Intention Recognition for Real-time Automotive 3D situation awareness

Intention recognition is the task of inferring an agent's intention based on its previous actions. It is crucial for human social intelligence which in turn enables understanding of, and the ability to predict, other humans' behaviours, such as for example other drivers' intent to overtake, stop, turn, or switch lanes. For making situation-based decisions, both autonomous and human drivers need to take the intentions of surrounding vehicles into account. This is especially true in a mix of autonomous and human drivers.

Existing algorithms and models for intention recognition need to be improved with respect to accuracy, robustness, transparency, and scalability, in order to meet the requirements of the Swedish automotive industry. It is an open research question how to meet these requirements. This lack of knowledge is a bottleneck for the automotive industry prohibiting the creation of novel advanced and intelligent automotive services and products based on social intelligence and intention recognition.

The overarching goal of the project is knowledge transfer to industry of novel algorithms and models for intention recognition and about their interdependencies with available industrial data and needs, on a level sufficient for enabling ensuing commercial exploitation of the project results. To achieve this, the project will develop new algorithms for intention recognition specifically aimed for the Swedish automotive industry, based on current state-of-the-art in intention recognition and automated reasoning, as well as in statistical learning and sensor technology.