Optimization method for improving the reliability of goods commissioning using a robot

1. An optimization method for improving the reliability of a pickup and discharge of articles according to an order in a picking process using a robot, wherein the robot has a robot head movable relative to a robot base and comprises a gripping unit, and wherein the picking process comprises the steps of picking up an article having an outer packaging from or out of a first load carrier and placing in or on or dropping into or onto a second load carrier by means of the gripping unit, the method comprising:

performing an image processing step comprising determining a gripping surface size and a gripping surface pose of the article by an opto-sensory preparation and analysis system, and calculating a gripping pose for the gripping unit from the gripping surface size and the gripping surface pose of the article determined by the opto-sensory preparation and analysis system,

determining at least one dimension of the outer packaging of the article to provide a determined dimension when the gripping surface size is determined,

comparing the determined dimension with dimension ranges stored in an article parameter field and allocating the determined dimension to an allocated dimension range of the dimension ranges, and

selecting a dimension value for the allocated dimension range, and allocating the dimension value so selected to the determined dimension, wherein depending on a confidence value of the allocated dimension range, the dimension value is selected from stored article reference data or from a normalization value of the allocated dimension range, wherein the normalization value and the confidence value of the allocated dimension range are stored in the article parameter field,

performing a preparation step comprising applying a mathematical scattering measure function for the determined dimension and for the dimension ranges stored in the article parameter field to determine normalization values and confidence values of the dimension ranges, and

moving the gripping unit to the gripping pose for the gripping unit calculated in the image processing step to pick-up the article.

2. The optimization method according to claim 1 , further comprising a counting step following the pickup of the article by the gripping unit, the counting step comprising determining a numeric quantity of picked-up articles by

determining an article weight by means of a weighing device,

comparing the article weight with weight ranges stored in the article parameter field, and determining a weight range allocation, and

determining a determined number value for the weight range allocation, wherein depending on a confidence value of a weight range from the weight ranges, the determined number value is selected from stored article reference data or from a normalization value of the weight range, wherein the normalization value and the confidence value of the weight range are stored in the article parameter field, and wherein the preparation step further comprises applying the mathematical scattering measure function for the article weight and for the weight ranges stored in the article parameter field to determine normalization values and confidence values of the weight ranges.

3. The optimization method according to claim 2 , wherein the weighing device is arranged separately from the robot and acquires the weight of the first load carrier, and the counting step is executed before discharge of the articles.

4. The optimization method according to claim 2 , wherein, in case of a determined number value which is greater than one, a check is executed as to whether the determined number value exceeds a target quantity of articles to be picked, wherein the target amount is stored in the order, and in case of exceedance, a special handling step is performed.

5. The optimization method according to claim 4 , wherein the special handling step comprises controlling the robot to move the robot head to the first load carrier and to place the picked-up article on or in the first load carrier or to drop the picked-up article onto or into the first load carrier.

6. The optimization method according to claim 2 , wherein, in case of exceeding a limit value of the determined number value, or in case of exceeding a range limit value during the determination of the weight range allocation, a special handling step is performed.

7. The optimization method according to claim 2 , wherein the normalization value of the weight is calculated by means of a mathematical weighting function from all normalization values of the weight ranges.

8. The optimization method according to claim 2 , wherein the mathematical scattering measure function comprises an expectation-maximization algorithm and iteratively groups determined values, dimensions and/or weight values into local clusters.

9. The optimization method according to claim 8 , wherein a probability distribution is applied to the grouped values, and wherein for local clusters, a mean value and a mean value scatter are determined and the mean value is defined as the normalization value.

10. The optimization method according to claim 2 , wherein the mathematical scattering measure function comprises a sum of weighted normal distributions and iteratively groups values, dimensions and/or weight values into local clusters.

11. The optimization method according to claim 2 , further comprising an adaptation step comprising

adapting the dimension ranges to the normalization values determined in the preparation step, and/or

adapting the weight ranges are adapted to the normalization values determined in the preparation step.

12. The optimization method according to claim 2 , wherein, for each of the dimension ranges and/or for each of the weight ranges, the confidence value is determined from a scattering of the normalization value, and/or wherein the confidence value is determined from the number of preparation steps performed.

13. The optimization method according to claim 2 , wherein, when forming the normalization and confidence value, a window function is applied, in each case, to the determined dimensions and article weights.

14. The optimization method according to claim 2 , wherein, when article reference data is missing, a series of article transfers between the first and the second load carriers is executed, and the article parameter field with normalization values and confidence values for dimensions and/or article weights is created from the respectively determined dimensions and/or article weights.

15. The optimization method according to claim 14 , wherein a fluctuation range is determined from a series of normalization or confidence values of the dimensions and/or of the article weights, and the article transfers are stopped when falling below a threshold of the fluctuation range.

16. The optimization method according to claim 2 , wherein, in case of a high confidence value for the dimension normalization value or for a weight normalization value, an automated or semi-automated update of the article reference data is executed.

17. The optimization method according to claim 1 , further comprising a counting step following the pickup of the article by the gripping unit, the counting step comprising determining a numeric quantity of picked-up articles by

determining an article weight by means of a weighing device,

calculating a quotient from the article weight determined by the weighing device divided by a normalization value of the weight,

scaling the quotient to obtain a scaled quotient and comparing the scaled quotient with the weight ranges, and determining a weight range allocation, and

determining a determined number value for the weight range allocation, wherein depending on a confidence value of a weight range from the weight ranges, the determined number value is selected from stored article reference data or from a normalization value of the weight range, wherein the normalization value and the confidence value of the weight range are stored in the article parameter field, and wherein the preparation step further comprises applying the mathematical scattering measure function for the article weight and for the weight ranges stored in the article parameter field to determine normalization values and confidence values of the weight ranges.

18. The optimization method according to claim 17 , wherein a range classification is performed for a decimal value of the quotient, and for a first range, the determined number value is determined by the integer part of the quotient, and for a second range, a special handling is performed.

19. The optimization method according to claim 18 , wherein for a third range, the confidence values of two adjoining weight ranges are analyzed, and the article weight is determined from the normalization value of the weight range with a higher confidence value.

20. The optimization method according to claim 1 , further comprising checking as to whether the determined dimension is in an overlap region of two dimension ranges, and in the case of the determined dimension being in the overlap region, performing a special handling step to allocate the determined dimension to one of the two dimension ranges.

21. The optimization method according to claim 20 , wherein in case of a determined position of the dimension in the overlap region, the image processing step is executed again in the special handling step.

22. The optimization method according to claim 20 , wherein in the special handling step comprises controlling the robot to move the robot head to the first load carrier and to pick-up the article and to place the article again, and subsequently, executing the image processing step again.

23. The optimization method according to claim 1 , wherein the normalization value is defined as a mean value of a normal distribution.

24. A workstation comprising:

a first provisioning position for the first load carrier,

a second provisioning position for the second load carrier,

the robot having the robot head, wherein the robot head is movable relative to the robot base and comprises the gripping unit for transferring articles between the first and second load carriers,

an image capturing device, and

a data processing unit configured for controlling the robot and for evaluating data from the image capturing device,

wherein the data processing unit is configured for performing the method according to claim 1 .