Real-time multi-mode accompanying robot intention understanding method and system
A companion robot and multi-modal technology, applied in the direction of neural learning methods, instruments, computer components, etc., can solve the problems of rare old people's intention understanding model, and the lack of a good solution to the efficient extraction of environmental semantic information and intention understanding, to achieve The effect of fast running speed, small training data and strong flexibility
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0051] Embodiment 1 of the present invention proposes a real-time multi-modal escort robot intent understanding method, part of which is contextual intent reasoning based on knowledge-based semi-naive Bayesian, which mainly includes gesture and body gesture labels obtained in real time by the neural network and detection Intention reasoning results are obtained by fusing the existence features of items with special semantics; the other part is distance-based intention reasoning, including the analysis of the position-distance relationship between characters and special items, and the probability of the user’s intention to interact with related items around is obtained from The intent probabilities derived from distance inference optimize the knowledge-based probabilities so that the probabilities from the two parts are fused to obtain the final intent. Such as figure 1 It is an overall block diagram of the implementation of a real-time multimodal escort robot intent understand...
Embodiment 2
[0085] Based on the method for understanding the intent of a real-time multi-modal escort robot proposed in Embodiment 1 of the present invention, Embodiment 2 of the present invention also proposes a system for understanding the intent of a real-time multi-modal escort robot. Such as image 3 It is a connection schematic diagram of a real-time multi-modal escort robot intent understanding system according to Embodiment 2 of the present invention. This includes a first calculation module, a second calculation module and an intent fusion module;
[0086] The first calculation module is used to identify the user’s local information and the target object when the distance between the user and the robot meets the requirements of safety detection; measure the sum of the distances from all target objects to the user, and calculate the probability of intentional interaction between the target object and the user ;
[0087] The second calculation module is used to obtain the interde...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


