Inventec had no grants in future of work as a theme in Q2 2024.

Recent Patents

Application: Transition method of locomotion gait of robot (Patent ID: US20240157548A1)

The patent filed by Inventec Corp. describes a transition method for the locomotion gait of a robot, involving the use of neural network models to control the robot's movements. The method includes a deployment procedure where source and destination policies are randomly selected, a transition operation is simulated, and results are recorded in a transition database. A transition-net is trained based on this database, and a meta-controller on the robot selects gait policies, inputs them into the transition-net to determine success probability, and executes the queued policy if the probability exceeds a threshold.

Additionally, the method involves collecting videos of various locomotion gaits, creating neural network models for each gait, training them through reinforcement learning with domain randomization, and storing them in a library upon completion. The neural network model structure includes input layers representing joint angles, robot direction, velocities, and ground contact, middle layers as latent states, and output layers for control parameters. The transition-net is described as a feed-forward neural network with specific neuron configurations and activation functions, and the simulation of transition operations utilizes the Issac Gym simulator.

To know more about GlobalData’s detailed insights on Inventec, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

Be better informed