Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

5 results about "Merit function" patented technology

Dynamic memory augmentation method and system for visual-linguistic-action model and readable storage medium

The application provides a dynamic memory enhancement method and system for a visual-language-action model and a storage medium, and solves the problems of short-sighted memory, memory pollution and inability to dynamically adjust the fusion weight of the existing VLA model in a long-distance task. The application comprises: constructing a working memory and retrieving historical memory from a perception-cognition-reward memory bank; using a gating network with trainable parameters to adaptively weight and fuse the current memory and the historical memory to generate an enhanced working memory; using a progress evaluator to calculate a task progress difference value based on the enhanced working memory to generate a single-step dense reward; using the reward as a merit function to perform online policy optimization on the gating network parameters; and when the memory bank is full, merging adjacent entries based on the weighted indicators of feature similarity and reward similarity; and finally outputting a motion sequence by a motion expert network. The application can be used for robot long-time sequence task learning and adaptive control in a dynamic environment.
Owner:HARBIN INST OF TECH

Method for optimizing the pupil diaphragm shape for simulating the illumination and imaging properties of an optical production system during illumination and imaging of an object by an optical measurement system - Patents.com

To simulate the characteristics of the optical generation system, an optical measurement system is used, which includes an illumination optical unit for an object to be imaged with a pupil stop in the region of the illumination pupil and an imaging optical unit for imaging the object. To optimize the pupil stop shape of the pupil stop, first, a starting aperture shape of the pupil stop is predefined (30) as an initial design candidate for the simulation. The starting aperture shape is modified (31) and at least one manufacturing boundary condition of the corresponding modified aperture shape is checked (33). The "modifying" and "checking" steps are repeated until the checking (33) step indicates compliance with the boundary conditions. A matching quality between the characteristics of the optical generation system and the characteristics of the optical measurement system is determined (34), the matching quality is queried (35), and the "modifying", "checking" and "determining" steps are repeated until a predefined optimization criterion is reached. A target aperture shape resulting from the target aperture shape resulting in the minimum merit function value E in the optimization is manufactured (37) as an optimized pupil stop shape after the optimization criterion is reached. This results in a simulation of the illumination and imaging properties of the optical generation system that is as free as possible from deviations during illumination and imaging of an object by the optical measurement system.
Owner:CARL ZEISS SMT GMBH

Merit function switching type derivative-free trust region wavefront correction system and method

PendingCN122362650AWavefrontAlgorithm
A wavefront correction system and method with evaluation function switching and derivative-free trust region (RDR) is disclosed. This invention relates to the field of optimization and control technology for wavefront-free adaptive optics systems, specifically to a wavefront correction system and method with evaluation function switching and derivative-free trust region (RDR) optimization. The invention organically integrates a phased evaluation function strategy with a model-based derivative-free trust region optimization algorithm, achieving seamless switching of the evaluation function through observation data reuse. The method includes the following steps: simultaneously defining a first evaluation function and a second evaluation function; performing first-stage derivative-free trust region wavefront correction based on the evaluation function, while simultaneously constructing an observation data reuse buffer; switching to second-stage derivative-free trust region wavefront correction; selecting historical sampling points from the observation data reuse buffer, performing second-stage derivative-free trust region wavefront correction based on the observation data, and obtaining the optimal sampling point; updating the wavefront correction value based on the optimal sampling point.
Owner:CHANGGUANG SATELLITE TECH CO LTD

Composite evaluation function stray light optimization method based on dual-mode ray tracing

The invention discloses a composite evaluation function stray light optimization method based on dual-mode ray tracing, and the method comprises the steps: 1, building a light source model and an optical-mechanical structure model; 2, according to light source information and optical system matrix information, sequence optical tracing is carried out, and a loss1 value is obtained according to a result; step 3, performing non-sequence optical tracing according to the light source information and the optical system matrix information, and obtaining a loss2 value according to a result; and step 4, optimizing the optical system by using a differential genetic algorithm in a dynamic weight distribution mode to obtain an optimized optical system. Compared with a traditional optimization mode, the optimization mode provided by the invention considers the system imaging quality while optimizing the stray light level, and meanwhile, the non-sequence tracing efficiency is improved by using the matrix, so that the time cost in the optimization process is reduced. The method is of great significance to stray light optimization of an optical system.
Owner:李路言 +4