5results about How to "Improve anthropomorphism" patented technology

The application discloses a kind of humanoid posture constraint under redundant mechanical arm inverse kinematics solving method, belong to robot control technical field;The method includes the following operations: S1, in offline training stage, construct humanoid posture model;Step S1 includes the following operations: S11, human body double-arm joint angle data extraction;S12, sine / cosine coding and standardization processing;S13, variational autoencoder humanoid prior training;S2, online solving stage, utilize the inverse kinematics solving of constructed humanoid posture model, in combination with particle swarm optimization algorithm PSO;The application is constructed by constructing humanoid posture model, and the implicit space distribution of humanoid posture is learned from human motion data using variational autoencoder, and human motion feature is quantified as the humanoid penalty that can be calculated, which provides the evaluation basis for the naturalness of the posture of the robot arm, solves the problem that the posture of the inverse kinematics solving result is not natural in the prior art, and the human motion data and the kinematic characteristics of the robot arm are not matched.

The application provides a game AI training method and device, electronic equipment and a storage medium. By introducing attention to all players in a game scene and predicting the macro decision of all players in a game, the perception of the game AI to the behaviors of other players can be enhanced, the data utilization rate in model training can be effectively improved by fully utilizing the data of all players in each game, the humanization of the game AI can be improved, the game AI is more realistic, and the application can be effectively applied to different application scenarios of various competitive games to improve the user experience of game players.

The invention discloses an automatic driving behavior decision-making method based on an intention-driven risk field. The method comprises the following steps: 1, eliminating geometric distortion by constructing a generalized bounding box; 2, introducing a momentum correction and intention coupling mechanism, and dynamically remodeling a risk field topology to simulate defensive driving psychology; and 3, scoring by using a space-time most disable principle, carrying out decision by combining with a dual risk threshold state machine, and introducing a decision reversal mechanism to break deadlock. According to the method, the problem of driving behavior decision oscillation is effectively solved, and the traffic efficiency and safety in a complex interaction scene are remarkably improved.

Embodiments of the present application disclose a virtual object control method and device, a terminal, a storage medium and a program product, and belong to the technical field of computers. The method comprises: displaying a first virtual object and a second virtual object, the second virtual object being a virtual object that automatically follows the first virtual object to move; controlling the first virtual object to move in a virtual environment; and in the case that the first virtual object moves, controlling the second virtual object to move to a target position in the virtual environment, the target position being located in a front region of the first virtual object in the moving process. The method provided by the embodiments of the present application can automatically move the second virtual object to a front position of the first virtual object, and the second virtual object no longer needs to move based on a real-time position of the first virtual object, so that the following performance of the second virtual object is more natural, which helps to improve the personification of the virtual object in the automatic following state, thereby improving the authenticity of the game.