Accelerating the Development of Multimodal, Integrative-AI Systems with Platform for Situated Intelligence
This framework addresses the challenge of building timing-sensitive, multimodal AI systems for researchers and developers in human-robot interaction and related fields, though it appears incremental as it builds on existing infrastructure concepts.
The paper introduces Platform for Situated Intelligence, an open-source framework designed to accelerate the development of multimodal, integrative-AI systems that process data streams with critical timing, particularly for physically situated interactive applications like social robots and virtual assistants.
We describe Platform for Situated Intelligence, an open-source framework for multimodal, integrative-AI systems. The framework provides infrastructure, tools, and components that enable and accelerate the development of applications that process multimodal streams of data and in which timing is critical. The framework is particularly well-suited for developing physically situated interactive systems that perceive and reason about their surroundings in order to better interact with people, such as social robots, virtual assistants, smart meeting rooms, etc. In this paper, we provide a brief, high-level overview of the framework and its main affordances, and discuss its implications for HRI.