Volta extends from drones to autonomous cars

Our friends at Volta robotics have extended their MAVLink-compatible autopilot series to autonomous cars. This is what they demonstrated at CES this week:

Product Description

LEAD TIME: 60 days (due to post-CES orders peak) + 2 days international shipping

REDUX: same as BASE1 Rover, but reduced computing performance.

BASE 1 STACK

BASE 1 is an advanced and complete stack to remotely control unmanned vehicles. By elevating control capabilities to an higher base, it’s a solid starting point to create new services, projects and applications.

Cloud Station Gateway (for browser-based control, connect your vehicle here)
Remote commands (e.g: GoTo, Takeoff, Dive, Set Mode)

Remote file transfer (including: Neural Networks, Groud Truth, Python Scripts, MAV Mission Files)

Remote triggers (Neural Networks, Python Scripts, Auto Missions)

Languages: Python (w/ OpenCV)

Self-Driving-Rover Sample Neural Network

Deep Learning Frameworks: Caffe, Tensorflow

Gstreamer, MavProxy, MavLink

Ubuntu 14.04 LTS

BASE 1 HARDWARE

Main BOARD:
ODROID XU4 OCTA CORE

4G/LTE External Modem

16 GB eMMC

All wired, turnkey.

TT-ROBOTIX ROVER VEHICLE

Weight: 8.1kg

Dimensions: 531mm x 418mm x 321mm

Maximum Payload: 15kg

Max Speed: 18km

User Power: AC 110V, 5V, 12V

Runtime: 2 hours with 4s Batteries

Modular structures – perfect for development, simple for production

Precise actuators – for smooth movements in small spaces

Wide case – for agile sensors / boards placement; batteries for long travels and more

Network Technology: 4G/LTE and Wifi ready

Independent Power Source for Electronics and Motors

Translucent front glass, for visual inspections

Modular roof, with several sensors-mount possibilities (including cameras)

Pixhawk (or any other ArduRover autopilot)

Logitech HD 1080 Pixel camera (h.264 native, Zeiss lens, autofocus).

PERFORMANCE VIDEO

Interesting Jack,

I do have some skepticism.

For the Base 1 the vantage point suggests the camera would have to be on the raised stalk, but there is almost no side to side motion of the camera.

Other wise the quality of the stabilization does not suggest that this could have been stabilized out of it.

The quality of the video for that matter does not suggest a reasonable solution to the tracking issue either.

Also, the way it always seems to intuitively know which direction it immediately needs to turn to at each curve seems suspect as well, there is little or no "hunting" which I would expect at least a bit of from this sort of endeavor.

If they truly have accomplished full autonomous driving of that path with that rover, under those lighting conditions, they truly have made a major breakthrough.

I would like to have seen additional video or photographic evidence of the rover itself performing this passage.

Best,

Gary

You need to be a member of diydrones to add comments!

Join diydrones

Comments

Al B January 9, 2017 at 11:40pm

I agree with Gary. For less than $500, you can just build one using your smartphone.

https://youtu.be/ihmyHNJodvQ
Gary McCray January 8, 2017 at 1:41pm

Interesting Jack,

I do have some skepticism.

For the Base 1 the vantage point suggests the camera would have to be on the raised stalk, but there is almost no side to side motion of the camera.

Other wise the quality of the stabilization does not suggest that this could have been stabilized out of it.

The quality of the video for that matter does not suggest a reasonable solution to the tracking issue either.

Also, the way it always seems to intuitively know which direction it immediately needs to turn to at each curve seems suspect as well, there is little or no "hunting" which I would expect at least a bit of from this sort of endeavor.

If they truly have accomplished full autonomous driving of that path with that rover, under those lighting conditions, they truly have made a major breakthrough.

I would like to have seen additional video or photographic evidence of the rover itself performing this passage.

Best,

Gary
Jack Crossfire January 7, 2017 at 7:06pm

They claim this is the BASE-1 rover driving itself:

https://www.youtube.com/watch?v=GiE-ETVy7ok

completely with just the webcam. For the 1st time in 11 years, there's no mention of GPS. It doesn't do a good job staying to the right, but it handles shadows.
Auturgy January 7, 2017 at 3:13pm

Also, I suspect Chris has mistaken this company for another: Volta don't make autopilots
Auturgy January 7, 2017 at 1:09pm

I'd really like Volta to be "open" about their use of open source code/tools/projects, and whether they actively support the work they benefit from, or just rebrand and repackage.
Olivier January 7, 2017 at 11:50am

Gary, you may be ...

ODroid XU4 Octa core, 4G LTE Modem, browser base control via cloud, sample four layer convolutional neural network for self-driving.

R&D is never cheap.
Gary McCray January 7, 2017 at 10:36am

Wow, a $500.00 Thunder Tiger K-Rock truck with a spiffy body, a Pixhawk and a Logitech camera for only $5000.00.

Seems a bit much to me, but maybe I'm missing something.

Best Regards,

Gary
Rob_Lefebvre January 7, 2017 at 5:08am

"MAVLink-compatible autopilot"

Can't you at least be intellectually honest and say the words Ardupilot or Ardurover? You try to find any way to connect this back to work from ETH or Dronecode. It's really disappointing.

Or maybe if you want Dronecode to have Rover software to offer, have somebody pay for that work, or try to attract some volunteer developers to add it?
Auturgy January 7, 2017 at 12:52am

I'm guessing I just couldn't find @volta Robotics link to the source code and GPL v3 license, because Chris wouldn't actively promote a company that is violating the GPL, would he?
Olivier January 6, 2017 at 10:51pm

Just coinciding with the latest release. Nothing like it ...

of 2

This reply was deleted.