The main goal of the EXPECT project is the development of an adaptive, self-learning platform for human-robot collaboration that not only enables various types of active interaction, but is also capable of inferring human intention from multimodal data (gestures, speech, eye movements, and brain activity). In the project, methods for automated labeling and joint evaluation of multimodal human data will be developed and evaluated in test scenarios. The systematic experiments also serve to investigate the question of how fundamentally significant brain data is for intention prediction in humans. Thus, EXPECT has a direct positive impact on the increased collaboration between humans and robots in the working world. The technologies to be developed in EXPECT can be used in many ways, for example in space travel and extraterrestrial exploration, robot-assisted rehabilitation and assistance as well as in industrial MRI.