By Jon Cash, Senior Program Manager, Draper
Global spending on unmanned aerial vehicles is poised for a major expansion in the coming decade as militaries invest an estimated $98 billion in new capabilities. One factor driving the market are improvements in UAS software that can enable drones of various sizes by various vendors to operate with new capabilities, most notably autonomous navigation.
The goal is to provide soldiers with an unmanned system that can fit in a backpack and serve as eyes and ears in areas too dangerous for troops to physically enter, such as suspicious buildings or a turn in the road ahead. Delivering such capability requires an autonomy architecture and software package that can enable UAS to do more than ever before.
Draper isn’t alone in developing sUASs for the next battlefield, and we welcome new
developments from the community. The common goal is to enable soldiers to proceed with greater certainty and capability in ever-changing operational environments.
Draper is working with the Department of Defense under a three-year contract to address these challenges—and improve UAS—by focusing on the most challenging aspects of autonomous navigation. In a series of recent demonstrations, a team from Draper and the DoD customer tackled technical issues related to reducing collisions, enhancing onboard intelligence and developing new robust navigation methods.
The demonstration showed that a small handheld UAS could navigate narrow interiors in urban and indoor GPS-denied environments, create 3D maps of these environments, identify and avoid objects and return autonomously to the base. While others have worked in this area, Draper’s approach uses highly-optimized autonomy software capable of running on a cellphone-size embedded processor while using a single camera as the main sensor, thus maintaining an overall low size, weight and power.
The new generation of small UAS needs to be able to fly independently and plan an obstacle-free route in real-time without any prior knowledge of the environment. And they should be capable of closed-loop and fully autonomous flight, but until now that goal has been out of reach for many small UAS.
Gian Luca Mariottini, a colleague of mine at Draper, points out another requirement for the next generation of military drones is to reduce the cognitive load of the operator. With a fully autonomous UAV, the operator can focus on higher value tasks, such as intelligence, surveillance and reconnaissance. Our view is that unmanned systems shouldn’t require the full attention of a soldier or pilot in order for them to be effective, which is where autonomy can help to offload some of this burden.
Toward that end, Draper has designed a user interface to provide a soldier with up-to-date information about the environment and the type of objects of interest observed during the UAS flight, as well as information about the UAS operational status.
Mariottini, an expert in unmanned aerial and ground systems, is already working toward more advanced autonomous capabilities for sUAS to enable robust navigation at night in more diverse operating environments.
In particular, Draper is adding new features to its autonomy system, including new onboard artificial intelligence (AI) solutions for inferring depth distance for each pixel in an image and enabling operations in more complex environments.
Longer term, Draper wants to enable autonomous adaptive exploration of large environments, possibly for groups of cooperating drones. With these and other advances in micro-, mini- and small-UAS, one thing is becoming clear: the next battlefield will rely on unmanned systems like never before.