Robotic Hand Pre-Grasp Sequencing for Multi-Object Grasping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic systems struggle to efficiently grasp and transfer multiple objects at once due to challenges in estimating object quantity and pose, occlusion, and the chaotic displacement of objects during grasping, leading to inefficiencies in perception and grasping accuracy.
Innovation Solution
A robotic system utilizing a Markov decision process to identify optimal pre-grasp and end-grasp configurations, combined with stochastic flexing routines and deep learning for object quantity estimation, to efficiently grasp and transfer multiple objects by modeling the grasping process as a Markov decision process (MDP) and employing a stochastic flexing routine to explore the grasping action space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a robotic system grasps one object at a time, then the grasping accuracy is maintained, but the productivity is reduced
Solution Approach 1:
The patent segments the grasping task into two distinct phases: pre-grasp configuration (fingers spread apart for insertion) and end-grasp configuration (fingers closed for securing objects). This segmentation allows the robotic system to maintain precise control over finger positioning while efficiently handling multiple objects, resolving the contradiction between grasping accuracy and transfer efficiency
Solution Approach 2:
The system performs preliminary action by identifying and executing the pre-grasp configuration before actual object contact. The fingers are positioned in a spread state and moved to the target location first, then transition to the closed configuration. This preliminary positioning enables accurate multi-object grasping without requiring complex real-time adjustments, thereby improving productivity while maintaining precision
2Productivity
If a robotic system grasps multiple objects at once, then the productivity is improved, but the measurement precision deteriorates due to challenges in estimating object quantity and pose
Solution Approach 1:
The patent employs dynamic transition between two distinct finger configurations: pre-grasp (spread) and end-grasp (closed). This dynamic approach allows the system to adapt to multiple object quantities and arrangements by adjusting the transition timing and finger trajectories, maintaining measurement precision while achieving high productivity in multi-object grasping
Solution Approach 2:
The system changes key parameters including finger spread angle, closure timing, and grasp force based on the detected object quantity and pose. By dynamically adjusting these parameters according to the specific multi-object scenario, the system overcomes estimation challenges and maintains accurate grasping while transferring multiple objects efficiently
3Productivity
If a robotic system uses complex grasping configurations for multiple objects, then the productivity is improved, but the device complexity increases
Solution Approach 1:
The patent simplifies device complexity by segmenting the grasping control into two distinct, pre-defined configurations (pre-grasp and end-grasp) with clear transition rules. This segmentation reduces the control complexity compared to continuous adaptive grasping, while still enabling efficient multi-object transfer through systematic configuration switching
Data Source
AI summary
Systems and methods for multiple object transferring using robotics. A system includes a robotic hand with a base and fingers capable of grasping objects. A robotic arm is coupled to the robotic hand and is capable of moving the robotic hand. One or more circuits are configured to operate the robotic hand and the robotic arm by identifying a pre-grasp configuration for the robotic hand and executing a transfer routine based on a Markov decision process model to operate the robotic hand and the robotic arm such that they move multiple objects from a first location to a second location.