Fully autonomous robots?

[nehalita]

(oh dear this is a long one. bear with me, i actually supported my statements so that's why it's long...)

Our team was actually talking about a possible hybrid of autonomous code and the use of drivers.

Ideally, a combination of both would make the robot more competitive. With the target far away, shooting at an angle could be more difficult than anticipated (this may not be true...obviously, we don't have a working robot that can shoot in the goal and drive around yet so this has yet to be determined). If we can use some autonomous code that automatically tracks the goal and provides the proper angle of inclination or speed, some human error can be eliminated.

However, I started off with "ideally" for a reason. The code has to be able to be properly developed, used, and corrected in time.

I personally feel that a fully autonomous robot would not be nearly as competitive. An autonomous robot doesn't have the awareness of its surroundings that we do looking across the field. What I like so much about this year's game is the amount of strategy needed. You cannot teach a robot strategy....at least not in the amount of time we are allotted.

I'm not saying that an autonomous robot isn't functionable but to be competitive, I still think we need a human touch -- that means the ease of going between offensive and defensive strategies and ensuring that no one gets in each other's way. Now, we still have that problem when we are controlling the robot (getting in each other's way) but we can easily fix that. To conjure a code that would anticipate all elements, possibilities, and problems into account would simply be illogical and impractical when, given our complex decision-making faculties, humans can do the same thing with a lot less effort.

Finally, I would like to point out that there are 3 of us on the field while there is one camera on the robot. We can decide what to do when a robot rams into us and figure out where to go next, the robot cannot. We can determine whether the corner goal is free alot faster than the robot can and if a robot needs help up the ramp, we can do that while an autonomous robot cannot see whether a robot needs help or not (or decide which robot to help in the even that both robots cannot go up the ramp). it cannot assess which robot would be easier to aid and even if we could devise a code to do that, it would be easier for a human to simply take 1/2 second to figure that out than spend several hours coding it into a robot.

So essentially, autonomous code can take out the guesswork but we still need humans to decide what's best to do next. If this games was 1 vs. 1, things would be different but we have 6 robots. Versatility is essential.

[Faith]

I don't think an excellent robot would come of fully autonomous. It is hard enough to make stuff accurate in FLL with a decent selection of sensors, and in FRC it would be harder because although you have more sensors you also, in this case, face unexpected field changes and strategy.

Strategy would be the hardest to accomplish with autonomous.

[d.courtney]

I had plans on doing this since last november when an alumni from our team chalenged me saying a fully autonomous robot would never survive in first. He did say that a pannel for the "driver" with general tasks, such as buttons for say "avoid all objects", "play defence", "shoot at will" and so on would constitute as still being fully autonomous. Which is exactly what I plan on doing with our team... however to this point one thing seems to be stoping me... TIME(as I am a lone programmer).

Now as I am sure you picked up I think it is feasible. and things a robot could do better: keeping away from penalties for one... as it would be easy to program in preventive measures from getting them.
Now the other thing I will want to include is a manual override system for tougher matches. or when we are in a pickle.



Oh yeah one more thing... is there anyway that the robot could remember information, ie a robot that improves as matches go by...

and last tracking a sphere isn't to hard, already have had some success with it and the green light.

[Mike]

Originally Posted by d.courtney

I had plans on doing this since last november when an alumni from our team chalenged me saying a fully autonomous robot would never survive in first.

The doubt of others is the best inspiration.

Originally Posted by d.courtney

Now as I am sure you picked up I think it is feasible. and things a robot could do better: keeping away from penalties for one... as it would be easy to program in preventive measures from getting them.
Now the other thing I will want to include is a manual override system for tougher matches. or when we are in a pickle.

Of course. Any system like this should have a good level of redundancy.

Originally Posted by d.courtney

Oh yeah one more thing... is there anyway that the robot could remember information, ie a robot that improves as matches go by...

I think you are thinking about a sort of Artificial Intelligence/Machine Learning system. This would be severely stretching the limits of any mid-priced microcontroller. But, you could use the EEPROM to store data. Kevin Watson has code to do that at http://www.kevin.org/frc

[d.courtney]

Originally Posted by Mike

I think you are thinking about a sort of Artificial Intelligence/Machine Learning system. This would be severely stretching the limits of any mid-priced microcontroller. But, you could use the EEPROM to store data. Kevin Watson has code to do that at http://www.kevin.org/frc

yeah, a bit, but that would be more for a project I do next summer, just something I have been wondering about.

btw, are you attempting for the fully atonomous robot mike?

[Mike]

Originally Posted by d.courtney

yeah, a bit, but that would be more for a project I do next summer, just something I have been wondering about.

btw, are you attempting for the fully atonomous robot mike?

Ahh, ok then.

I would love to work on a fully autonomous robot. Whether or not I do comes down to a team decision. To be perfectly honest, I think it will be hard to convince my team to relinquish the beloved CH Flightsticks.

However, if I can't do it in FIRST, I'd probably do it outside of FIRST. I just need to think of a cool application. Having a robot autonomously navigating my backyard isn't very fun, so suggestions are welcome.

[d.courtney]

hmm my team seemed much more willing, all they said was "If you can do it we will use it"... so if you'd do it either way wheather in or out of first, you should code as if it will be used, and if it is good I am sure your team or any for that matter would be willingfor it (just give them manual override so they can play some of the matches) because it is quite an impressive thing, which would garuntee the inovation award, and its just plain cool... correct me if i am wrong but I think it would be a first in FIRST. and I for one would like to be apart of it... besides you have to admit this is the best year in a while to have fully autonomous code, since the shoting has to be autonomous anyway.

[jbobj]

A fully automonous robot really would not happen unless there was advantages to it. Here is an idea that if FIRST applied to a future game, many teams would seriously think about a fully autonomous robot.

All robots start off the match in auto mode like normal and they will stay in auto mode unless the drivers of the robot press a button similar to the e-stop in the player station. When this button is pressed, the robot switchs to manual control and cannot be switched back. The advantage they could add to auto mode is that any points scored by a robot in auto would be doubled. This would encourage teams to stay in auto mode as long as possible, even the whole match, and be rewarded for being so.

[Tom Bottiglieri]

Originally Posted by Mike

Ahh, ok then.

I would love to work on a fully autonomous robot. Whether or not I do comes down to a team decision. To be perfectly honest, I think it will be hard to convince my team to relinquish the beloved CH Flightsticks.

However, if I can't do it in FIRST, I'd probably do it outside of FIRST. I just need to think of a cool application. Having a robot autonomously navigating my backyard isn't very fun, so suggestions are welcome.

Make an autonomous snowblower.

[Mike]

Originally Posted by Tom Bottiglieri

Make an autonomous snowblower.

Haha, I'll go ask my dad if I can rip apart our new $1,100 snowblower

[d.courtney]

and if you did make an autonomous snowblower you'd want some proximity sensors just in case little kids ar playing in its way... that wouldn't be too pretty

[CJO]

I think that partial autonomous, or perhaps better phrased, driver augmentation is the perfect, and indeed key component of this year's game. I think that especially with shooting, the driver needs to be able to just hit a "shoot" button, and have the robot auto-fire if in range.

Furthermore, I think that the ideal system is like a nice glass aircraft . . . the pilot still flys, but does not have to worry about individual settings like mixture or prop, instead having the computer manage those for a requested "power."

[Andrew Blair]

Originally Posted by Mike

Ahh, ok then.

I would love to work on a fully autonomous robot. Whether or not I do comes down to a team decision. To be perfectly honest, I think it will be hard to convince my team to relinquish the beloved CH Flightsticks.

However, if I can't do it in FIRST, I'd probably do it outside of FIRST. I just need to think of a cool application. Having a robot autonomously navigating my backyard isn't very fun, so suggestions are welcome.

What you need to build is a people follower. Use an infrared camera to seek out moving heat signatures, then keep it at a safe distance, while still inciting curiosity. Keep it in your front yard, or close, not an attack robot...
It would be really neat to walk down the street and notice a robot "watching" you, by itself. The hard part's going to be the algorithm that lets it run when it's being stolen!

[Jared Russell]

While I've thought about this before, and in each year our team increased the amount of autonomy involved, the problem is in the limitations posed by FIRST.

Too little money. Too little time. Too few motors. Too little battery. Too small a processor.

If all that were not an issue, then I have no doubts that a fully-autonomous robot would work well.

The problem is that FIRST allows you four of a really powerful computer when you run your robot, a computer than can react to all sorts of stimuli - vision, sound, the score of the match. It has built in feedback controls and is powered by coffee and donuts.

Four living, breathing, thinking people are tough to beat.

[phrontist]

I think that a strong alliance could win against a weaker one with properly implemented autonomy.