“Smart automation” is defined as automating appropriate elements of flight context-sensitive tasks to reduce workload peaks and even overall workload. Examples include automating checklists, using connectivity to create a “distributed cockpit”, extensive monitoring and data logging of system state, auto route planning based on vehicle state or contingency, and enabling reduced crew operations.
We view automation initially as a back stop to mitigate the human as a single point of failure but in the longer run, to serve as a transition from predominantly human-run operations to ultra reliable automation that enables full autonomy.
Because system and mode complexity have increased and variation between aircraft and software versions in fielded legacy systems is increasing, we believe that “smart automation” should start with flight critical but deterministic tasks (nominal checklist usage, system monitoring), and as experience and confidence is increased, move on to non-deterministic tasks (flight/mission planning, contingency planning, decision support, self-preservation, reaction to imminent threats) in the transition from those human-run operations to ultra reliable automation.
We have been building and flight testing systems that enable Manned-Unmanned Teaming since the company’s inception. We have built the on-board Mission Computer hardware and software and the off-board Control Station software for multiple MUM-T programs and have flight tested them to TRL-7. Our designs use a task-based approach (e.g. “Follow Him”, “Loiter”, “Fly Over That”, “RTB”, etc) and include a myriad of functionality that means the human supervisor or the manned part of the manned-unmanned team does not need to spend much cognitive bandwidth in controlling or directing the unmanned team members.
Our software has been specifically designed to support multi-ship collaborative autonomous operations. While multiple architectures are possible, to date, we’ve implemented an IP-network based approach such that every Mission Computer and Control Station is an entity in the network. Example functionality supported so far include multiple forms of x-y-z offset station keeping such as flying formation with another aircraft, maintaining a position or pattern referencing a fixed-position asset with aerial refueling next up in the queue. We are also moving to mesh network architectures that support n>>1 or swarming behaviors. The collaborative formation works as a distributed collective to find targets, reassign formation roles if required and share various forms of information.
We believe a new generation of Vertical Takeoff and Land (VTOL) vehicles will enable a new form of urban transportation using an Urban Air Mobility model, much like companies such as Uber and Lyft provide for urban surface transportation. Towards those ends, Autonodyne can provide:
- 4D Flight Management System (auto generate a route such that the user doesn’t need the expertise to define a proper route);
- Terminal departure/arrival guidance (create the depiction and guidance commands for 3D urban departure and approach verti-port corridors);
- Full envelope protection autopilot (a user or environment can not push a vehicle out of a safe flight envelope);
- Total connectivity (aircraft always connected to the internet with encrypted key);
- Redundant system monitors (includes extensive data-logging and on-demand maintenance alerts);
- Sensor fusion for high-risk flight segments (camera assist for landing and unique landing pad marking);
- Control station (all airborne data presented in near real-time cockpit-like presentation);
- Collision avoidance equipment and algorithms (e.g ACAS-X, TAWS - our sister company did the 2013 TSAA/ACAS flight testing for FAA);
- Graceful degradation algorithms.
We design and build mission computers (hardware and software) for defense and civil applications. These mission computers can manage a large selection of functions including vehicle navigation, vehicle health and status, on-board systems control like payloads, communications to/from other onboard systems like autopilots, and external comm links. We can host 3rd party software on our mission computer hardware and we can host our mission computer software on 3rd party hardware. We are currently in the process of designing the next generation of optimized UAS mission computers.
We design and build control station software ("RCU-1000") for unmanned or non-traditionally piloted aircraft. We can apply our expertise in Natural User Interface (NUI) design which enables control of multiple dissimilar make/model vehicles at the same time by a single operator. Our control stations serve as a supervisory tool, can run on a host of different hardware platforms (e.g. mobile tablets, PCs, laptops, etc), can display all known entities in the network and is link agnostic. It supports multi-touch (e.g. pinch zoom), traditional keyboard/mouse, commercial gaming controls (e.g. Xbox), and voice/gesture inputs from augmented reality devices (e.g. Hololens).
One of our mobile tablet control stations directly controlled a formation of high-speed (0.95Mach) UAS vehicles from a crew station on an airborne platform in the summer of 2017.
We are focused on applying commercially available augmented reality devices (e.g. Microsoft Hololens, Meta 2, smart eye-ware, etc) to flight operations. We have found AR can have a profound operational impact in areas such as 3D holographic representations of control station functionality, enabling remote maintenance of a flight vehicle, providing 3D overwatch functionality, providing innovative interactive swarm control and providing increased situational awareness in flight.