Summary of the technology
A research group from a Spanish University has designed and implemented a new system based on a technology able to perform optimal navigation planning in aircrafts. The new approach is mainly characterized by its autonomously learning capacity and adaptability to changes in the dynamics of the platform and environment. Potential collaborations with international/national research centres and companies interested in applying the technology are sought.
New and innovative aspects
The developed technology for being applied to aircrafts in order to perform optimal navigation planning is cost-effective and robust against changes in the environment or in physic structure of the platform. One of the pillars of the new technology is the lack of mathematical models for the performance of planning, and, instead, it uses the experience gained through interaction with the environment and the platform. As a consequence of the internal behaviour of the technology, the new system is not sensitive to sampling period used.
Main advantages of its use
Low cost, robust against changes, 4D-trajectories generation autonomously and intelligent for aircrafts.
Easy transfer of technology due to the maturity achieved with the new approach in other areas.
The Space Research Group (SRG), specialised in different areas related to Aerospace, including Optimal Control, designs and builds instrumentation to be used on-board satellites, spacecrafts and unmanned aerial vehicles.
This new technology offered by this group is able to perform optimal navigation planning according to specific optimization criteria (e.g. minimum time).
The research carried out by the SRG Group lets us have an available system, which is very robust against changes in the environment or in physic structure of the aircraft. In order to achieve this robustness, it is necessary to perform a learning that takes into account of an implicit way these possible changes and is able to know the dynamics of the aircraft in real-time. From this learning, the system shall perform optimal navigation planning. Also, the new approach is a closed-loop solution and learning is focused on reaching a specific goal starting from any origin state, according to an optimization criterion. Both the goal and origin are states that are characterized by dynamics and location information of the aircraft. The goal is a state to where the aircraft should be directed optimally and autonomously. On the other hand, the origin state is the current state of the platform.
In this way, the aircraft learns the dynamics and kinematics from the experience without any kind of explicit mathematical models. Thus, the implementation of the new technology consists of learning the dynamics of the platform and performing optimal navigation planning of a concurrent way. The great advantage of the concurrency is to adapt the controller while it is being applied and, thus, achieving a behaviour that comes close to optimum.
The platform is characterized by so-called state variables and the procedure carried out by the new technology is to act on the platform through control actions in order to modify its current state. Therefore, the set of state variables and their values range constitute the so-called state space which will be the scope of the new system. Sometimes, in order to reduce learning times, it is important to take into account possible symmetries among state variables and the possibility of extrapolating local knowledge to other areas of the state space.
Another unique feature of the new technology is the absence of criticality in the choice of sampling period. Regardless of chosen value, controllability will not be affected because the period is automatically adjusted.
- Aerospace and aeronautics