision systems, a strategy for picking up items from the bin is determined. When no strategies with high probability of success exist, the robotic device may perturb the contents of the bin to create new available pick-up points.