Robotic Arm Motion Mapping for Human-Like Imitation Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for imitating human arm movements by robotic arms suffer from low similarity due to the complexity of handling multiple degrees of freedom and the need for accurate motion planning, often relying on inefficient three-dimensional modeling and noise-prone data processing.
Innovation Solution
A method involving the acquisition of pose information from human arms using infrared positioning, denoising, and motion mapping to convert human arm movements into robotic arm movements, utilizing inverse kinematics and oriented bounding boxes for collision detection to ensure safe and stable motion imitation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional motion capture systems are used to extract human motion information, then motion data can be obtained, but the imitation similarity is low due to complexity in handling multiple degrees of freedom
Solution Approach 1:
The patent segments the human arm motion into discrete key points (shoulder, elbow, wrist) and processes each point's pose information separately. This segmentation simplifies the handling of multiple degrees of freedom by breaking down the complex motion capture data into manageable components that can be independently mapped to robotic arm joints.
2Manufacturing precision
If three-dimensional modeling is used for motion mapping, then human arm movements can be replicated, but the computational load is high and processing is inefficient
Solution Approach 1:
The patent replaces complex three-dimensional modeling with a simplified coordinate system transformation approach. By using direct pose information from key points and applying coordinate transformations, the system achieves accurate motion mapping without the heavy computational burden of full 3D modeling, thereby improving processing efficiency.
3Productivity
If motion data is processed without denoising, then processing is faster, but the data is noise-prone and affects imitation quality
Solution Approach 1:
The patent applies denoising processing as a preliminary step before motion mapping. By filtering and cleaning the pose information from key points beforehand, the system ensures high-quality input data for the mapping process, which improves imitation accuracy without significantly impacting overall processing speed.
4Device complexity
If collision detection is not performed, then the system is simpler, but safety cannot be ensured during motion imitation
Solution Approach 1:
The patent introduces collision detection as an intermediary safety mechanism between the motion mapping and execution phases. By detecting potential collisions before motion execution, the system ensures safety during motion imitation while maintaining relative simplicity through targeted detection rather than comprehensive system complexity.
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 method achieves high imitation similarity and stability by accurately mapping human arm motions onto robotic arms, reducing computational load and ensuring safety through effective collision detection, thus improving the robotic arm's ability to replicate human-like motions.
Implementation Method 1
acquiring first pose information of key points of a human arm to be imitated
Data Source
AI summary
A method for controlling an arm of a robot to imitate a human arm, includes: acquiring first pose information of key points of a human arm to be imitated; converting the first pose information into second pose information of key points of an arm of a robot; determining an angle value of each joint of the arm according to inverse kinematics of the arm based on the second pose information; and controlling the arm to move according to the angle values.