Grasp Neural Network Output Transformation for Covariate Shift

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Covariate shift in grasping neural networks, which occurs when the distribution of input data changes between training and inference regimes, leading to sub-optimal or incorrect labels for pixels, resulting in poor robotic grasping operations.

Innovation Solution

Transform the output of grasping neural networks to address covariate shift by filtering out incorrectly labeled grasp scores and adjusting grasp locations to avoid edges and potential collisions, without the need for retraining or regenerating datasets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If grasping neural networks are trained on synthetic data, then training efficiency and safety are improved, but covariate shift occurs when deployed with real camera data, degrading performance

Engineering Contradiction:
Improvetraining safetyVSAvoidgrasp score accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent introduces an output transformation layer as an intermediary between the neural network and the grasp execution. This transformation layer adjusts the network outputs to compensate for covariate shift, effectively mediating between synthetic training data and real-world deployment conditions without requiring retraining

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent modifies the neural network output parameters through transformation functions that adjust grasp scores and locations based on the detected covariate shift. This allows the system to adapt to real camera data distribution by changing the output parameters dynamically

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If neural network output is transformed to address covariate shift, then grasp location accuracy is improved, but additional processing steps are required

Engineering Contradiction:
Improvegrasp location accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs covariate shift compensation and output transformation as preliminary actions during the inference process. By addressing the covariate shift early in the pipeline through transformation layers, the system avoids more complex post-processing steps that would be required otherwise

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4327299B1Transformation for covariate shift of grasp neural networks
Publication Date: 2026.01.21 SIEMENS AG
  • EP4327299B1 patent drawingFigure 1
  • EP4327299B1 patent drawingFigure 2
  • EP4327299B1 patent drawingFigure 3

AI summary

A covariate shift generally refers to the change of the distribution of the input data (e.g., noise distribution) between the training and inference regimes. Such covariate shifts can degrade the performance grasping neural networks, and thus robotic grasping operations. As described herein, an output of a grasp neural network can be transformed, so as to determine appropriate locations on a given object for a robot or autonomous machine to grasp.