Keynote Lectures

Abstract
Robotic agents that can accomplish manipulation tasks with the competence of humans have been one of the grand research challenges for artificial intelligence (AI) and robotics research for more than 50 years. However, while the fields made huge progress over the years, this ultimate goal is still out of reach. I believe that this is the case because the knowledge representation and reasoning methods that have been proposed in AI so far are necessary but too abstract. In this talk I propose to address this problem by endowing robots with the capability to internally emulate and simulate their perception-action loops based on realistic images and faithful physics simulations, which are made machine-understandable by casting them as virtual symbolic knowledge bases. These capabilities allow robots to generate huge collections of machine-understandable manipulation experiences, which robotic agents can generalize into commonsense and intuitive physics knowledge applicable to open varieties of manipulation tasks. The combination of learning, representation, and reasoning will equip robots with an understanding of the relation between their motions and the physical effects they cause at an unprecedented level of realism, depth, and breadth, and enable them to master human-scale manipulation tasks. This breakthrough will be achievable by combining leading-edge simulation and visual rendering technologies with mechanisms to semantically interpret and introspect internal simulation data structures and processes. Robots with such manipulation capabilities can help us to better deal with important societal, humanitarian, and economic challenges of our aging societies.

Abstract
“Automation is a fundamental part of industry and our private lives. At Festo, our vision is to free humans from harming tasks – these might be mentally (by being boring and repetitive) or even physically harming. Today, one aspect of an automation solution is that it is engineered to a specific problem and environment and often does not interact actively with humans. For humans to naturally interact with machines, it is needed that the machines can react to changing tasks and environments. Here, AI-based solutions come into play and offer a solution. Mechanisms inspired by biology offer efficient solutions to many questions arising in this field. This keynote will show concrete challenges from within the industrial automation and the solutions Festo research came up with.”

Abstract
In this talk, I will present our work toward building Socially Interactive Agent SIA, that is agent able to be socially aware, interact with human partners, but also adapt its behaviors to favor user’s engagement during the interaction.
During an interaction, partners adapt their behaviors to each other. Adaptation can happen at different levels, such as at the linguistic one (choice of vocabulary, grammatical style), the behavior one (change of posture), etc. It can involve the choice of a given conversational strategy to manage user’s impression, or synchronization mechanisms (eg imitate a smile)… Lately we have developed three adaptation mechanisms that work on different levels: conversational strategy, nonverbal behaviors and multimodal signals. I will present the general framework on which these models have been built. As it interacts with a human partner, the agent learns to adapt to maximize the quality of the interaction. These models have been evaluated through a study involving visitors of a science museum. I will discuss the results of these studies.
Touch is a modality that is not much considered in human-agent interaction. Social touch bares many functions during an interaction. A caress can convey comfort, a tap human’s attention, etc. We have been working on endowing an agent to respond to social touch by a human and to touch the human to convey different intentions and emotions. I will describe the decision model based on the emotional model FAtiMA we have developed.