Community Research and Development Information Service - CORDIS


FLOBOT Report Summary

Project ID: 645376
Funded under: H2020-EU.

Periodic Reporting for period 1 - FLOBOT (Floor Washing Robot for Professional Users)

Reporting period: 2015-01-01 to 2015-12-31

Summary of the context and overall objectives of the project

Supermarkets, as well as other industrial, commercial and public use premises, such as airports, trade fairs and hospitals, have huge floor surfaces that have to be cleaned daily or even several times during the day. Cleaning those surfaces is time demanding and requires human effort, in terms of repetitive actions. Those cleaning activities take place at different times of the day, often with a tight schedule, depending on the area that has to be cleaned and on the available time slots. The economic viability of the cleaning service provider often relies on low wages and low-skilled personnel. Furthermore, cleaning tasks have often been related to workers’ health issues. Therefore, floor washing activities are best suited for robotization.
Currently, there exists no robot that satisfies the requirements of the professional users and cleaning service providers. Floor washing tasks have many demanding aspects, including operational autonomy, navigation precision, safety with regards to humans and goods, interaction with the human cleaning personnel, paths optimization, easy set-up and reprogramming.
FLOBOT addresses these problems by integrating existing and new results to produce a professional, robotic scrubber-dryer (floor washer with brushes and suction to dry the floor) for large areas. The system consists of a mobile robotic platform (the floor washing robot) and a docking station for automatically refilling the robot’s water tank, emptying the dirty water tank and recharging the battery. FLOBOT uses advanced software modules for navigation and mapping, human tracking for safety, floor cleanliness level estimation, mission programming and connection to the logistics management system of the end-users.
Project requirements come directly from the professional end-users. The work that will be carried out on production prototypes will ensure that the actual system is completed and ready for real-world use shortly after project completion. The robot and the whole concept will be validated in four different pilot sites: a large supermarket and a hospital in Italy, as well as in the Lyon airport and in a logistics warehouse in France.

Overall project objectives are summarised below:
• To develop an autonomous, robotised, professional washing machine for large premises, ready for real-world use shortly after project completion
• To develop FLOBOT as a robotic system that increases the quality of service and lowers the cost of operation, while preserving competitiveness and respecting workers’ rights and health, abiding to all related laws and regulations
• To integrate modular, low cost solutions for mapping, localisation, autonomous navigation, object detection and human tracking, building on existing research results and commercial know-how of the consortium partners
• To develop user interfaces for easy mission and tasks reprogramming, remote supervision and control of the robot
• To prove the usability and flexibility of the robot by testing it in four real-world use-case scenarios

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

One of the first project activities (WP2) has been the identification of the user requirements. A questionnaire was used to collect user requirements from the participating cleaning service providers and from the participating supermarket. Scrubber manufacturer requirements were also collected. A description of current practices has been made by the participating end-users, in order to understand how the FLOBOT could be integrated in the daily routine and which requirements derive from these practices. Requirements deriving from related standards and regulations were also studied. The FLOBOT design will be mainly affected by the recently published ISO 13482:2014 standard, which can be applied for certification, in absence of other specific standards. Additionally, regulatory requirements were also analysed in terms of privacy and data management issues.
Modularity requirements both in terms of hardware and software were also analysed. The FLOBOT higher-level system will be capable of activating different modules after having checked the sensory configuration. Through the same work package (WP2), the requirements for Human-Robot interaction and operational integration in professional cleaning services in sundry premises and work organisation settings were defined. The selected pilot sites were also analysed in detail. The pilot sites descriptions are important in order to understand the requirements for each Use Case and accordingly design the FLOBOT. Appropriate performance metrics, as well as corresponding testing procedures, have been prepared, to be used in the validation phase.
After defining all the aforementioned requirements, the preliminary, conceptual design of the FLOBOT was prepared, especially in terms of main dimensions, sensor requirements & positioning and preliminary pricing. The FLOBOT hardware is modular and thus the design and main requirements were presented on a module by module basis. Software preliminary design consisted in the definition of the approach to be followed for the software modules that will be developed. As the final task of WP2, the technical specifications for all FLOBOT hardware modules were prepared. Docking station technical specifications have also been produced. The specification document produced covers also the various software parts specifications.
In parallel to WP2 activities, issues related to safety, standards, risk analysis and future certification of the FLOBOT were also examined (WP3). Particular emphasis was paid to the analysis of the requirements coming from the ISO 13482:2014 standard. At the end of the second project month, requirements derived from standards and other regulations that can affect FLOBOT developments were used as an input in WP2, in order to prepare the system specifications. The analysis of the requirements is a continuous process and proceeds in parallel with the FLOBOT development. Essentially, the FLOBOT can be seen as made up of two parts: the robotics part and the conventional scrubber/dryer part. For the latter, the main reference is the IEC standard TC61/SC61J. For the robotics part, the main reference standard is the ISO 13482:2014. In the absence of other specific standards, this standard was chosen as the best applicable reference. The preliminary risk analysis performed allowed to identify risks related to the scrubber robotization. These are risks related either to hardware components specifications or to software functionalities and robustness.
Privacy and data management issues were also examined. For the field validations in France, authorisation will be asked to ADL (Airport administrator) and to the CNIL (independent authority that monitors data protection issues in France). For the validation sites in Italy, people will have to be informed through signs regarding their data collection. Authorisation will have to granted from the pilot site owner.
Significant progress has been achieved in terms of hardware design & development (WP4). As a first step, the position and size of all main components (sensors, actuators) that have to be integrated in the FLOBOT were defined. The necessary interfaces were also defined. In order to be able to evaluate the functionality of several sensors and decide about their use and position on the FLOBOT, a preliminary robot prototype was prepared. This consists in a remotely operated scrubber-dryer that integrates just the main mechanical, scrubber-related parts and does not have water tanks or other external components. This, so called Prototype Zero, was used for several tests by the robotisation partners. Based on the interfaces defined and on the sensors selected, the CAD design of the mobile platform and the docking station was prepared. It was decided that, at least as a first step, the first prototype will be made using metal sheets and not plastic parts, in order to allow easy sensor re-configuration.
In terms of software development (WP5), all modules are progressing as planned. The navigation and mapping module functionality will be based both on a 3D Lidar and on conventional odometry. Additional sensors are used for safety and obstacle avoidance, following regulatory requirements. The 3D Lidar, combined with an RGB-D camera is also used by the human tracking module. Visual floor inspection (for cleanliness) is based on data, gathered either by the RGBD-camera or the Stereo setup. Particular attention during this first period has been paid to the development of the user interface on the tablet. Major screens have been defined, as well as the functionalities of the tablet application. A mock-up has been shared with the partners for receiving feedback. Regarding the proactive safety module, a preliminary design has been prepared and components are currently being tested in the lab. The development of the software module responsible for interfacing to the ERP has also progressed. A preliminary interface is available, as well as several back-end modules.
FLOBOT has also been quite active in terms of dissemination activities (WP8). It has been presented in several events, including the IROS conference. Information about the project was published in several newspapers and magazines. The project website and social accounts are regularly updated.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

The project’s main result will be an autonomous, robotised, professional scrubber-dryer for large premises. The project answers the need of the cleaning industry for robotic scrubber that can operate unattended for a long period of time. Progress beyond the state of the art is expected in several aspects.
Regarding localisation and mapping, the technique used is SLAM (Simultaneous Localization And Mapping). In FLOBOT, SLAM is based on the use of data from a 3D Lidar, as well as on data from an odometry subsystem. Several modules were already available in the consortium before the start of the project, but the use of the 3D Lidar is a new approach for robots of this type. Additional sensors are used for obstacle avoidance and safety purposes.
Regarding navigation and path planning, FLOBOT adopts an approach considering a default, optimal, pre-planned path to follow, but still maintaining the flexibility to modify the planned trajectory in case an unexpected obstacle appears. Additionally, when an object recurrently appears on the available map, the FLOBOT will consider adding is as a permanent obstacle in the map, after requesting user confirmation. The same applies to obstacles that seem to not be present anymore.
Regarding image analysis for floor cleanliness detection, very little literature exists. Thus, the project is aiming at an advancement in the state of the art by using the approach described by Bormann et al. in 2013, adapted to the FLOBOT case. Two RGB-D cameras are being used for this purpose. Additionally, regarding object detection on the floor, it is planned to implement a basic plane detection and height based object detection algorithm. Optionally we plan to advance the basic approach with a more experimental algorithm that simultaneously segments and reconstructs the area of operation. This technique is still not applied in industrial prototypes.
Regarding human tracking for safety, FLOBOT will exploit data collected using the 3D Lidar and an RGB-D camera. The system will be able to detect animate objects and provide a classification appropriate to the task. FLOBOT’s human tracking module will be capable of detecting and tracking multiple people. Safety during FLOBOT operation within a complex environment with humans is of primary importance. The solution proposed is the projection of warning signs on floors in an intuitive way, by controlling the position of these signs to be on specific position of high risk such as corridor junctions etc. To our knowledge, there are no such technologies currently used in robots for industrial purposes.
FLOBOT is expected to have significant impact on labour aspects of the cleaning industry. Currently, professional cleaning is a hard labour, low skills job, where competitiveness and profit margin are at the expense of the workers’ conditions. Additionally, about 74% of the people employed in the sector are women and there are difficulties in the recruitment of new personnel. With the adoption of FLOBOT, the worker’s role will evolve from low skills to that of an expert user and maintenance operator of robotic machines. At the same time, the robot will relief the physically weaker workers, such as women, from part of the hard labour. The same applies for the ageing working population.
FLOBOT is also expected to support the European industry producing professional cleaning floor machines, that has to deal with the highly competitive Asian and American companies. The consortium end-users are large companies that, with the adoption of the FLOBOT, will allow the FLOBOT manufacturer to cover an important market share.
Furthermore, FLOBOT has already had a great impact in terms of Industry-Academia cross-fertilisation. Important modules of the robot are based on research produced within the participating universities. Additionally, the universities are having the chance of applying their research on real products in an industrial environment.

Related information

Record Number: 190020 / Last updated on: 2016-11-03
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top