We’re updating the NavAbility Cloud!

We're updating the NavAbility Cloud!

In preparation for our tutorials at ICRA2022 (join us on May 27th in person or by remote on Gather.Town!) NavAbility is excited to announce the deployment of our first official production environment of NavAbility Cloud. Our mission is to enable more vibrant robotics automation and this is an important step in empowering our community with a reliable, stable, and secure NavAbility Cloud.

These changes will enable exciting upcoming features such as automated calibration, big data integration, and simplified user authentication. More to follow as we release these features!

Timeframe and Affected Services

The deployment will begin at 8:00pm PST on April 14, 2022. You may experience some instability of existing environments during the deployment as we cut various services over into production.

Once the deployment is complete, we will announce it in ‘general_help’ on the NavAbility Slack channel. After that announcement, you should switch to using NavAbility Cloud via the following URLs:
https://app.navability.io
https://api.navability.io

As a consequence of this deployment, we will be asking our existing users to recreate their user accounts. Please go to https://app.navability.io, click login and then sign up. If you need your existing data migrated to your new account, please email us at support@navability.io by May 13, 2022.

Thank you for your patience and understanding while we take this milestone step in our journey.

New YouTube video: Easily using camera data for navigation and localization

New YouTube video: Easily using camera data for navigation and localization

You have a camera on your robot… but now what?

We’re starting the discussion on how to convert camera data into information that can be used for navigation and localization.

Next up: Loop closures and why that’s the crux of a robust navigation solution!

References:
* Edwin Olson’s AprilTags paper: https://april.eecs.umich.edu/media/pdfs/olson2011tags.pdf
* C/C++ library: https://github.com/AprilRobotics/apriltag
* A Python library: https://github.com/duckietown/lib-dt-apriltags
* Julia library: https://github.com/JuliaRobotics/AprilTags.jl

We’re all learning here, so please feel free to comment about other good wrappers of the AprilTags library!

New YouTube video: Factor graphs and their importance in robotics

New YouTube video: Factor graphs and their importance in robotics

We promised to have a conversation on all things robotics, and a great place to start that conversation is on factor graphs. This is the topic of your second video on the NavAbility YouTube channel, which is embedded below.

We also love communication, so If you have a topic in mind please comment on the videos or email us at info@navability.io.

Start small, dream big! How does NavAbility empower teams to deliver?

Start small, dream big!

At NavAbility, we believe that robotics and autonomy are hard problems. This is because they’re emerging and changing continuously. Robotics and autonomy require a journey. In this article, we discuss how NavAbility empowers you to deliver on your projects.
 
We want to make solutions that are accessible to organizations of all sizes. The current state of this industry has numerous technologies which rarely interoperate and require significant upfront cost to implement. We want to change that. We want you to be able to get started with a minimal viable navigation solution. And then provide a comprehensive and robust suite of tools that allows you to scale and grow that solution into a production ready product.
 

We are developing that platform.

The NavAbility Platform is has a zero-install setup (Stay tuned for our tutorials app!) through to a fully-functional on-device deployment. It is grounded in next generation technology, MM-iSAMv2, allowing for almost limitless possibilities for your project journey.
 
This is where we need your help! We are focusing on building the best-in-class navigation software, but we need you to integrate your projects on top of it. It is early days, but already our technology can perform in place of GTSAM, Nav2, or SLAMCore. From there, we cannot wait for you to try the additional game-changing features made possible by our next generation technology.
 
The NavAbility Platform will give any organization a significantly lower cost of ownership, a much quicker time to market, and a reduced risk with a clear roadmap as you scale up. Reach out to discuss how we can help each other. Continue reading to learn more about how our strategy and technology enables these outcomes.

Lower cost of ownership

Deploy today with our ready to use products

First, the algorithm<->hardware tradeoff. There is often a trade off between the quality of your algorithms and the quality of your hardware. On one hand, you can use an algorithm with simplifying assumptions for speed and performance, but this may require an expensive sensor. However, if your algorithm is robust, it may run more slowly, but you can use a lower-cost sensor. The issue is that this choice has to be made very early in the project with little knowledge of how the design may iterate. If the wrong choice is made, or the technical requirements change, this can result in high cost. The MM-iSAMv2 technology allows you to start with the simplest available hardware while you develop and test and only upgrade when you need. The underlying algorithms leverage factor graph and manifold mathematics, enabling it to solve the most challenging problems without compromising performance. In the end, you can engineer for cost rather than be stuck with whatever you started with.

Second, the true cost of implementation. Once you get everything working in the lab or on your desktop computer, how do you bring that to market? There is a huge gap between a proof-of-concept and a running production product. NavAbility is providing a ready to use cloud platform that can be used from initial concept to scaled-up production system. This way you can focus on your specific product rather than how to host your computations.

Third, the distributed computing problem. The MM-iSAMv2 technology allows for data syncing between edge devices and cloud allowing for the flexibility to run large compute in the cloud and share that data with the edge. This reduces the overall cost of the compute hardware on the edge if your application has any sort of connection to the cloud.
As we stated above, robotics and autonomy are hard problems. They require a journey. Often it takes weeks to properly validate that a technology will work for your needs. In addition, your organization may have to hire costly personnel to develop navigation solutions. NavAbility’s core competency is navigation solutions and we are here to help. Together we are able to solve the navigation problem you are encountering.
 
The MM-iSAMv2 technology is flexible, so you can get a Minimum Viable Product running and just start gathering feedback from your customers. When the timing is right or if something is not right, it’s easy to drop in new, or more, hardware or iterate on the algorithm. In the end, we are always here to help you optimize your designs as your approaching launch day.

Faster time to market

Engage our experts to rapidly develop your novel applications

experiment

Reduce project risk

Leverage our next generation technology to avoid costly R&D

One of the greatest risks on a project is missing the targets. In an R&D project, you might go over budget. When developing a product, the market might not bear the cost needed to deliver. The best solution to these challenges is to get feedback quickly.
 
The platform we are building is there to help you understand what is possible and how to get there quickly. You can validate designs with customers through simulations on the NavAbility Cloud or even build a one-off Proof-of-Concept using AprilTag stickers and cell-phone cameras. This isn’t the final solution, but gathering early data to validate the viability of an idea dramatically reduces the risk.
 
The MM-iSAMv2 technology is built into an open-source suite known as Caesar.jl. Our success stories are examples and papers. Our struggles are out there in the open. You know what will work on day one and what needs additional R&D budget. Why trust a single company, when you can trust our community of followers and open codebase?

How can we help?

We want to build the platform that you need. What is your minimum viable navigation solution? What projects are you working on that are over-budget, not getting to market, or may be canceled? What technologies are you using today and how can they be better? The more we know, the better we can support your needs!

Contact us

Find out how we can help you in your navigation journey

Announcing our YouTube channel on all things robotics!

Announcing our YouTube channel and Livestream on all things robotics!

We’re excited to announce our NavAbility YouTube channel on all things robotics!

We’ll dive into interesting topics about robots, sensors, navigation, and coordination – the “what to expect when you’re expecting a robot” for everyone from commercial users through to home hobbyists. Jim will also be doing a YouTube Live stream to discuss the last video, answer questions, and talk about industry news.

Subscribe the NavAbility YouTube channel to follow us as we release these discussions. We also love communication, so If you have a topic in mind please comment on the videos or email us at info@navability.io.

Conference News: Join us at ICRA 2022 in Philadelphia!

Join Us At ICRA 2022 in Philadelphia

Great news! We’re giving a tutorial workshop at the premier robotics conference, IEEE’s International Conference on Robotics and Automation (ICRA) in Philadelphia. 

Join us to learn why navigation robustness is critical in building effective robotics. This is a great opportunity to discuss real-world robotics problems such as the notorious “How do I handle uncertainties in my data?” question, i.e. multi-hypothesis and null-hypothesis data. We’ll also address emerging topics such as SLAM cloud computing and data persistence.

Find our Workshop Landing Page here.  See you in Philadelphia May 23rd – 27th!

More to follow! Keep up to date by following us on LinkedIn, join the discussion on Slack, or learn more about our Technology .

Coming soon: Marine surface vehicle example using radar for localization

One of our immediate aims is to demonstrate the NavAbility technology in real-world applications, and in this vein we’d like to give a preview of results from an exciting project.

This example is applicability to a variety of use-cases, from docking marine vehicles through to navigation of industrial indoor robots… And yes, self-driving too.

In the coming weeks we will release this as a complete working example. In the meantime, here is a short overview and preliminary results.

Seagrant REx at the MIT pavilion with Njord submersible hanging from center

REx and Radar Data

The MITSea Grant Remote Explorer (REx), shown above, is an autonomous marine surface vehicle used for diverse research applications . The vehicle is equipped with a variety of sensors, however the focus of this project is to use only the radar data for localization as it entered the Boston harbor. 

Dehann Fourie (CEO) constructed a GPS-denied navigation solution using the NavAbility stack, processing raw ROS radar payloads (shown below) into a complete factor graph to calculate a SLAM solution.

The example demonstrates how specialized data types can be created to capture and process radar information, which is simple to do using the Caesar.jl stack. A preliminary result of the solved trajectory is shown below.

Raw radar sweep extracted from ROS dataset
The solved trajectory (light-blue) of the vehicle as it travels into the harbor (poses highlighted).

Complete application example to follow soon

Keep an eye out for the complete example in the coming weeks!

Intrigued? Imagine what we can do with your robotics application! Please reach out to us at info@navability.io if you’re curious or have any questions.