Boston Dynamics Big Dog and other military transport robots

Triton said:
Yes, Boston Dynamics videos give me chills.

There's a Black Mirror episode with some of these as Terminators. Sort of creepy but a shot gun with slugs would make short work of them.
 
sferrin said:
There's a Black Mirror episode with some of these as Terminators. Sort of creepy but a shot gun with slugs would make short work of them.

Yes, but make them stronger, armored and give them a shotgun of their own and then things start to get interesting.
 
Testing Robustness

Published on Feb 20, 2018

A test of SpotMini's ability to adjust to disturbances as it opens and walks through a door. A person (not shown) drives the robot up to the door, points the hand at the door handle, then gives the 'GO' command, both at the beginning of the video and again at 42 seconds. The robot proceeds autonomously from these points on, without help from a person. A camera in the hand finds the door handle, cameras on the body determine if the door is open or closed and navigate through the doorway. Software provides locomotion, balance and adjusts behavior when progress gets off track. The ability to tolerate and respond automatically to disturbances like these improves successful operation of the robot. (Note: This testing does not irritate or harm the robot.)

View: https://youtu.be/aFuA50H9uek
 
Published on Oct 11, 2018

Atlas does parkour. The control software uses the whole body including legs, arms and torso, to marshal the energy and strength for jumping over the log and leaping up the steps without breaking its pace. (Step height 40 cm.) Atlas uses computer vision to locate itself with respect to visible markers on the approach to hit the terrain accurately. For more information visit www.BostonDynamics.com.

View: https://youtu.be/LikxFZZO2sk
 
Published on Oct 11, 2018

We have begun field testing the Spot robot for commercial usage around the world. After an initial mapping run, Spot autonomously navigated two dynamic construction sites in Tokyo and used a specialized payload for surveying work progress. An additional camera in its hand lets Spot do even more detailed inspection work on site. The Spot robot will be available in the second half of 2019 for a variety of applications.

View: https://youtu.be/wND9goxDVrY
 
DARPA personnel have seen the Terminator movies and this is all that is. All versions will carry weapons. Even ASIMO could carry a gun. But, for now, all are too dumb to do much more than simple tasks.
 
So how much $ for Spot? It will be interesting to see what services OEM's might target. I doubt they are cheap enough for personal use.
 
So how much $ for Spot? It will be interesting to see what services OEM's might target. I doubt they are cheap enough for personal use.
Apparently just for now they're only going to be leasing them, but they're rumoured / speculated to be in the ballpark of $50,000 to $100,000 (they are advanced robots, but Boston Dynamics has been specifically doing quite a bit of work to make Spot Mini cheaper to manufacture for commercial use).

Edit: I should have watched that video you posted first; it more or less says what I posted.
 
Last edited:
Cops have long had dogs, and robots, to help them do their jobs. And now, they have a robot dog.
Massachusetts State Police is the first law enforcement agency in the country to use Boston Dynamics' dog-like robot, called Spot. While the use of robotic technology is not new for state police, the temporary acquisition of Spot — a customizable robot some have called“terrifying” — is raising questions from civil rights advocates about how much oversight there should be over police robotics programs.

 
View: https://www.youtube.com/watch?v=9j2a1oAHDL8


View: https://www.youtube.com/watch?v=_rPvKlvyw2w


View: https://www.youtube.com/watch?v=v4cM5I_mTTs


It appears that robotics has reached the point of practicality, with knowledge also distributed sufficiently wide for real development. What is needed is conceptualizing applications, engineering and scaling. The immense investment in batteries and autonomy due to cars will also increase robot capability in the near future.

- So what do you think will be the first killer app/functionality for military legged robots?
- What kind of concept of operation would work best?
- What performance characteristic combination would define a useful robot? (range, terrain crossing, speed, autonomy, payload, stealth, etc)
 
For moving payloads only. Simple barbed wire entanglements would be too much for them.
 
- So what do you think will be the first killer app/functionality for military legged robots?
- What kind of concept of operation would work best?
- What performance characteristic combination would define a useful robot? (range, terrain crossing, speed, autonomy, payload, stealth, etc)

Logistic. Hauling heavy loads on rough terrain for infantry. Maybe some combat use too, like placing the mines and remote-controlled turrets on no-man land (where the risk for human personnel is too great).
- What performance characteristic combination would define a useful robot? (range, terrain crossing, speed, autonomy, payload, stealth, etc)
Well, in my assumption, the priority is in this order:

1) Terrain crossing
2) Payload
3) Autonomy
4) Range
5) Stealth
6) Speed

Thing is, that in role of infantry support robots, they do not need much speed or range, since they would always be linked to the infantry (which is neither fast, nor long-range). But terrain crossing is extremely important, because one thing infantry is still the best - is traversing the rough terrain. Any machine, useful for infantry, must at least be capable of doing the same.
 
Boston Dynamics has been passed around a bit - owned by google, then Softbank, now Hyundai. This is a Hyundai-only project, but this time the potential synergy is clearer. Hyundai's long been working on combinations of wheels and legs to cross rough terrain.

 
A number of spot robots have been purchased by police, this deserve some discussion.

And hopefully more interesting than predictable frontlash~

Looking at the police use case, what a robot needs is exactly arms.

*As in, manipulators.*

Patrolling, opening doors in higher risk situations and bomb disposal are all no brainers. What is really interesting is potential for dog-bot kung-ku to take-down and subdue folks without the problem of oppressive demographics. Robots dancing is old now, what we need is robot martial arts :D

*god this seem obscure and fun enough: anyone help crowdfund this idea?*
 
A number of spot robots have been purchased by police, this deserve some discussion.

And hopefully more interesting than predictable frontlash~

Looking at the police use case, what a robot needs is exactly arms.

*As in, manipulators.*

Patrolling, opening doors in higher risk situations and bomb disposal are all no brainers. What is really interesting is potential for dog-bot kung-ku to take-down and subdue folks without the problem of oppressive demographics. Robots dancing is old now, what we need is robot martial arts :D

*god this seem obscure and fun enough: anyone help crowdfund this idea?*
Imagine them relentlessly following their targets and serving writs and subpoenas with those arms.
 
I am not impressed. The loud gas engine on BigDog is a dead giveaway. If I was guarding a perimeter, I would find out how many rounds it would take to bring one down or cripple it. The same with other robot dogs.
 
I am not impressed. The loud gas engine on BigDog is a dead giveaway. If I was guarding a perimeter, I would find out how many rounds it would take to bring one down or cripple it. The same with other robot dogs.
Have you actually been watching what's going on the last few years? For real applications Bigdog and it's gas engine has long since been superseded by Spot, which is all electric and quiet.
 
I have. I also recall watching a video of a six-legged manned vehicle on trials. Anyway, the more complex a system is, the easier it is to eliminate. Damage one leg and a four-legged robot is not going far. And due to cost, I cannot see this going beyond civilian tasks. And how much armor does one of these have? It would be like taking down an animal.
 
Last edited by a moderator:
I have. I also recall watching a video of a six-legged manned vehicle on trials. Anyway, the more complex a system is, the easier it is to eliminate. Damage one leg and a four-legged robot is not going far. And due to cost, I cannot see this going beyond civilian tasks. And how much armor does one of these have? It would be like taking down an animal.
Take a look at their DARPA collaboration cheetah bot...

Also they've extensively worked on ML with Carnegie Mellon and others which will eventually result in them being able to operate with damaged or lost limbs.

It may not be there yet but we are reaching a point where brute force computing will start speeding stuff like this up more and more.
 
Given that Spot is capable of hopping around on just two legs, I'm sure they could add a gaits for damaged legs.
 
I am not impressed. The loud gas engine on BigDog is a dead giveaway. If I was guarding a perimeter, I would find out how many rounds it would take to bring one down or cripple it. The same with other robot dogs.
Have you actually been watching what's going on the last few years? For real applications Bigdog and it's gas engine has long since been superseded by Spot, which is all electric and quiet.

Spot can carry a 400 lbs payload? Then again even LS3's original requirements, being based on Army squads, might be too weedy for the Marines.

Something like Spot might replace the Packbots for pre-breaching reconnaissance, though. Rafael has something similar for indoor recon built on a Ghost Robotics' chassis.
 
Chinese cheap robots, coming to swarm bored yuppie near u
View: https://www.youtube.com/watch?v=xdfmhWQyp_8



Spec sheet
%E5%A4%A9%E7%8C%AB-%E8%8B%B1%E6%96%87-19_d843080f56.jpeg


Now that I think about it, the door opening arm as kind of a killer app (with deepest growth curve with software dev, which have barely started) IMO, legged locomotion by itself is really quite meh.

Winning the software stack will probably be the biggest thing. Will have to do some research into the field....
 
Chinese cheap robots, coming to swarm bored yuppie near u
View: https://www.youtube.com/watch?v=xdfmhWQyp_8



Spec sheet


Now that I think about it, the door opening arm as kind of a killer app (with deepest growth curve with software dev, which have barely started) IMO, legged locomotion by itself is really quite meh.

Winning the software stack will probably be the biggest thing. Will have to do some research into the field....

Aged care is probably going to be a major market for these if they're thought of as part of house systems rather than singular devices - especially installed as valets in houses not originally designed for the elderly.
 

...announcing Rapid Motor Adaptation (RMA)....

Until now, legged robots have either been fully hand-coded for the environments they will inhabit or taught to navigate their environments through a combination of hand-coding and learning techniques. RMA is the first entirely learning-based system to enable a legged robot to adapt to its environment from scratch by exploring and interacting with the world.

Our tests demonstrate that an RMA-enabled robot outperforms alternative systems when walking over different surfaces, slopes, and obstacles, and when given different payloads to carry. This requires going beyond even sophisticated hand-coding, because it is difficult or impossible to preprogram a robot to adjust to the full range of real-world conditions, whether it’s a different type of rug, a deeper mud puddle, or a bouncier trampoline. Moreover, to work reliably, robots must be able to adjust not only to carrying different loads but also to expected wear and tear, like a dent on the bottom of its foot, a slightly worn-down part, or the countless other unpredictable changes that happen in the real world. Because its ability is based entirely on what it encounters, an RMA-enabled robot can adjust to situations programmers never even considered.

We are now sharing our work, including implementation details and experimental results, in this paper.

View: https://www.youtube.com/watch?v=qKF6dr_S-wQ


------------
Impression: Research is DONE. It is now market research and engineering~
 

Similar threads

Back
Top Bottom