BIMROB: Bidirectional Interaction between huMan and Robot for the learning of movements

The overlap between the workspaces of humans and robots has been increasing in the last decades. Situations in which people interact with robots are becoming more frequent. Such situations pose a number of research questions, such as:

1. How can humans and robots learn the execution of movements together or from each other?
2. What is the best way to combine the advantages of humans and robots?

The main focus of the BIMROB project is the scientific investigation of the interaction between humans and robots when learning movements. Efficient and effective interaction configurations will be determined in order to allow humans and robots to acquire new movements or improve their performance at certain tasks that involve their sensorial and motor capabilities.

The search for configurations that allow humans and robots to jointly learn movements may result in a large number of applications: industrial robots may be retrained through the physical interaction with humans, instead of through the rewriting of lines of code; new devices and training programs for the rehabilitation of motor impaired patients may be designed.

BIMROB will comprise four work packages. The investigation of the joint acquisition/improvement of movements by humans and robots will be developed in the scenario of learning to putt a golf ball. Each of the work packages corresponds to a type of interaction:

1. A human learns a movement from another human.
2. A robot learns a movement from a human.
3. A human learns a movement from a robot.
4. A human and a robot learn a movement together.

We hope that the results will become important for applications ranging from sport training devices to rehabilitation.

BIMROB is funded by the Forum for Interdisciplinary Research (FiF) at the Technische Universität Darmstadt.