Robot Grasp Strategy Selection Using Machine Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots face challenges in determining the appropriate manner to grasp objects due to the complexity of selecting the correct grasping strategy, which is difficult for them to determine innately like humans.
Innovation Solution
The use of machine learning models to select a grasp strategy based on sensor data, such as vision data, to define grasp regions and semantic indications, influencing the pose and type of grasp, as well as pre- and post-grasp manipulations, allowing robots to determine the optimal approach and interaction with objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional programming methods are used to control robot grasping, then the robot can execute predefined grasp actions, but it cannot adapt to different object types and grasp scenarios
Solution Approach 1:
The patent replaces traditional mechanical control systems with machine learning models that process sensor data and automatically select grasp strategies. The system uses trained neural networks to analyze object properties from sensor inputs and determine appropriate grasp parameters, substituting complex rule-based programming with data-driven intelligent decision-making.
Solution Approach 2:
The system dynamically adjusts grasp parameters such as grasp pose, approach direction, and end effector configuration based on processed sensor data and semantic indications. By changing these parameters adaptively according to object characteristics, the system achieves versatility across different object types without requiring separate predefined programs for each scenario.
2Measurement precision
If multiple candidate grasp strategies are evaluated to find the optimal grasp, then the grasp accuracy improves, but the computational time and processing complexity increase
Solution Approach 1:
The system performs preliminary actions by pre-training machine learning models on extensive datasets of objects and grasp strategies. During actual operation, the already-trained models can quickly evaluate candidate grasps and select the optimal strategy without requiring time-consuming real-time analysis, thus achieving both high accuracy and fast execution.
Solution Approach 2:
The system uses semantic indications and grasp region mappings that serve as simplified representations or copies of the full grasp evaluation process. Instead of performing complete physical simulations for each candidate grasp, the system uses pre-computed semantic features and region data to rapidly determine the optimal grasp strategy.
Data Source
AI summary
Grasping of an object, by an end effector of a robot, based on a grasp strategy that is selected using one or more machine learning models. The grasp strategy utilized for a given grasp is one of a plurality of candidate grasp strategies. Each candidate grasp strategy defines a different group of one or more values that influence performance of a grasp attempt in a manner that is unique relative to the other grasp strategies. For example, value(s) of a grasp strategy can define a grasp direction for grasping the object (e.g., “top”, “side”), a grasp type for grasping the object (e.g., “pinch”, “power”), grasp force applied in grasping the object, pre-grasp manipulations to be performed on the object, and/or post-grasp manipulations to be performed on the object.