Microsoft technology licensing, llc (20240264658). PREDICTING BODY MOTION simplified abstract
Contents
- 1 PREDICTING BODY MOTION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 PREDICTING BODY MOTION - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Key Features and Innovation
- 1.6 Potential Applications
- 1.7 Problems Solved
- 1.8 Benefits
- 1.9 Commercial Applications
- 1.10 Prior Art
- 1.11 Frequently Updated Research
- 1.12 Questions about Motion Prediction Technology
- 1.13 Original Abstract Submitted
PREDICTING BODY MOTION
Organization Name
microsoft technology licensing, llc
Inventor(s)
Mohammand Sadegh Ali Akbarian of Cambridge (GB)
Fatemehsadat Saleh of Cambridge (GB)
Pashmina Jonathan Cameron of Cambridge (GB)
PREDICTING BODY MOTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240264658 titled 'PREDICTING BODY MOTION
Simplified Explanation
The patent application describes a method for predicting body motion of an articulated entity using a motion model based on a reference joint pose and a mask token.
Key Features and Innovation
- Motion model predicts body motion of an articulated entity.
- Reference joint pose and mask token used to prompt the motion model.
- Mask token represents unobserved or observed joints of the entity.
- Temporally adaptable mask token based on indications of joint observance.
- Utilizes information from previous and current time steps for mask token adaptation.
Potential Applications
This technology can be applied in:
- Animation and gaming industries for realistic character movements.
- Robotics for predicting and controlling articulated robot motion.
- Sports analytics for tracking and analyzing athlete movements.
Problems Solved
- Predicting body motion of articulated entities accurately.
- Adapting to unobserved joints in real-time scenarios.
- Enhancing motion modeling for various applications.
Benefits
- Improved accuracy in predicting body motion.
- Real-time adaptation to unobserved joints.
- Enhanced performance in animation, robotics, and sports analytics.
Commercial Applications
Title: Real-time Motion Prediction Technology for Animation and Robotics This technology can be commercialized in:
- Animation software for creating lifelike character animations.
- Robotics industry for precise control of articulated robot movements.
- Sports analytics platforms for advanced athlete performance analysis.
Prior Art
Readers can explore prior art related to motion prediction models in animation, robotics, and sports analytics fields.
Frequently Updated Research
Stay updated on the latest advancements in motion prediction models for articulated entities in animation, robotics, and sports analytics.
Questions about Motion Prediction Technology
How does this technology improve motion prediction accuracy?
This technology enhances accuracy by using a reference joint pose and a mask token to prompt a motion model that adapts to unobserved joints.
What are the potential applications of this motion prediction technology?
This technology can be applied in animation, robotics, and sports analytics for predicting and analyzing body motion of articulated entities.
Original Abstract Submitted
for each of a plurality of time steps: receive a reference joint pose of an articulated entity and receiving an indication that another joint of the articulated entity is unobserved or observed. prompt a motion model using the reference joint pose and a mask token. the model predicts body motion comprising a trajectory of the articulated entity and a pose of a plurality of joints of the articulated entity. the mask token represents the other joint and is temporally adaptable by: in response to receiving an indication that the other joint is unobserved, using information about the reference joint pose and a pose of the other joint from a previous time step; and in response to receiving an indication that the other joint is observed, using information about the reference joint pose and a pose of the other joint from the current time step.