Skip to main content

Multi-contact Collaborative Humanoids in Aircraft Manufacturing

Periodic Reporting for period 3 - COMANOID (Multi-contact Collaborative Humanoids in Aircraft Manufacturing)

Reporting period: 2018-01-01 to 2018-12-31

COMANOID aims at deploying humanoid robots to achieve non-added value tasks that have been identified by Airbus Group in civilian airliner assembly operations. The project focuses on showing precise accessibility (namely into areas where wheeled robots cannot be deployed) through whole body multi-contact planning motion with advanced embedded 3D dense SLAM localization and multi-modal servoing capabilities. This will be demonstrated with a bracket positioning task, but also, as recently requested by Airbus, circuit-breakers checking and torqueing operations. These tasks do not require gripper manipulation dexterity but high precision. These scenarios can be extended to others after the project. Because the robots evolve in human worker co-localized spaces, safety issues will be specifically accounted for. The results of COMANOID will be showcased during the final review meeting within a 1:1 scale demonstrator of a real aircraft (A350), already made available at Saint-Nazaire (France) using two humanoid robots: the HRP-4 position controlled humanoid robot provided by CNRS partner and the TORO torque controlled humanoid robot provided by DLR partner. During the course of the COMANOID project, an AIST-CNRS-Airbus project was established (that terminated also this year) in order to address other use-cases of increasing complexity such as the A400M access use case by Airbus Defence and Space, and Airbus Helicopters (circuit-breakers).

We have structured the project into five work packages. The work achieved for the third and last reporting period is described together with the sub-objectives of each of them. As writing rules, we decided to simply refer to the deliverable document when a given work was released as a report; synthetize the main results for works that have been published as scientific papers but not released as a deliverable report; and finally provide a thorough explanation and description of the work otherwise (no published yet). We have also attached into the annex all publications that are new, (i.e. published or submitted within 2018) and not provided in any other deliverable (including previous ones).
The main achievement during this period in WP1 are the following:
- Finalizing all the pending publications, writing a book chapter concerning multi-contact planning and control in the Springer-Nature handbook of humanoids.
- Finalizing work that was on-going or initiated during the previous review meeting.
- Integration in the final demonstrators we achieved.

WP2 provides all the information required for multi-contact planning and control (WP1), as well as safe and robust walking (WP1 and WP3). Its outputs compose the main bricks for the humanoid perception integration achieved in WP4. Visual servoying and SLAM have been further developped and integrated to the demonstrators.

WP3 provides guidelines for the safe deployment of humanoid robots. The most critical aspect is the safety of human co-workers that share the environment with the robot. However, safety of the humanoid itself and of the surrounding environment is also very important. This period also focused on integration and finalizing the tasks that were in progress.

In WP4, the demonstrators are acheived and will be shown at the review meeting.
The progress that is achieved in main COMANOID technologies is now ahead of the current state-of-the-art in multi-contact planning and control. We have achieved substantial advances in all key technologies as described in the technical document provided. We will be able to measure any impact on the socio-economical and societal tissues when the demonstrator will be achieved. Note that for walking, we are far from what Boston Dynamics is capable of achieving, this is due to the quality of their hardware, the funding discrepancy and the man-power.