Toolpath generation by reinforcement learning for computer aided manufacturing
Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using toolpaths generated by reinforcement learning for use with subtractive manufacturing systems and techniques, include: obtaining, in a computer aided design or manufacturing program, a three dimensional model of a manufacturable object; generating toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model; and providing the toolpaths to the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object.
1. A method comprising:
obtaining, in a computer aided design or manufacturing program, a three dimensional (3D) model of a manufacturable object;
generating, by the computer aided design or manufacturing program, toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning during training, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model, wherein the machine learning algorithm comprises two or more machine learning algorithms, and providing at least the portion of the three dimensional model to the machine learning algorithm comprises:
generating at least one starting position by processing a global view of at least the portion of the three dimensional model with a first of the two or more machine learning algorithms; and
generating a set of toolpaths near each of the at least one starting position by processing a local view of at least the portion of the three dimensional model with a second of the two or more machine learning algorithms; and
providing the toolpaths to the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object.
2. The method of claim 1 , wherein the desired toolpath characteristics comprise tool engagement for a selected cutting tool and a contact track of a selected tool.
3. The method of claim 1 , wherein the machine learning algorithm employs variable feeds and/or speeds.
4. A method comprising:
obtaining, in a computer aided design or manufacturing program, a three dimensional (3D) model of a manufacturable object;
generating, by the computer aided design or manufacturing program, toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning during training, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model, wherein the machine learning algorithm comprises two or more machine learning algorithms, and providing at least the portion of the three dimensional model comprises:
processing at least the portion of the three dimensional model with a first of the two or more machine learning algorithms; and
processing the portion of the three dimensional model with a second of the two or more machine learning algorithms to produce the toolpaths; and
providing the toolpaths to the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object.
5. The method of claim 4 , wherein the first of the two or more machine learning algorithms comprises a convolutional neural network used to generate data from the portion of the three dimensional model to be processed with the second of the two or more machine learning algorithms.
6. The method of claim 4 , wherein the first of the two or more machine learning algorithms operates on a low resolution view of at least the portion of the three dimensional model, and the second of the two or more machine learning algorithms operates on a high resolution view of the portion of the three dimensional model.
7. The method of claim 1 , wherein the machine learning algorithm comprises an advantage based actor-critic machine learning architecture.
8. The method of claim 1 , wherein the toolpaths are for 2.5-axis machining by the computer-controlled manufacturing system.
9. The method of claim 8 , wherein generating the toolpaths that are usable by the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object comprises:
generating a plurality of two dimensional (2D) representations of the three dimensional model at discrete 2D layers;
providing each 2D representation to the machine learning algorithm to generate a corresponding set of toolpaths for manufacturing each discrete 2D layers; and
generating the toolpaths that are usable by the computer-controlled manufacturing system by combining the corresponding sets of the toolpaths for the plurality of 2D representations of the three dimensional model at discrete 2D layers.
10. The method of claim 1 , wherein generating the at least one starting position comprises processing the global view with the first of the two or more machine learning algorithms using discretized representations of the three dimensional model of the manufacturable object and of a model of a stock material from which the at least the portion of the manufacturable object is to be manufactured, and wherein generating the set of toolpaths comprises processing the local view with the second of the two or more machine learning algorithms using a continuous representation of a model of a tool in the computer-controlled manufacturing system to be used to manufacture the at least the portion of the manufacturable object.
11. The method of claim 10 , wherein generating the at least one starting position comprises processing the global view with the first of the two or more machine learning algorithms using a discretized representation of the model of the tool, and generating the set of toolpaths comprises processing the local view with the second of the two or more machine learning algorithms using continuous representations of the three dimensional model of the manufacturable object and of the model of the stock material.
12. The method of claim 1 , wherein the desired toolpath characteristics comprise a turn direction of a tool being set based on a rotation direction of the tool.
13. The method of claim 12 , wherein the turn direction of the tool is set based on a location of the tool relative to the 3D model of the manufacturable object, wherein the one or more scoring functions include one or more rewards that encourage freely choosing a turning direction for the tool when the location of the tool is greater than a threshold distance from the 3D model of the manufacturable object, and the one or more rewards encourage the tool to turn only in one direction, which exposes a correct side of the tool based on the rotation direction, when the location of the tool is within the threshold distance from the 3D model of the manufacturable object.
14. The method of claim 1 , wherein the machine learning algorithm includes the one or more scoring functions that include stage-based rewards that correlate with corresponding percentages of completion of the manufacturable object.
15. A system comprising:
a data processing apparatus including at least one hardware processor; and
a non-transitory computer-readable medium encoding instructions configured to cause the data processing apparatus to perform operations comprising
obtaining, in a computer aided design or manufacturing program, a three dimensional (3D) model of a manufacturable object;
generating, by the computer aided design or manufacturing program, toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning during training, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model, wherein the machine learning algorithm comprises two or more machine learning algorithms, and providing at least the portion of the three dimensional model to the machine learning algorithm comprises:
generating at least one starting position by processing a global view of at least the portion of the three dimensional model with a first of the two or more machine learning algorithms; and
generating a set of toolpaths near each of the at least one starting position by processing a local view of at least the portion of the three dimensional model with a second of the two or more machine learning algorithms; and
providing the toolpaths to the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object.
16. The system of claim 15 , wherein the desired toolpath characteristics comprise tool engagement for a selected cutting tool and a contact track of a selected tool.
17. A non-transitory computer-readable medium encoding instructions operable to cause a data processing apparatus to perform operations comprising
obtaining, in a computer aided design or manufacturing program, a three dimensional (3D) model of a manufacturable object;
generating, by the computer aided design or manufacturing program, toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning during training, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model, wherein the machine learning algorithm comprises two or more machine learning algorithms, and providing at least the portion of the three dimensional model to the machine learning algorithm comprises:
generating at least one starting position by processing a global view of at least the portion of the three dimensional model with a first of the two or more machine learning algorithms; and
generating a set of toolpaths near each of the at least one starting position by processing a local view of at least the portion of the three dimensional model with a second of the two or more machine learning algorithms; and
providing the toolpaths to the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object.
18. The system of claim 15 , wherein the machine learning algorithm employs variable feeds and/or speeds.
19. The system of claim 15 , wherein the machine learning algorithm comprises an advantage based actor-critic machine learning architecture.
20. The system of claim 15 , wherein the toolpaths are for 2.5-axis machining by the computer-controlled manufacturing system.
21. A system comprising:
a data processing apparatus including at least one hardware processor; and
a non-transitory computer-readable medium encoding instructions configured to cause the data processing apparatus to perform operations comprising:
obtaining, in a computer aided design or manufacturing program, a three dimensional (3D) model of a manufacturable object;
generating, by the computer aided design or manufacturing program, toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning during training, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model, wherein the machine learning algorithm comprises two or more machine learning algorithms, and providing at least the portion of the three dimensional model comprises:
processing at least the portion of the three dimensional model with a first of the two or more machine learning algorithms; and
processing the portion of the three dimensional model with a second of the two or more machine learning algorithms to produce the toolpaths; and
providing the toolpaths to the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object.
22. The system of claim 21 , wherein the first of the two or more machine learning algorithms comprises a convolutional neural network used to generate data from the portion of the three dimensional model to be processed with the second of the two or more machine learning algorithms.
23. The system of claim 21 , wherein the first of the two or more machine learning algorithms operates on a low resolution view of at least the portion of the three dimensional model, and the second of the two or more machine learning algorithms operates on a high resolution view of the portion of the three dimensional model.
24. A non-transitory computer-readable medium encoding instructions operable to cause a data processing apparatus to perform operations comprising:
obtaining, in a computer aided design or manufacturing program, a three dimensional (3D) model of a manufacturable object;
generating, by the computer aided design or manufacturing program, toolpaths that are usable by a computer-controlled manufacturing system to manufacture at least a portion of the manufacturable object by providing at least a portion of the three dimensional model to a machine learning algorithm that employs reinforcement learning during training, wherein the machine learning algorithm includes one or more scoring functions that include rewards that correlate with desired toolpath characteristics comprising toolpath smoothness, toolpath length, and avoiding collision with the three dimensional model, wherein the machine learning algorithm comprises two or more machine learning algorithms, and providing at least the portion of the three dimensional model comprises:
processing at least the portion of the three dimensional model with a first of the two or more machine learning algorithms; and
processing the portion of the three dimensional model with a second of the two or more machine learning algorithms to produce the toolpaths; and
providing the toolpaths to the computer-controlled manufacturing system to manufacture at least the portion of the manufacturable object.
25. The non-transitory computer-readable medium of claim 24 , wherein the first of the two or more machine learning algorithms comprises a convolutional neural network used to generate data from the portion of the three dimensional model to be processed with the second of the two or more machine learning algorithms.
26. The non-transitory computer-readable medium of claim 24 , wherein the first of the two or more machine learning algorithms operates on a low resolution view of at least the portion of the three dimensional model, and the second of the two or more machine learning algorithms operates on a high resolution view of the portion of the three dimensional model.