Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

188 results about "Weight transfer" patented technology

Weight transfer and load transfer are two expressions used somewhat confusingly to describe two distinct effects: the change in load borne by different wheels of even perfectly rigid vehicles during acceleration, and the change in center of mass (CoM) location relative to the wheels because of suspension compliance or cargo shifting or sloshing. In the automobile industry, weight transfer customarily refers to the change in load borne by different wheels during acceleration. This is more properly referred to as load transfer, and that is the expression used in the motorcycle industry, while weight transfer on motorcycles, to a lesser extent on automobiles, and cargo movement on either is due to a change in the CoM location relative to the wheels. This article uses this latter pair of definitions.

Open set category mining and extending method based on depth neural network and device thereof

The invention discloses a sample categorization method based on a depth neural network. The open set category mining and extending method based on a depth neural network comprises steps of using a sample set comprising defined category samples to train a categorized model to be extended, obtaining categorization threshold value information, sending a sample set comprising undefined category samples into the categorization model to be extended, determining at least part of the undefined category samples according to the categorization threshold value information of the categorization model to be extended, artificially marking the undefined category samples, adding a number of columns of a weight transfer matrix in a categorization layer of the depth nerve network in order to increase a total number of model recognition categories, wherein the added weight columns comprise first information associated with global categorization and second information associated with connection between categories and using the undefined category samples which are artificially marked to increase the models which already finish training and updating. The open set category mining and extending method based on the depth neural network and the device thereof extend the depth neural network through modifying a depth neural network categorization layer weight transfer matrix, dynamically increases the number of the recognized categories so as to process the open set recognition problem and can be applied to a scene which is closer to a real scene.
Owner:PEKING UNIV +1

Lower limb rehabilitation exoskeleton system and walking control method thereof

ActiveCN108379038AAvoid problems with hard landingWalking aidsMedical robotWeight transfer
The invention relates to a lower limb rehabilitation exoskeleton system and a walking control method thereof, and belongs to the technical field of medical robots. The walking control method comprisesa real-time data acquisition step, a gait phase recognition step and an exoskeleton control step, wherein the exoskeleton control step comprises the following operations: controlling a main supporting leg of an exoskeleton to be kept in a nearly upright state in a swinging process that a swing leg of the exoskeleton is to leave away from the ground up until the swing leg is to touch the ground; and controlling the swing leg of the exoskeleton to conduct a swinging action in a mode of leaving away from the ground when the exoskeleton is kept in a gait phase that the swing leg is to leave awayfrom the ground and after a weight transfer criterion is satisfied, wherein the weight transfer criterion is that an inclination angle of the upper body of an exoskeleton wearer is located within a first preset interval and plantar pressure of the exoskeleton wearer is located within a second preset interval. On the basis of the walking control method, a lateral overturning moment can be effectively eliminated, so that stable walking of the exoskeleton wearer can be guaranteed; and the exoskeleton system can be widely applied to rehabilitation training of patients with lower limb weakness or hemiplegia.
Owner:ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products