The following operators can be used to better focus your queries.
( ) , AND, OR, NOT, W/#
? single char wildcard, not at start
* multi char wildcard, not at start
(Cat? OR feline) AND NOT dog?
Cat? W/5 behavior
(Cat? OR feline) AND traits
Cat AND charact*
This guide provides a more detailed description of the syntax that is supported along with examples.
This search box also supports the look-up of an IP.com Digital Signature (also referred to as Fingerprint); enter the 72-, 48-, or 32-character code to retrieve details of the associated file or submission.
Concept Search - What can I type?
For a concept search, you can enter phrases, sentences, or full paragraphs in English. For example, copy and paste the abstract of a patent application or paragraphs from an article.
Concept search eliminates the need for complex Boolean syntax to inform retrieval. Our Semantic Gist engine uses advanced cognitive semantic analysis to extract the meaning of data. This reduces the chances of missing valuable information, that may result from traditional keyword searching.
A method of developing software that will "remember" which previous retry worked the best on each specific pallet and hole and then attempt that retry first is described herein.
English (United States)
This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately
93% of the total text.
Page 1 of 2
Robot Artificial Intelligence
A method of developing software that will "remember" which previous retry
worked the best on each specific pallet and hole and then attempt that retry first
is described herein.
If the most ideal retry is not effective, then the second most successful retry
is attempted, and so forth, until the robot finds the correct position. The robot
then adds the successful retry number to its "memory" for that pallet hole.
The robot's "artificial intelligence" is achieved by keeping a log in memory for
each hole on each pallet in terms of which previous retry worked (see Fig. 1).
Each retry offset is an entry in the log and when that retry works, the count for
that retry is incremented. When the robot goes to load a hole, it looks in the log
for that hole to see which retry variation has the highest count or best success,
and it attempts this one first. If that does not work, then the log is checked for the
second highest count, and so forth.
Putting new pallets on the system requires all the retry logs to be zeroed and
the robot must then "learn" the new pallets. With the logs zeroed, the robot will
start with retry 1 (see Fig. 2) and continue until the right position is found.
Learning the pallet takes only 3-4 runs to build up a somewhat reasonable entry
log so that the robot will load into the right position.
In the past, retries were tried sequentially with no memory, and thus if the
20th retry was the proper one for each h...