In-flight Replanning Research Articles

Data-Driven Approach Using Machine Learning for Real-Time Flight Path Optimization

Airlines traditionally gather weather information before departure to generate flight routes that avoid hazardous weather while minimizing flight time. However, flight crews may have to perform in-flight replanning as weather information can significantly change after departure. This in-flight replanning activity is currently not fully automated, which has the potential to increase crew workload and adversely impact flight safety. The objective of this research is to mitigate some of these issues by developing an automated framework to perform continuous in-flight replanning. The proposed framework relies on three pillars and leverages: supervised machine learning technique to augment existing wind forecasts by providing a higher spatial and temporal granularity, unsupervised machine learning technique to perform short-term predictions of areas with significant convective activity, and graph-based pathfinding algorithm to generate optimized trajectories. The main contribution of this research is to combine these techniques to autonomously and continuously generate trajectories that minimize operating expenditures for airlines. Statistical analyses are performed to demonstrate the applicability and benefits of the proposed framework. Results indicate that optimized trajectories are 2% shorter than actual flight routes in most cases.

Choosing Path Replanning Strategies for Unmanned Aircraft Systems

Unmanned aircraft systems use a variety of techniques to plan collision-free flight paths given a map of obstacles and no-fly zones. However, maps are not perfect and obstacles may change over time or be detected during flight, which may invalidate paths that the aircraft is already following. Thus, dynamic in-flight replanning is required. Numerous strategies can be used for replanning, where the time requirements and the plan quality associated with each strategy depend on the environment around the original flight path. In this paper, we investigate the use of machine learning techniques, in particular support vector machines, to choose the best possible replanning strategy depending on the amount of time available. The system has been implemented, integrated and tested in hardware-in-the-loop simulation with a Yamaha RMAX helicopter platform.

Flight path optimization with application to in-flight replanning to changing destinations

PurposeThe purpose of this paper is to present a new approach for finding a minimum-length trajectory for an autonomous unmanned air vehicle or a long-range missile from a release point with specified release conditions to a destination with specified approach conditions. The trajectory has to avoid obstacles and no-fly zones and must take into account the kinematic constraints of the air vehicle.Design/methodology/approachA discrete routing model is proposed that represents the airspace by a sophisticated network. The problem is then solved by applying standard shortest-path algorithms.FindingsIn contrast to the most widely used grids, the generated networks allow arbitrary flight directions and turn angles, as well as maneuvers of different strengths, thus fully exploiting the flight capabilities of the aircraft. Moreover, the networks are resolution-independent and provide high flexibility by the option to adapt density.Practical implicationsAs an application, a concept for in-flight replanning of flight paths to changing destinations is proposed. All computationally intensive tasks are performed in a pre-flight planning prior to the launch of the mission. The in-flight planning is based entirely on precalculated data, which are stored in the onboard computer of the air vehicle. In particular, no path finding algorithms with high or unpredictable running time and uncertain outcome have to be applied during flight.Originality/valueThe paper presents a new network-based algorithm for flight path optimization that overcomes weaknesses of grid-based approaches and allows high-quality solutions. The method can be applied for quick in-flight replanning of flight paths.

Direct Manipulation Interfaces for In-Flight Four-Dimensional Navigation Planning

A direct manipulation interface for 4-dimensional (spatio-temporal) in-flight replanning was developed. The interface coupled the pilots' actions and the consequences of these actions for the overall replanning goals through a visual display of the flight plan's temporal and spatial layout, as well as the temporal and spatial constraints on altering the flight plan. Three levels of interface information detail were tested for 2 scenarios with different levels of complexity of the flight plan and the changes required. It was found that the medium- and high-detail interfaces are faster, are easier to use, provide better task performance, and are preferred by the pilots participating in the experiment. The expected advantage of visualizing the spatial and temporal constraints on the interface through elliptical affordance zones did not result in a better performance, lower click count, or higher appreciation than the medium-level interface.