Talk by Jawad Nagi, IDSIA, March 23rd, 11:00 RLC D1 661

© 2015 EPFL

© 2015 EPFL

Human-Swarm Interaction and Cooperation

Comprising of a potentially large team of autonomous cooperative robots locally interacting and communicating with each other, swarm robots provide a natural diversity of parallel and distributed functionalities, high flexibility, intrinsic redundancy and fault-tolerance.
This suggests that robot swarms are good candidates to support interaction with humans. As the use of autonomous mobile robots is expected to increase in the future, swarm robots are envisioned to play important roles in search and rescue missions, ambient assisted living, distributed surveillance and reconnaissance operations.

The evolution of interactions between humans and robot swarms has reached a stage where swarms can robustly be deployed. However, fundamental problems in the relatively new field of human-swarm interaction (HSI) need to be addressed. The main objective of this research is to develop an intelligent automated interaction system that allows dialogue-based interaction and cooperation between humans and robotic swarms, while providing the capabilities of bidirectional communication using multiple modalities.

Ultimately, the goal is develop HSI technologies to address swarm-level and human-in-the-loop challenges and other open problems, which include: distributed sensing, autonomous deployment, decentralized data fusion, cooperative recognition and decision-making, information selection and sharing, and cooperative distributed learning. The effectiveness of the proposed system is demonstrated in the context of human assistance-based scenarios.