Robotics Motion Retargeting Using Reference-Point Control Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotics control systems are inefficient in quickly and accurately generating control signals for robotics devices to perform target motions, especially when retargeting expressive motions across devices with varying characteristics, relying on manual programming and trial-and-error, and often require artificial intelligence or machine learning, which limits user control and accuracy.
Innovation Solution
A computer-implemented method that determines control signals by correlating movement data points with reference points on a robotics device, minimizing distances and optimizing trajectories, allowing for real-time retargeting of motions across devices with different proportions, mass distributions, and degrees of freedom without relying on AI or ML, using a system that includes processors and memory to perform calculations and generate control signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual programming and trial-and-error methods are used to program controllers for robotic devices, then control accuracy can be achieved, but the time and effort required to update desired movement patterns across different robotic devices increases significantly
Solution Approach 1:
The patent uses motion capture data from a source subject (human or animal) as a template to generate control signals for the robotic device. Instead of manually programming each controller, the system copies movement patterns from recorded data and adapts them to the target robotic device's characteristics, dramatically reducing programming time while maintaining accuracy
Solution Approach 2:
The system adjusts control signals by changing parameters based on the target robotic device's physical characteristics (mass, dimensions, degrees of freedom). The controller modifies movement parameters from the motion capture data to match the specific dynamics of each robotic device, enabling accurate control without manual reprogramming
2Adaptability or versatility
If controllers are programmed to accurately control robotic devices with different proportions and characteristics, then adaptability across devices is improved, but the complexity of programming and testing increases
Solution Approach 1:
The control system is designed to be universal by accepting motion capture data as a common input format and automatically adapting it to different robotic devices. The system uses a standardized approach that works across devices with varying proportions and characteristics, eliminating the need for device-specific programming while maintaining adaptability
Solution Approach 2:
The system automatically generates and adjusts control signals based on the target device's characteristics without requiring manual intervention. The controller self-adapts by computing appropriate control parameters from the motion capture data and the device's physical properties, reducing programming complexity while maintaining versatility
Data Source
AI summary
Techniques for generating robotics control signals are disclosed. Movement data is received for a desired motion for a robotics device, which can include animation, motion capture, sensor data, or movement of a different robotics device. Robotics device data is received, including control data and reference points corresponding to locations on the robotics device. A correlation is determined between movement data points in the movement data and the reference points. Using the control data, a control signal is determined based on the desired motion. The control signal is based on a distance between at least one movement data point and at least one reference point. The disclosed technology can retarget motions onto under-actuated systems and without regard to differences in degrees of freedom, mass distributions, and proportions of robotics devices.