Research proposals for 2020 announced
Artificial Intelligence and Multi-Agent Systems Laboratory
The Laboratory of Artificial Intelligence and Multi-Agent Systems (AI-MAS) is part of the Computer Science Department, Faculty of Automatic Control and Computers in University POLITEHNICA of Bucharest.
Our research is focused on models and architectures of intelligent agents and multi-agent systems, ambient intelligence tools and environments, context-aware computing, machine learning algorithms, applications of social and assistive robotics, and swarm intelligence.
In 2018 we start a new direction of research devoted to autonomous driving by developing vision and path planning modules for an electric car (Dacia).
We believe that AI models and technologies can improve users’ experience and systems’ performance in a plethora of domains, such as distributed systems, big data, learning platforms, web services, e-business, assisted living, and applications in general.
We investigate issues related to coordination mechanisms, automated negotiation and voting methods in multi-agent systems, agent learning, affective agents, swarm formation and coordination of our own robotic swarm.
In the field of Ambient Intelligence, we work for developing tools and agent-based software for user activity support, posture recognition, human activity recognition, and we build applications for Active and Assisted Living to offer a better and user friendly environment for people with special needs. We also develop context aware models and techniques for empowering Ambient Intelligence applications.
We use computer vision and planning techniques to develop specialized software for social robots that interact with people and other physical robots, and are able to interpret people’s action and respond appropriately. We also develop software for assistive robots that are able to insure multi-modal interaction and perform actions for the well-being of people with disabilities and seniors, thus integrating these robots in our Active and Assisted Living applications.
We are studying different models of deep neural networks and deep reinforcement learning for recognition and tracking tasks, and for the coordination of autonomous agents.
Recently, we have started an exciting project devoted to autonomous driving and driver support. We are partnering with Prime Motors and their electric cars to develop several modules for vision, autonomous navigation, and simulation of driver’s behavior.