Skip to main content

IMage BAsed Landing Solutions

Periodic Reporting for period 1 - IMBALS (IMage BAsed Landing Solutions)

Reporting period: 2018-03-01 to 2019-08-31

The approach and landing phases are the most critical ones in commercial aircraft operations and many aircraft accidents have a significant contribution from human error. Hence, automation during these phases is a promising path to increase aviation safety, which is a societal interest. The current state of art in automated landing is depending on ground infrastructure on the airport which is often lacking due to cost and/or obstacle constraints. The overall objective of the IMBALS project is to develop, validate and verify a certifiable Image Processing Platform (IPP) and demonstrate it in a Vision Landing System (VLS) that is capable of autolanding a large passenger aircraft based on images supplied by an on-board camera system. This resolves the dependency on ground infrastructure and will enable automated (and thus safer) landings at the many locations where today it is not possible.
The current state of art in auto-landing also imposes restrictions which negatively impact airport throughput. This may result in aircraft waiting in a holding pattern, which increases the environmental footprint of aviation. This can be avoided with the proposed VLS since these restrictions would not apply to image based technology.
The aviation sector fears that the training of new pilots will not be able to cope with the fast growing demand for pilots. This would result in pilot shortage. The workload reduction provided by the VLS is one of the enablers to transition to single-pilot operations, which would be a workaround for that pilot shortage. This will help to address the societal challenge towards mobility.
The IMBALS project will start from the Concept of Operations (CONOPS) for VLS approach and landing. From there, requirements will be derived for the IPP equipment and these will drive the IPP development and prototyping. The IPP will be validated and verified in lab environment, system test bench and flight tests. The VLS Human-Machine-Interface (HMI) will be validated in a cockpit simulator. The purpose is to reach TRL5 and the project will strongly emphasise on safety and certifiability of the system. Particularly the certification of image processing algorithms will require progress beyond the current state of art.
"The following work has been performed in the first reporting period:

WP1 Detailed project plan
A master plan has been released as deliverable D1.1 ""Project Plan"" and has been approved in a formal planning review (MS2 ""Planning Review""). This master plan is the basis for managing the project in WP9. WP1 is closed.

WP2 Definition of requirements
The functional requirements have been defined by Airbus. ScioTeq has captured equipment level requirements in deliverable D2.1 ""System Requirements Document"". These requirements are being reviewed with the consortium partners and with Airbus.

WP3 Validation & verification plan
ScioTeq and Airbus did a first alignment on the different V&V environments and strategies. ScioTeq has drafted a ""V&V Plan"" (deliverable D3.1) which is in review with the partners and Airbus. Further work on D3.1 is obstructed by the delay in WP2 and WP4.

WP4 System definition
KU Leuven demonstrated a first representative algorithm. (UN)MANNED has already started defining the operators for this algorithm in their Sol language.
ScioTeq started comparing different system architectures for the VLS and IPP. Progress in WP4 is obstructed by the delay in WP2.

WP5 System validation - WP6 System verification - WP7 Final report
Not started yet.

WP8 Prestudies
WP8 can be divided in two main activities: collection of video footage and a technology survey.
TEKEVER recorded visual and Infra-Red video footage during flight patterns that were defined by TEKEVER and ScioTeq. Airbus provided complementary visual wavelength video footage. This footage is a stimulus during the testing of algorithms. TEKEVER also released a first version of its video player. A description of the video gallery and the video player is captured in deliverable D8.1 ""Video Gallery"".
The technology survey yields a ""shopping list"" with building blocks and principles that could be used in the upcoming work packages and this is captured in D8.2 ""Technology Survey Report"".
WP8 is closed.

WP9 Project management & dissemination
This work package includes
- MS1 ""Kick-off Meeting""
- Establishing the contractual framework, resulting in deliverable D9.1 ""Report of the signature of the agreement"",
- Progress meetings within the consortium (weekly) and with the topic manager (monthly), quarterly report to the CS2 JU,
- Tracking progress towards the master plan from WP1,
- Develop deliverables D9.2 and D9.3 ""Plan for Dissemination and Exploitation of Results"" and launching the first communication actions.
WP9 remains anyway an active work package and deliverable D9.4 ""Management plan and risk register"" is not yet released."
The main progress beyond the state of art relates to the increased autonomy that will be reached for the landing of large passenger aircraft. Today, fully automated landing can only be performed when expensive ground infrastructure is available on the ground. This is not always available due to cost and/or obstacle considerations. Additionally, auto-landing operations impose some restrictions that negatively impact airport throughput. As a result, the large majority of landings with commercial aircraft (close to 99%) is still conducted with a phase where the human pilot takes full control of the aircraft. With 49% of fatal aircraft accidents happening in the approach and landing phases and many of them having a demonstratable contribution from human error, it is clear that fully automated landing will have a positive impact on aviation safety, provided that commensurate safety levels of the automated system can be assured. To reach this goal, the image based landing function must meet the safety objectives for catastrophic failure conditions. This immediately sets the highest safety levels to the IPP and its hosted algorithms. This will require novel techniques to establish a measurable confidence level about the output of these algorithms. There is no prior art in certifying image processing algorithms with possibly catastrophic failure conditions for use in commercial aircraft.
Additionally, preserving airport throughput while auto-landing operations are ongoing will reduce the number of aircraft in holdings and thus have a positive impact on the environmental footprint of aviation.
The high level of automation enabled with image based landing will also support the transition from dual to single pilot operation in large commercial aircraft. This will address the expected shortage of airline pilots and reduce operating cost. This will be an important competitive advantage for the aircraft manufacturer adopting such system.