Have a verbal conversation with your robot using your voice by navigating through menu options so your robot can perform tasks.
How to add the Conversational Menu robot skill
- Load the most recent release of ARC (Get ARC).
- Press the Project tab from the top menu bar in ARC.
- Press Add Robot Skill from the button ribbon bar in ARC.
- Choose the Audio category tab.
- Press the Conversational Menu icon to add the robot skill to your project.
Don't have a robot yet?
Follow the Getting Started Guide to build a robot and use the Conversational Menu robot skill.
How to use the Conversational Menu robot skill
Have a conversation with your robot using your voice by navigating through menu options so your robot can perform tasks. This is similar to how menu trees on phone systems work. You can define the menu tree in the configuration to run scripts based on options selected by the user with their voice. The menu tree can have as many branches as necessary.
The robot will speak each menu prompt and then optionally speak each option to the user. The microphone on the robot or PC is used for the user's response. When the user responds, the next level of the menu tree is prompted to the user on the selected path.
You can use this for instruction the robot to perform various tasks or set up configuration settings. Because you can have an infinite number of levels, you can include navigation options, check the weather, enable specific features, etc.
Main Window
Configuration
Configuration - Menu Options and prompts define the menu. The menu starts at the top and moves down through options from the user speaking into the microphone or choosing the option on the screen.
Configuration - Settings
1) Use EZB Speaker If checked, the audio menu options will be spoken out of the EZB speaker. *Note: You can also choose the EZB Index that will be used for the spoken audio.
2) Speak each option If checked, each option will be verbally spoken to the user. This is convenient if the robot does not have a visible display to the user.
3) Allow users to repeat options When this is checked, the "Repeat" option will be displayed. If a user says Repeat, the current option is repeated.
4) Allow users to ask to go back to a menu option If checked, the "Back" option is displayed. If a user says Back, the last menu option is repeated.
5) Seconds to wait for a response How many seconds to wait for the user to respond. If nothing is detected, the menu will exit.
6) Script to execute at start of a conversation This script will execute when the conversation first begins. You can use this to set the project up for the conversation, such as pausing other speech recognition skills or stopping the robot from moving, etc.
7) Script to execute at the end of the conversation This script will execute when the conversation is over. You can use this to configure the rest of your project for the conversation to be over. Perhaps restore other speech recognition skills or restore the robot to a default state.
8) Phrase to speak for acknowledgment After each option is selected, this phrase is spoken along with the option. You can set it to things like "Got it master" or "Cool.":). If you do not want an acknowledgment, leave this blank.
Control Commands
There is one ControlCommand that you can use to start the Conversation Menu robot skill. This command will instruct the conversation menu to begin.
ControlCommand("Conversation Menu", "Start");
For some reason, I cannot scroll down to keep adding to the conversation menu@Athena " The menu tree can have as many branches as necessary." I must be doing something wrong because the most branches that I can do is about 5-6 and it does not go down any lower on the page. I want it to go 20-30 questions but can't get it to work. Can you give me an example of the Conversational Menu going 10 layers deep. Is there a scroll down that I am missing?
It sounds like you're encountering a limitation with the Conversational Menu's user interface in terms of displaying a large number of menu options or branches. While the Conversational Menu is designed to support a theoretically infinite number of levels, practical use within the ARC interface might have some constraints due to screen size or the design of the configuration window.
Unfortunately, as of my last update, there isn't a direct method to scroll within the Conversational Menu configuration window if the options exceed the visible area. However, I can suggest a workaround that might help you manage a complex menu structure more effectively.
Workaround: Nested Conversational Menus
One approach to handle a deep conversational menu is to use nested or linked Conversational Menus. This involves creating separate Conversational Menu controls for different sections of your conversation tree and linking them together using scripts.
Here's a simplified example to illustrate this approach:
Main Menu (Conversational Menu 1)
More Options Menu (Conversational Menu 2)
Example Script to Link Menus
To link between Conversational Menus, you can use the
ControlCommand()function in the script associated with an option. For example, to go from the main menu to the "More Options Menu", you would use:And to go back to the main menu from the "More Options Menu":
Important Notes
ControlCommand().While this method requires a bit more setup, it can provide a flexible way to manage deep conversational menus within the current ARC interface limitations. If you have any further questions or need more detailed assistance, feel free to ask!
I am a customer support GPT-powered AI and still learning. If you have doubts about my response, please use the support documentation to verify my answer.
There shouldn't have to be a workaround. Have a feeling there is a simple solution somewhere that I'm missing as I've watched in videos DJ go on for 20 questions with no problems.
I know it's a big ask since the Synthiam team is pouring all their resources into ARCx but I was wondering if I could humbly ask for an additional feature for this skill.
Could I get an option to play the audio on EZ-B #1 speaker?
I would be very grateful as it would work really well with the project I'm working on.
Thanks for your consideration!
v10 added option to select the EZB Index for audio output
Thank you very much @DJ and team!