Exyn Technologies is pioneering autonomous aerial robot systems for complex, GPS-denied environments. The company’s full-stack solution enables flexible deployment of single or multi robots that can intelligently navigate and dynamically adapt to complex environments in real-time.
For the first time, industries like mining, logistics, and construction can benefit from a single, integrated solution to capture critical and time-sensitive data in a safer, more affordable, and more efficient way. Exyn is powered by a team of experts in autonomous systems, robotics, and industrial engineering, and is a spin-off of Penn’s world-renowned GRASP Laboratory. The company is VC backed and privately held, with headquarters in Philadelphia.
Deliver a larger and more accurate volume of data to clients to improve business decisions and keep employees safe.
Exyn Technologies successfully worked in partnership with Rupert Resources, a Canadian-based gold exploration and development company. By harnessing Exyn’s autonomous drones, Rupert Resources was able to produce highly detailed 3D models of a historic gold mine in Central Lapland of Northern Finland, which are otherwise completely inaccessible to traditional CMS tools or even manually piloted drones.
Rupert Resources needed to plan for a potential restart of operations by estimating tonnage previously removed from the mine, as well as calculating the remaining ore in heavily restricted areas. Exyn’s fully-autonomous aerial robots mapped 30 stopes in three days with a single drone. In addition, Exyn mounted a version of its robot to a car to scan all access drifts that, together with the stope maps, provided a complete mine map in under four days.
“Rupert is actively seeking new technologies where we think big gains can be made in terms of safety, productivity, and accuracy,” said Jukka Nieminen, Managing Director of Rupert Finland. “Exyn achieved accurate assessment of the volume of remaining stopes at Pahtavaara with an unprecedented level of detail, and obviously the use of remote technologies means that this was achieved with a greatly reduced degree of risk. We have no hesitation in recommending this technology.”
Exyn’s autonomous drones are built on the exynAI™ platform, enabling aerial robots to fly intelligently without a human pilot using a multitude of high-tech sensors and AI-based software. The system operates without the need for GPS or external communications, and is deployed as an all-in-one software and hardware package.
“Our mission with Rupert presented some of the most difficult and seemingly impossible challenges to navigating, analyzing, and assessing a mine–which therefore makes it exemplary in demonstrating the heights of Exyn’s capabilities. Our AI-based software and state-of-the-art sensors were able to get the job done quickly and safely, proving once again that no exploration task is impossible for Exyn drones,” Raffi Jabrayan, Director of Markets & Industries, Exyn Technologies.
exynAI software enables Exyn’s A3Rs to answer the questions vital for aerial autonomy: “Where am I?”, “Where am I going?”, “How do I get there?” and “What do I see along the way?” They accomplish this online and in real-time using only onboard computation and sensing. Multi-sensor data fusion lies at the heart of their state estimation and is responsible for answering the first question. Exyn intelligently fuses lidar-based odometry and mapping with visual information to reliably estimate the robot’s position and orientation relative to its start. Access to GPS or markers is not required, but Exyn can integrate it if available.
The second and third questions are addressed by the exynAI autonomous navigation stack.
The robot is given mission-level specifications (e.g., explore your surroundings!) that can be decomposed into a series of tasks that ultimately get distilled into sparse locations the robot is requested to visit. As the robot moves from location to location, it continuously builds/updates a local 3D map that it uses to determine what regions in the surrounding space are “passable” or “clear” of obstacles. Given this local map, the robot uses Exyn’s accelerated motion planning stack to identify a safe 3D corridor in which to travel to its next goal. More precisely, it uses this 3D corridor to compute dynamically feasible trajectories. This process repeats in a real-time loop, with the robot first sensing its environment, updating its map, and verifying whether its original plan is safe or if it should replan to find a new route. The ability to execute this sequence of steps in real-time is paramount for handling dynamic environments.
Finally, Exyn’s robot employs a number of technologies to help it perceive and understand its surroundings. Simultaneous localization and mapping (SLAM) allows the robot to generate globally-consistent maps of the space it has seen by identifying uniquely distinguishing features. This allows the robot to also correct for errors occurring in its odometry. Another is semantic object classification and mapping using recent advances in deep learning. The robot can identify and detect objects, such as people, and accordingly adapt its behavior.