TheSwamp
CAD Forums => CAD General => Topic started by: jtm2020hyo on March 23, 2019, 10:42:05 PM
-
Exist some way to use Machine Learning or Artificial intelligence to draw automatically in AutoCAD?
I found some videos where explain that Machine Learning and Artificial intelligence can be used for everything and I can teach to the Machine or A.I. to draw like my old projects.
...If this it's possible then someone already did?
... please share me some projects related to this.
-
One of the road blocks for AI and Machine Learning with AutoCAD (or any drafting package ) is the requirement for "someone" to set the rules.
Design standards and drafting standards are different from country to country as well as in some cases between organisations in each country ... this is without taking into account the contradictions within some standards, Then there ispersonal preferences to be considered.
The mechanics of the technology is relatively simple, but ...
added: Don't expect a return on investment in the short term :)
-
One of the road blocks for AI and Machine Learning with AutoCAD (or any drafting package ) is the requirement for "someone" to set the rules.
Design standards and drafting standards are different from country to country as well as in some cases between organizations in each country ... this is without taking into account the contradictions within some standards, Then there is personal preferences to be considered.
The mechanics of the technology is relatively simple, but ...
added: Don't expect a return on investment in the short term :)
I think AutoCAD 3d, Revit, fusion, or any 3d drawing will be hard, painful and expensive to develop. So my choice is to draw in AutoCAD 2d.
I just want to draw in 2D because is very similar issues with 2D games solved by Machine learning showed in videos from youtube.
So I think at least one guys on this planet has already developed a way to draw with machine learning in Autocad.
...So I want, if exist, a template project that someone already shared, or if not exist such project, I just want to develop such an idea since zero but using any project of any game already published that can be used in AutoCAD.
...Well, that is my first idea. I hope someone can help me.
PD: I'm just an enthusiast that think is already the time to developing AUTOCAD for LINUX and create a Machine Learning or Artificial Intelligence solution for Autocad
-
On another forum of sorts ...
Today, Siemens PLM Software announced a new capability coming to #NX: a #machinelearning powered interface called Adaptive UI. I think there are near-term benefits that are worthwhile, but I also see this as the tip of the iceberg of applying #artificialintelligence as a #virtualassistant in #3dcad. Let me know your thoughts. Share if you can.
To be honest I find the proliferation of AI into everything disturbing. Yes, despite making a living from, and having genuine love for the craft of programming. (Arguably) This isn't going to speed up design or make for more efficient drafting. (Unrefutable) It will however make us more vulnerable to sinister exploit than we already are. Do you really want machines watching you ALL THE TIME? Ewww.
Curmudgeonly yours, MP.
-
For now, you may as well read any reference to "machine learning" the same as "blockchain" i.e. marketing hype.
-
In theory it's being already being done (https://www.autodesk.com/redshift/machine-learning/). I think machine learning has great potential to help out in the design/drafting space. I've been looking at how to implement it myself.
My current genre of design (landscape) is mostly 2D. After taking a machine learning class, I've had a difficult time figuring out how I could apply it to my designs. That doesn't mean it can't be done, it just means I'm not there yet. As with many problems, one of the hardest parts is figuring out what question to ask, and how to ask it.
My current thought on how to apply it to CAD looks something like:
Build a machine learning model
- Using existing completed designs (dwg files) use LISP/.NET to generate hundreds or thousands of problem and solution datasets (probably text files, possibly images)
- Write some miracle machine learning code, (Python) and generate a really nice ML model as an analysis tool
Use that model for new designs
- Using the same code in the first step , generate a problem set from a dwg file you want to design to
- Feed that problem dataset to the miracle model from step 2 and retrieve it's solution (along with it's accuracy)
- Read the solution and write it into the drawing via LISP/.NET.
- Review design and tweak as necessary. When it's what you want, feed it back into the model (as a problem solution dataset) so the next iteration is better.
The first two steps are going to be REALLY hard.
I agree with dgorsman in that there's a lot of marketing hype around it. I do think it will have real world applications within a decade. As far as I can tell, AI is mostly marketing speak and for now, machine learning is where the work is being done. The first applications of machine learning to design aren't about putting out perfect design, they're about helping the designers see and find patterns in existing data that were difficult to see before. Basically, machine learning isn't autonomous, it needs a human driving it.
Want to get started? Take some of the many courses online for machine learning. Install BricsCAD (runs in Linux,and can run LISP). It's going to be a lot of work, it's still early days for this. It'll take a while for the investment of time and effort to return. But if when it does, I think the returns will be exceptional. Keep me posted on your progress. :)
If it's written in python, it's machine learning, if it's written in Power Point, it's AI.
:2funny:[/list]
-
not possible with all the crazy architects and designers :crazy2:
-
The simplest is about writing macro's Autocad "Macro" is well useless its just not editable. Look at excel record a macro you get some usefull code, there are write lisp from keystrokes recorders you pay for them.
So for me AI is write the code to repeat something I created.
-
So for me AI is write the code to repeat something I created.
(http://i.imgflip.com/2x4p8e.jpg)
-
The simplest is about writing macro's Autocad "Macro" is well useless its just not editable. Look at excel record a macro you get some usefull code, there are write lisp from keystrokes recorders you pay for them.
So for me AI is write the code to repeat something I created.
Yes. this is exactly my doubt.
what do different a LISP that repeat others macros o LISP routines, to a Machine Learning or AI, someone please share us their open source code...
PD: fuck humans
-
In theory it's being already being done (https://www.autodesk.com/redshift/machine-learning/). I think machine learning has great potential to help out in the design/drafting space. I've been looking at how to implement it myself.
My current genre of design (landscape) is mostly 2D. After taking a machine learning class, I've had a difficult time figuring out how I could apply it to my designs. That doesn't mean it can't be done, it just means I'm not there yet. As with many problems, one of the hardest parts is figuring out what question to ask, and how to ask it.
My current thought on how to apply it to CAD looks something like:
Build a machine learning model
- Using existing completed designs (dwg files) use LISP/.NET to generate hundreds or thousands of problem and solution datasets (probably text files, possibly images)
- Write some miracle machine learning code, (Python) and generate a really nice ML model as an analysis tool
Use that model for new designes
- Using the same code in the first step , generate a problem set from a dwg file you want to design to
- Feed that problem dataset to the miracle model from step 2 and retrieve it's solution (along with it's accuracy)
- Read the solution and write it into the drawing via LISP/.NET.
- Review design and tweak as necessary. When it's what you want, feed it back into the model (as a problem solution dataset) so the next iteration is better.
The first two steps are going to be REALLY hard.
I agree with dgorsman in that there's a lot of marketing hype around it. I do think it will have real world applications within a decade. As far as I can tell, AI is mostly marketing speak and for now, machine learning is where the work is being done. The first applications of machine learning to design aren't about putting out perfect design, they're about helping the designers see and find patterns in existing data that were difficult to see before. Basically, machine learning isn't autonomous, it needs a human driving it.
Want to get started? Take some of the many courses online for machine learning. Install BricsCAD (runs in Linux,and can run LISP). It's going to be a lot of work, it's still early days for this. It'll take a while for the investment of time and effort to return. But if when it does, I think the returns will be exceptional. Keep me posted on your progress. :)
If it's written in python, it's machine learning, if it's written in Power Point, it's AI.
:2funny:[/list]
....just curious... why BricsCAD and not AUTOCAD?
can I do it with an OPEN SOURCE alternative?
-
If you want this bad enough please do some research, write some code and post your results. Maybe you'll get some help then as a community project. Right now it just looks like you want someone else to do the leg work solving 'the magic red button' problem...
-
>>> ... <<<
....just curious... why BricsCAD and not AUTOCAD?
can I do it with an OPEN SOURCE alternative?
Please explain ??
-
....just curious... why BricsCAD and not AUTOCAD?
can I do it with an OPEN SOURCE alternative?
I mentioned BricsCAD because it's a cheaper alternative to AutoCAD, and your post made it sound like you wanted to implement it as a personal project. You could certainly use AutoCAD.
As for an open source alternative, I see no reason you couldn't do it. Heck, it might even be easier if the open source CAD alternative you're looking at has native python support. Many of the machine learning libraries in python are open source (https://stackabuse.com/the-best-machine-learning-libraries-in-python/).
After my first post, I felt like I wasted time responding to your question. I may have misinterpreted, but it almost seems like you're looking for a turn-key answer for you to use (free of charge no less).
As far as I know (and I've been looking) that answer doesn't exist. It's gonna take work. Lots of it. Work worth doing IMO, but work none the less.
From your original post:
I found some videos where explain that Machine Learning and Artificial intelligence can be used for everything and I can teach to the Machine or A.I. to draw like my old projects.
Whenever a statement (even on the internet :uglystupid2:) applies it's self to everything chances are it's probably a false statement.
If anyone in this community wanted to start up a team doing some of this work, I would be happy to contribute some time and attention to it.
-
not possible with all the crazy architects and designers :crazy2:
Ahhh sorry but it already here. In the form of Google Sketch Up.
And it should not be a surprise that Google was the one to bring it.
-
not possible with all the crazy architects and designers :crazy2:
Ahhh sorry but it already here. In the form of Google Sketch Up.
And it should not be a surprise that Google was the one to bring it.
Print! “I’m sorry Dave, I’m afraid I can’t do that”
-
not possible with all the crazy architects and designers :crazy2:
Ahhh sorry but it already here. In the form of Google Sketch Up.
And it should not be a surprise that Google was the one to bring it.
Print! “I’m sorry Dave, I’m afraid I can’t do that”
LOL literally.
-
....just curious... why BricsCAD and not AUTOCAD?
can I do it with an OPEN SOURCE alternative?
I mentioned BricsCAD because it's a cheaper alternative to AutoCAD, and your post made it sound like you wanted to implement it as a personal project. You could certainly use AutoCAD.
As for an open source alternative, I see no reason you couldn't do it. Heck, it might even be easier if the open source CAD alternative you're looking at has native python support. Many of the machine learning libraries in python are open source (https://stackabuse.com/the-best-machine-learning-libraries-in-python/).
After my first post, I felt like I wasted time responding to your question. I may have misinterpreted, but it almost seems like you're looking for a turn-key answer for you to use (free of charge no less).
As far as I know (and I've been looking) that answer doesn't exist. It's gonna take work. Lots of it. Work worth doing IMO, but work none the less.
From your original post:
I found some videos where explain that Machine Learning and Artificial intelligence can be used for everything and I can teach to the Machine or A.I. to draw like my old projects.
Whenever a statement (even on the internet :uglystupid2:) applies it's self to everything chances are it's probably a false statement.
If anyone in this community wanted to start up a team doing some of this work, I would be happy to contribute some time and attention to it.
you did not waste time. I just searching for a "TEMPLATE" to start my project... at least that as I always start to learn anything.
-
jtm2018hyo,
Which languages do you program in ??
-
from: kdub on 2019-04-04, 17:17:03
jtm2018hyo,
Which languages do you program in ??
I just programmed a beautiful and perfect AUTOEXE.cfg for bind keys in DOTA 2, and a beautiful and perfect AUTOhotkeys for my Warcraft III.
basically, I'm like Stev Jobs ... but programming a bit.
-
I understand ...
you like playing games.
-
I've been putting some thought to this and can't determine any areas of CAD production that would benefit from Machine Learning and Artifitial Intelligence.
I know, I don't get out very much :)
Anyone have any realistic ideas ??
... even without the proviso of being financially viable.
Regards,
-
I've been putting some thought to this and can't determine any areas of CAD production that would benefit from Machine Learning and Artifitial Intelligence.
That won't stop the overlords.
(http://pbs.twimg.com/profile_images/783463529156194304/-kNoFIOC_400x400.jpg)
-
...
Anyone have any realistic ideas ??
kdub, I don't think it will help CAD production for a while. Right now it's about design. And really about design that has multiple good solutions; flexibility if you will. If you can code the design requirements into a rigid algorithm with all constraints known and one single solution, you don't need machine learning, just run the algorithm. It'll be way faster, cheaper and efficient.
If you have a problem with multiple good solutions, that's where the magic of ML will come in. So if the algorithm is 'loose' machine learning will run thousands/millions of iterations, while optimizing certain outputs. It comes up with stuff that doesn't make logical sense, but work. Some of the solutions will suck, and some will be really good, and appear to be creative because designers tend to limit themselves to what they know works.
The cool thing I think is, it would be possible to 'teach' the machine learning algorithm using a bunch of previous designs done by a human. At that point, it might be possible for ML to come up with designs that pull from previous designers experience, but still iterate and generate new solutions. Or once the ML algorithm is tuned, it'll just be faster. And if we can figure out how to use the thousands of existing drawings as a learning dataset, all the better.
My understanding is ML is being used to design airplane parts now (https://www.wired.com/2015/12/airbuss-newest-design-is-based-on-slime-mold-and-bones/). And I'd love to see it expand into other areas. I have ideas on how to apply it to my current area of design (landscape irrigation) but I haven't figured out the nature of the implementation. As I said in a previous post, just figuring out how to ask the question correctly is difficult.
Regarding AI, as far as I know it's not here yet, and would be a waste of time trying to develop it for CAD. Once/if AI shows up, all bets are off. It's not worth worrying about IMO. Anyone claiming to have achieved AI hasn't done a good job of reigning in their marketing dept. :P
-
>>>> And if we can figure out how to use the thousands of existing drawings as a learning dataset, all the better. <<<
Just make sure the drawings have the lines joining up at the corners.
but seriously;
I may be naive and a bit of a romantic but I can't visualise 'design' without input of a human brain ... without a brain and emotion it is just sausage making.
Current software evaluates multi-thousands of emails trying to learn to identify fraud and spam ... and that's with a major percentage of the 'rules' being written by human hands. It's a big step from there to designing a bridge ( or an irrigation system ).
Wearing a different hat:
An irrigation system would be feasable ( without ML and AI ) once the rules were established and a full reference database was created. I don't think you'd find it too difficult, just time consuming.
Regards,
-
Most systems design has rules, however in some cases the rules can get so complex that a linear calculated solution isn't very practical.
The first example would be laying out pipes through a pipe rack. You would have source and destination equipment or other piping; commodities and properties; etc. A good designer could lay out a design in a couple of days, while an AI could iterate through hundreds of potential designs within an hour, and cull out the top performers for further development.
The second example is a little more drafting oriented - automatic tag layout. Again, there are all sorts of rules - don't cross the streams (er... leaders :-P ); don't overlay annotations; keep annotations close to the point where they are annotating; etc. You could do some rough calculating but the end results wouldn't be pretty, and would likely fail on those drawings which don't fall within certain strict parameters. On the other hand, an AI could evaluate the potential options and find a top-performer that is "good enough" using a genetic algorithm (which is something I've got on the go).
-
I haven't looked further than the release notice, but this may be better than re-learning R and Python with all it's add-ons :)
https://visualstudiomagazine.com/articles/2019/04/08/mlnet-rc.aspx
or not, YMMV
-
http://www.theswamp.org/index.php?topic=55115.0
-
hello, I have some question:
about Autodesk licenses, can be AutoCAD can be used to get profit for (example) myself?
I mean, in the hypothetical case that I get some advances in Machine Learning to automate my work in AutoCAD, Autodesk could you ask me for some money?
if the answer is yes, then have no sense work with Autodesk software, then, what software might suggest to me?
PD: sorry for the late answers, this is just a hobby and I will just join in my free time, I would never leave it in oblivion.
-
Autodesk would only ask you for the subscription fee you agreed to.
I could see that they might make an AutoCAD version with a built in ML module that would cost more. But I think that's long in the future.
Drafting and design is a tough set of problems for machine learning so far. The questions aren't as well defined as Hot Dog or not Hot Dog (https://techcrunch.com/2017/06/28/thinking-about-hotdogs/)
-
The simplest is about writing macro's Autocad "Macro" is well useless it's just not editable. Look at excel record a macro you get some useful code, there are write lisp from keystrokes recorders you pay for them.
So for me, AI writes the code to repeat something I created.
how BIGAL mentioned, some should be a combination of macro and lisp, if they (Autodesk) do not have problems, then we have the light green to start the project.
I already have a lot of lisp, but 0 macros, anyway I think I already have what is necessary to start.
but I still did not find anything related to AutoCAD merged with Machine learning, at least I already have an idea thanks ta your post guys.
PD: any advance I will report you, maybe we can build this project guys, even just for hobby.
-
It sounds like Design Automation to me, what you want to do.
Autodesk is developing Dynamo for this. I assume it will come in vanilla AutoCAD as well some day. It is a great start to use for design Automation. Also Autodesk is working on generative design software (Project Refinery).
Machine Learning is a bridge too far for Autodesk, so I wonder if you will succeed :tongue2:
-
A book about machine learning (A Guide for Making Black Box Models Explainable):
https://christophm.github.io/interpretable-ml-book/ (https://christophm.github.io/interpretable-ml-book/)
-
Not sure if this is covered yet, but take a look at BricsCad. They are getting into this AI now.
-
It sounds like Design Automation to me, what you want to do.
Autodesk is developing Dynamo for this. I assume it will come in vanilla AutoCAD as well someday. It is a great start to use for design Automation. Also, Autodesk is working on a generative design software (Project Refinery).
Machine Learning is a bridge too far for Autodesk, so I wonder if you will succeed :tongue2:
look nice, but sadly works just for Revit, I will choice AutoCAD over REVIT for AI or Machine Learning because of the AutoLISP. you just need to open a .txt for start. but for Revit, you need .NET (VisualBasic C+ C#, etc) and .Net IMO is very hard to work and 3D is painful. so that is a great point for AUTOCAD over REVIT, especially If you need a lot of them for AI or machine learning.
Not sure if this is covered yet, but take a look at BricsCad. They are getting into this AI now.
I found this in Bricscad's shared link "A big problem in CAD is the increase in complexity. Machine learning is a possible solution", BricsCAD understands the point with Machine Learning.
I want to use, for example, AUTOCAD or BRICSCAD with the 1000 lisp that I already have or I will create, I do not want to pay others $10000 for a month for doing my work.
99% of my works are repeated the same lisp but in a different order, something like DYNAMIC MACRO is what I need.
IMO BricsCAD is making the winning play. but AUTODESK just wants to try to kill AutoCAD.
A book about machine learning (A Guide for Making Black Box Models Explainable):
https://christophm.github.io/interpretable-ml-book/ (https://christophm.github.io/interpretable-ml-book/)
a lot of thanks, I will check it.
-
Hey! Absolutely. There are applications of machine learning and artificial intelligence in AutoCAD. These technologies have been leveraged to enhance various aspects of AutoCAD, such as automating repetitive tasks, optimizing design processes, and even assisting in generating design suggestions. Machine learning algorithms can be trained to recognize patterns, identify objects, and make intelligent predictions based on existing data. It's pretty exciting how these technologies are transforming the field of computer-aided design. If you're interested in learning more about machine learning, there are some great resources out there, like the Best Machine Learning Courses (https://www.selectcourses.com/best-machine-learning-courses/), that can help you dive deeper into this fascinating field.