Home / Blog

Blog

SLAM: The L is for Localization – the M is for Mapping

SLAM: The L is for Localization – the M is for Mapping

Autonomous Drone Sensing Technologies for SLAM

There are many components and technologies that go into building a drone that can navigate on its own. An autonomous drone uses an on-going loop of sensing, thinking and acting. A robot is only as good as its sensors, so sensing is an essential component that allows the drone to reach its destination.

SLAM, short for Simultaneous Location and Mapping, is the foundation of a self-navigating system and provides the framework within the robot can path plan. To arrive at its destination, a drone needs to know its location, build a map of its surroundings, and then plan a path or trajectory to where it’s going. In a dynamic environment, the drone needs to continuously update its mapping and SLAM supports that in real-time. If an object enters the drone’s path, it needs to generate a new path.

See an overview video about SLAM here.

ModalAI is using Visual Inertial Odometry (VIO) to support localization capabilities in its SLAM implementation and Voxels for the mapping elements.

Visual Inertial Odometry (VIO)

Visual Inertial Odometry (VIO) fuses an image sensor and an Inertial Measurement Unit (IMU) to estimate the drone’s change in position relative to where it started. In VOXL we use a global shutter image sensor that captures low-distortion pixels needed for computer vision simultaneously, instead of a rolling shutter sensor that is affected by the rapid movement of a drone.

Voxels

Voxels, or volumetric pixels, are computed by using the drone’s current location and projecting points from a depth map into 3D space. Voxel mapping is used for the Unmanned Aerial Systems (UAS) to understand the structure of its environment. For indoor applications, such as warehouse or security inspection, an active depth sensor like Time of Flight provides great results. For outdoor applications, passive stereo cameras work best, especially to compute depth maps at a longer range.

How it Works

As the drone takes flight, the UAS maintains its position using VIO and voxel mapping begins. 

Once the 3D structure is known, tree-based path planning (RRT*) can be used to generate a trajectory.

As the drone proceeds on its flight path, it continuously updates the mapping to stay on its mission and avoid obstacles. When new voxels obstruct the UAS’ planned path, it computes a new path to navigate around the obstacle.

While performing its mission, the drone is streaming the video the operator needs for the application. Some examples are mission-critical defense and security applications or safety inspections of a bridge or road.

The drone typically records video at a much higher resolution than it streams while in flight. You can use the captured video for further offline analysis.

ModalAI is Accelerating the Path to Autonomy

ModalAI is Accelerating the Path to Autonomy

At ModalAI, we are making our VOXL navigation computer easier than ever to use. Big news: Flight Deck is now available in our store! Flight deck is everything you need to get going on your own drone frame; it includes VOXL, Flight Core, and calibrated computer vision sensors ready to mount on your drone for visual inertial odometry and obstacle avoidance. All of our flight control hardware is made in the USA.

 

To help make the transition to our platform even easier, we have a complete reference drone for folks looking for a development platform to work out of the box. Check out our VOXL m500 here.

 

VOXL-Flight, our upcoming platform that combines a Qualcomm Snapdragon SoC on the same PCB as an STM32F7 fight controller, is back from our Southern California manufacturer. Check out our first flight here! VOXL-Flight combines VOXL and Flight Core to reduce cabling, size and cost. Long term, VOXL-Flight will enable advanced redundancy with multiple flight controllers running in parallel. 

Please post any suggestions or feature requests at support.modalai.com and we will do our best to incorporate in future releases.

We are frequently updating the following resources and encourage you to visit:


Advance your autonomous robot and drone development now with the tools and technologies offered by ModalAI. Sign up for our newsletter at shop.modalai.com to keep up with the news.

2020 is off to a fast start at ModalAI!

2020 is off to a fast start at ModalAI!

Here are the top 7 most exciting things we’ve got going on:

1. Flight Core is now shipping! Check out the latest PX4 flight controller from ModalAI. Flight Core is Made in the USA and can be paired with our VOXL platform for PX4 obstacle avoidance. We have support for programming Flight Core with the latest PX4 software in QGroundControl. More details here in the Flight Core Manual.

2. Say cheese! 4k video on board. Multiple 4k sensors are now available for VOXL, check them out here and here. More sensor options are coming soon!

3. We’re hittin the small screen Check out co-founder and CTO, Donald Hutson, and his STEM-supporting BattleBots efforts in Subaru commercial. Look closely and you can see an early proto of one of our upcoming products, VOXL-CAM. 

4. CES Showcase - We highlighted our latest in indoor, GPS-denied autonomy with our partner PMD in a video at this year’s CES show. (Watch)5. It’s a party! We’ve enabled multiple users to view video and control missions on a single SUAS. Our voxl-vision-px4 library, which enables native indoor/outdoor GPS-denied navigation and visual obstacle avoidance, now supports multiple QGC instances. This is useful for networked drones where multiple users want to monitor progress or video from a mission.

6. The mission continues...we’re continuing to add hardware capabilities based on your feedback. If it’s just one extra connection you are looking for our M0017 USB expansion and Serial debug board is now shipping. It exposes an expansion USB with a robust, locking connector for robotics applications.

7. Developers welcome! ROS is easiest to use when running in Ubuntu. To make VOXL as developer friendly as possible, we have been testing running Ubuntu 16.04 and ROS Kinetic in a Docker directly on VOXL. More details on accelerating your robotics and ROS development with Docker can be found here.

    Please post any suggestions or feature requests at support.modalai.com and we will do our best to incorporate in future releases.

    We are frequently updating the following resources and encourage you to visit:


    Begin your autonomous robot and drone development now with the tools and technologies offered by ModalAI. Sign up for our newsletter at shop.modalai.com to keep up with the news.