The main focus of the research within WASP is artificial intelligence and autonomous systems acting in collaboration with humans. At KTH, a large number of research projects are currently underway within the WASP programme. This page describes only a selection of the ongoing WASP projects at KTH.
NEST Environments
WASP supports nine multidisciplinary world-leading research environments and networks characterized by Novelty, Excellence, Synergy, and Team – NEST. Six of them are coordinated by KTH researchers. The NESTs were awarded funding through a call in 2021.
DISCOWER – Distributed Control in Weightless Environments
Photo: Jeremy Thomas / Unsplash
Space and subsea environments are one of the most challenging among the emerging fields of autonomous systems. One of the key challenges encompassing both environments is the unconventional weight conditions that need to be tackled when dealing with robot operations’ design. The lack of gravity in space and buoyancy underwater leads to significant challenges when it comes to traditional and otherwise well-studied robotics’ features, such as navigation, manipulation, control, or safe human-robot interaction. This project aims at filling the gap in the state-of-the-art on trans-environmental multi-robot control and planning.
STING – Synthesis and Analysis with Transducers and Invertible Neural Generators
Photo: Markus Spiske / Unsplash
Humans communication is rich and varied, drawing on abstract concepts, grammatical rules, speech melody, facial expressions and body gestures to convey meaning. This project aims to develop a unified machine-learning framework that accounts for the entire range of modalities, and that works equally well for analysing and generating human communication. This brings together theory and methods from here-to separate research fields, and creates new opportunities for detecting and managing bias.
PerCorSo – Designing appropriate ways for robots to behave in human-crowded environments
Photo: Jacek Dylag / Unsplash
Autonomous robots of all kinds have been increasingly finding their way to our daily lives: think of autonomous vehicles, delivery drones, as well as service robots deployed in the healthcare domain. Not only are they complex, regarding the technology they embed, but also regarding the tasks they must complete and requirements they must meet. PerCorSo aims to design autonomous behaviors of interacting robots that are not only guaranteed to be safe but are also perceived as safe and accepted by people.
Learning in Networks: Structure, Dynamics, and Control
Photo: Conny Schneider / Unsplash
Many complex systems, whether biological, physical, social, or economical, are structured in networks consisting of a large collection of interacting entities. Some of these networks, such as social networks on the Internet emerge without our control or intervention. As a consequence, their structure, the way their entities interact and evolve are unknown. In this project, we will develop novel mathematical and computational tools to devise efficient algorithms learning the network structure and dynamics, as well as efficient ways to control it.
The current AI revolution is driven by our ability to collect, store and process huge amounts of data. However, even the most recent generation of computing systems is struggling to keep up with the continuously increasing data volumes. Data bound computing aims at developing the principles behind the next generation of computing systems, optimized for modern data-intensive workloads.