The future trends in robotics are many and diverse. Their common goals are to make applications more efficient and autonomous. Robots should further relieve the burden on humans and at the same time be even easier to set up and operate.
What's next? – An overview of the future topics in robotics:
The trend is toward programming operations that do not require expert knowledge. This is because setting up a new system or adapting an existing one is still too time-consuming for many companies, especially where small batch sizes are concerned. We develop processes that enable programming by demonstration or by intuitive software, for example, so that programming efforts are reduced.
When humans and machines work together in a workspace, it is essential that the application is safe and complies with standards. We are working on facilitating the setup of such workplaces and providing partially automated support. At the same time, we keep an eye on the economic efficiency of an HRC application and advise companies on their individual requirements.
Research into innovative body-mounted mechatronic systems in the fields of industry, medical technology, rehabilitation, and crafts is another of our focal points and serves to maintain, restore, or increase human mobility.
In both the industry and service sector, mobile robotics enables situation-specific machine support. It is a key technology for flexible logistics. Challenges here are environments with moving and unknown objects, which must be considered in dynamic motion planning and execution. Mobile manipulators, i.e. industrial robot arms on mobile platforms, once again offer completely new application possibilities and are slowly penetrating the market.
Open source frameworks such as ROS (Robot Operating System) now offer many basic but complex software components. In research, open source software is already established and the demand from industry is also constantly increasing. In the future, the use of open source software is likely to become a decisive competitive and innovation factor.
With the methods of machine learning and deep learning, artificial intelligence provides more autonomy for robots. They can set themselves up in perspective, react independently to deviations or tolerances in processes, and learn based on the underlying data. Simulations help to efficiently generate the required data sets and accelerate the setup of the real system.
When systems exchange information with each other, a kind of collective intelligence emerges. In the navigation of automated guided vehicles (AGVs), for example, this means that the knowledge of the individual vehicles flows into a shared, centrally available map. If one vehicle detects an obstacle on the route, all other vehicles already know about it thanks to the shared map and plan an alternative route without having seen the obstacle themselves. Networked AGVs thus offer optimized traffic flow.