Neural networks to generate robotic task demonstrations
A technique for training a neural network, including generating a plurality of input vectors based on a first plurality of task demonstrations associated with a first robot performing a first task in a simulated environment, wherein each input vector included in the plurality of input vectors specifies a sequence of poses of an end-effector of the first robot, and training the neural network to generate a plurality of output vectors based on the plurality of input vectors. Another technique for generating a task demonstration, including generating a simulated environment that includes a robot and at least one object, causing the robot to at least partially perform a task associated with the at least one object within the simulated environment based on a first output vector generated by a trained neural network, and recording demonstration data of the robot at least partially performing the task within the simulated environment.
1. A computer-implemented method for generating a robot task demonstration, the method comprising:
generating, via a simulator engine, a simulated environment that includes a robot and at least one object;
causing the robot to at least partially perform a task associated with the at least one object within the simulated environment based on a first output vector that is generated by a trained neural network in response to a first input vector that specifies a sequence of past poses of an end-effector of the robot within the simulated environment; and
recording demonstration data of the robot at least partially performing the task within the simulated environment.
2. The computer-implemented method of claim 1 , wherein the first output vector specifies a sequence of future poses of the end-effector of the robot.
3. The computer-implemented method of claim 1 , wherein causing the robot to at least partially perform the task comprises causing the robot to perform a sequence of future poses of an end-effector specified in the first output vector.
4. The computer-implemented method of claim 1 , further comprising:
receiving, at the simulator engine, a second output vector generated by the trained neural network, wherein the second output vector specifies a sequence of future poses of an end-effector of the robot; and
displaying a trajectory forecast within the simulated environment, wherein the trajectory forecast comprises a graphical representation of the sequence of future poses of the end-effector.
5. The computer-implemented method of claim 1 , further comprising:
receiving a first user input that causes the simulator engine to enter into a manual mode; and
in response, causing the robot to at least partially perform the task based on one or more user control inputs.
6. The computer-implemented method of claim 5 , further comprising recording additional demonstration data of the robot at least partially performing the task based on the one or more user control inputs.
7. The computer-implemented method of claim 5 , wherein the simulated environment comprises a virtual reality (VR) environment, the VR environment is displayed via a VR headset, and the one or more user control inputs are received via a VR controller.
8. The computer-implemented method of claim 5 , further comprising:
receiving a second user input that causes the simulator engine to enter into an automatic mode; and
in response, causing the robot to at least partially perform the task automatically based on a third output vector generated by the trained neural network.
9. The computer-implemented method of claim 8 , wherein the third output vector is generated by the trained neural network based on an input vector that specifies a sequence of past poses of an end-effector of the robot when the robot was at least partially performing the task based on the one or more user control inputs.
10. The computer-implemented method of claim 1 , further comprising:
receiving, at the simulator engine, a second output vector generated by the trained neural network, wherein the second output vector specifies a sequence of future poses of an end-effector of the robot;
displaying a trajectory forecast within the simulated environment, wherein the trajectory forecast comprises a graphical representation of the sequence of future poses of the end-effector; and
displaying a past trajectory in the simulated environment comprising a graphical representation of a sequence of past poses of the end-effector, wherein the past trajectory is displayed with a different appearance than the trajectory forecast.
11. One or more non-transitory computer readable media storing instructions that, when executed by one or more processors, cause the one or more processors to generate a robot task demonstration by performing the steps of:
generating, via a simulator engine, a simulated environment that includes a robot and at least one object;
causing the robot to at least partially perform a task associated with the at least one object within the simulated environment based on a first output vector that is generated by a trained neural network in response to a first input vector that specifies a sequence of past poses of an end-effector of the robot within the simulated environment; and
recording demonstration data of the robot at least partially performing the task within the simulated environment.
12. The one or more non-transitory computer readable media of claim 11 , wherein the first output vector specifies a sequence of future poses of an end-effector of the robot, further comprising:
before causing the robot to at least partially perform the task, displaying a trajectory forecast within the simulated environment, wherein the trajectory forecast comprises a graphical representation of the sequence of future poses of the end-effector.
13. The one or more non-transitory computer readable media of claim 11 , further comprising:
causing the robot to complete performance of the task based on a plurality of output vectors generated by the trained neural network; and
recording additional demonstration data of the robot completing performance of the task within the simulated environment.
14. The one or more non-transitory computer readable media of claim 11 , wherein the first output vector specifies a sequence of future poses of the end-effector of the robot.
15. The one or more non-transitory computer readable media of claim 11 , further comprising:
receiving, at the simulator engine, a second output vector generated by the trained neural network, wherein the second output vector specifies a sequence of future poses of an end-effector of the robot; and
displaying a trajectory forecast within the simulated environment, wherein the trajectory forecast comprises a graphical representation of the sequence of future poses of the end-effector.
16. The one or more non-transitory computer readable media of claim 15 , further comprising:
receiving a first user input that causes the simulator engine to enter into a manual mode; and
in response to the first user input, not operating the robot based on the second output vector.
17. The one or more non-transitory computer readable media of claim 11 , further comprising:
receiving a first user input that causes the simulator engine to enter into a manual mode; and
in response to the first user input, causing the robot to at least partially perform the task based on one or more user control inputs.
18. The one or more non-transitory computer readable media of claim 17 , further comprising recording additional demonstration data of the robot at least partially performing the task based on the one or more user control inputs.
19. The one or more non-transitory computer readable media of claim 17 , further comprising:
receiving a second user input that causes the simulator engine to enter into an automatic mode; and
in response, causing the robot to at least partially perform the task based on a third output vector generated by the trained neural network.
20. A system, comprising:
one or more memories that store instructions, and
one or more processors that are coupled to the one or more memories and, upon executing the instructions, generate a robot task demonstration by performing the steps of:
generating, via a simulator engine, a simulated environment that includes a robot and at least one object;
causing the robot to at least partially perform a task associated with the at least one object within the simulated environment based on a first output vector that is generated by a trained neural network in response to a first input vector that specifies a sequence of past poses of an end-effector of the robot within the simulated environment; and
recording demonstration data of the robot at least partially performing the task within the simulated environment.