Skip to main content
European Commission logo print header

Safe human-robot interaction in logistic applications for highly flexible warehouses

Periodic Reporting for period 3 - SafeLog (Safe human-robot interaction in logistic applications for highly flexible warehouses)

Reporting period: 2019-01-01 to 2020-12-31

The European market for e-commerce is growing rapidly, thus the need for larger warehouses and distribution centers increases. In such facilities goods for the end-users or products in the B2B sector are stored, commissioned and shipped. In logistics, the concept of full automation is not desirable or even feasible. Thus the vision of "Warehouse Co-workers" becomes more and more important to advance automation as an assistant system to the human worker. So what did we aim to overcome with this project? In short: Provide the technology to allow safe human-robot interaction or coexistence in warehouses.

The typical way robotized warehouses are organized is the strict separation of humans and robots by fences or other safety measurements like safety light curtains, which – when detecting a human shut down big parts or even the whole warehouse system. In SafeLog we tried to overcome this issue by enabling humans to safely enter the area where the robots are working, without the need to stop the whole warehouse. This opens up new opportunities, e.g. allowing service technicians to enter the area without interrupting the warehouse system, therefore much less downtime. Another use case would be to allow the handling of prioritized tasks by humans, e.g. humans can collect priority orders in parallel to the standard orders executed by the robots.

Therefore the overall objectives of SafeLog were the conception and implementation of a large-scale flexible warehouse system which enables a safe and efficient collaboration of human and robots in the same area at the same time. This included:

1. Safety concept: Design of a holistic safety concept, which allows the collaboration of humans for a flexible warehouse system.
2. Safety vest: Hard- and software design for a new kind of safety vest.
3. Planning and scheduling: Development of planning and scheduling algorithms for a heterogeneous fleet manager.
4. Assisting technologies: AR based interaction strategies to support workers in a robotised warehouse system.
5. Assessment and integration: Integration and Assessment of Use-cases and Scenarios.
6. Dissemination and information: The proposed concept requires a strong dissemination and information concept to inform warehouse-operating companies.
So what makes our approach particularly innovative? We’ve tried to look at this in a holistic way right from the start. First and most important, we developed a certifiable safety concept and a new safety technology to detect whether a robot comes close to a human and if so, will slow down or even stop the robot and only this robot. Moreover, this technology is much cheaper than the very expansive strategy to equip all robots with safety laser scanners. Second, we developed concepts and planning algorithm to manage and orchestrate a heterogeneous team consisting of humans and robots sharing the warehouse floors. As robots typically stay on their given paths, humans – in contrast – can deviate and choose to take another route than originally planned. This has to be detected and the rest of the warehouse - or at least all robots nearby - has to react accordingly. In SafeLog we investigated centralized and decentralized strategies. Finally, we can basically organize, replan and orchestrate around 1000 robots with humans. And third, as humans get orders to fetch and collect certain goods in the warehouse, they have to be guided to this location. In SafeLog this is done by using Augmented Reality (AR). The person in the warehouse is carrying an AR-Device and the path to his destination and other information are shown in that AR-Device. This makes it pretty intuitive to navigate in the warehouse and to pick up the right goods. The same idea is used to support service technicians. Via AR they get information about the current robot they are looking at, error message, etc.

To support the visibility of SafeLog a web site was launched ( and continuously updated with news, publications, test sets etc. A flyer, a roll-up and posters were designed. About 65 result presentations at conferences, workshops and other events have been done as well as 5 workshops (co-)organised. A highlight was the participation in the IROS 2018 with a project booth and a large demonstration of the project concept and prototypes. A total of 9 press articles were published addressing the general public to create awareness of the European Funding of SafeLog in addition to a total of 53 scientific publications published since project start.
With a total of 53 scientific publications, SafeLog has already significantly contributed to the current state of the art in human intention estimation, localisation, AR-based interaction, human-robot interaction, planning of heterogeneous fleets, centralized and decentralized concepts for managing robot fleets.

So what are the main outcomes and achievements of the project? In principle, we can state that we successfully addressed all originally envisioned objectives. Therefore the main achievements are the three technologies mentioned above. Safety concept and technology for human-robot-interaction, planning and orchestrating of a heterogeneous warehouse with human and robots working together and AR-based interaction technologies for supporting humans working in a robotizes warehouse. But one special task of SafeLog definitely worth emphasizing was, that from the beginning the safety concept and the design of the safety hardware was accompanied by the certification body TÜV Nord. So, everything was developed with the idea of certification in mind, which at the current status - then will be achievable short after projects end. Based on these outcomes, SafeLog impacts following topics:

1.) Enhance safe interaction between humans and mobile robots by introducing a new affordable and certifiable technology.
2.) Ubiquitous localization of humans and mobile robots, managing systems with over 1000 units.
3.) Reduction of system wide downtimes with a granular approach stopping only robots near the human in combination with fast replanning of the optimal schedule of impacted robots.
4.) Significantly reduction in installation costs in comparable human-robot collaborative workspaces.
5.) Impact on the European logistic market, and especially introducing a new concept of cooperation between automation and humans in logistics: This impact is covered by the contributions 3.) and 4.)

We think that the future of efficient production, of flexible logistic applications and other upcoming robotized/automated application scenarios lie – even in a high automated environment – in a safe and effective human-robot cooperation and coexistence. SafeLog is addressing these issues directly. So, the long-term prospects of the project results seem very promising. Especially as the SafeLog technologies are not necessarily tied to warehouses. There are multiple areas in production, transport, construction or healthcare sector, which would benefit from the technologies developed in SafeLog.
SafeLog Concept