Autonomous systems are becoming increasingly important when it comes to tasks that are either too dangerous, too difficult or too monotonous for people. The systems react to events in their environment and make an appropriate decision; they perceive, learn, think and act confidently and react intelligently to unforeseen changes in the environment.
Autonomous systems also offer great potential for collaborative robotics. For example, based on training and experience they can predict what the worker will do next and control their movements accordingly. This ability to predict movement makes cooperation safer and more efficient.
If an autonomous robot knows the required finished state, it can also use appropriate artificial intelligence (AI) algorithms to decide on all the work steps that are needed to solve the task itself. In addition to reinforcement learning, we also use bio-inspired AI. This efficient and specialised AI is inspired by the intelligence of ants, bees and other insects.
To enable these and other intelligent robot capabilities such as packing boxes or estimating weight, the AI can be taught using virtually generated data sets. Sim2Real Learning – learning during simulations or using hybrid systems and transferring what has been learned to the real robot – is also used.