Technische Universität Berlin
DAI-Labor
This chapter focuses on emotion and intention engineering by socially interacting robots that induce desired emotions/intentions in humans. The authors provide all phases that pave this road, supported by overviews of leading works in the... more
This chapter focuses on emotion and intention engineering by socially interacting robots that induce desired emotions/intentions in humans. The authors provide all phases that pave this road, supported by overviews of leading works in the literature. The chapter is partitioned into intention estimation, human body-mood detection through external-focused attention, path planning through mood induction and reshaping intention. Moreover, the authors present their novel concept, with implementation, of reshaping current human intention into a desired one, using contextual motions of mobile robots. Current human intention has to be deviated towards the new desired one by destabilizing the obstinance of human intention, inducing positive mood and making the “robot gain curiosity of human”. Deviations are generated as sequences of transient intentions tracing intention trajectories. The authors use elastic networks to generate, in two modes of body mood: “confident” and “suspicious”, transient intentions directed towards the desired one, choosing among intentional robot moves previously learned by HMM.
This paper focuses on reshaping a previously detected human intention into a desired one, using contextual motions of mobile robots, which are in our applications, autonomous mobile 2-steps stairs and a chair. Our system first estimates... more
This paper focuses on reshaping a previously detected human intention into a desired one, using contextual motions of mobile robots, which are in our applications, autonomous mobile 2-steps stairs and a chair. Our system first estimates the current intention based on human heading and trajectory depicted as orientation and location. Our previous reshaping applications have shown that the current human intention has to be deviated towards the new desired one in phases. In our novel approach, Elastic network generates way points of trajectories each of which acts as transient trajectories directed towards the desired intention's location. Our methodology aims at generating an “intention trajectory” towards the final goal. The initial way points possess destabilizing effects on the obstinance of the person intention making the “robot gain the curiosity and the trust of the person”. Each way point generated by the elastic network is executed by moves of an adequate robot (here mobile 2-steps or chair) in adequate directions (towards coffee table, PC, TV, library). After each robot moves, the resulting human intention is estimated and compared to the desired goal in the intention space. Intention trajectories are searched in two modes: the “confident mode” and the “suspicious mode” which are defining human body-mood detected relying on proxemics. This paper analyzes our novel approach of planning trajectories via elastic networks based on these two modes.
Recent studies show that robots are still far from being long-term companions in our daily lives. With an interdisciplinary approach, this position paper structures around coping with this problem and suggests guidelines on how to develop... more
Recent studies show that robots are still far from being long-term companions in our daily lives. With an interdisciplinary approach, this position paper structures around coping with this problem and suggests guidelines on how to develop a cognitive architecture for social robots assuring their long-term personal assistance at home. Following the guidelines, we offer a conceptual cognitive architecture enabling assistant robots to autonomously create cognitive representations of cared-for individuals. Our proposed architecture places Theory of Mind approach in a metacognitive process first to empathize and learn with humans, then to guide robot's high-level decision-making accordingly. These decisions evaluate, regulate and control robot's cognitive process towards understanding, validating and caring for interacted humans and serving them in a personalized way. Hence, robots deploying this architecture will be trustworthy, flexible and generic to any human type and needs; in the end, they will establish a secure attachment with interacted humans. Finally, we present a use-case for our novel cognitive architecture to better visualize our conceptual work.
— We propose an architecture that integrates Theory of Mind into a robot's decision-making to infer a human's intention and adapt to it. The architecture implements human-robot collaborative decision-making for a robot incorporating human... more
— We propose an architecture that integrates Theory of Mind into a robot's decision-making to infer a human's intention and adapt to it. The architecture implements human-robot collaborative decision-making for a robot incorporating human variability in their emotional and intentional states. This research first implements a mechanism for stochastically estimating a human's belief over the state of the actions that the human could possibly be executing. Then, we integrate this information into a novel stochastic human-robot shared planner that models the human's preferred plan. Our contribution lies in the ability of our model to handle the conditions: 1) when the human's intention is estimated incorrectly and the true intention may be unknown to the robot, and 2) when the human's intention is estimated correctly but the human doesn't want the robot's assistance in the given context. A robot integrating this model into its decision-making process would better understand a human's need for assistance and therefore adapt to behave less intrusively and more reasonably in assisting its human companion.
We propose an architecture as a robot's decision-making mechanism to anticipate a human's state of mind, and so plan accordingly during a human-robot collaboration task. At the core of the architecture lies a novel stochastic... more
We propose an architecture as a robot's decision-making mechanism to anticipate a human's state of mind, and so plan accordingly during a human-robot collaboration task. At the core of the architecture lies a novel stochastic decision-making mechanism that implements a partially observable Markov decision process anticipating a human's state of mind in two-stages. In the first stage it anticipates the human's task related availability, intent (motivation), and capability during the collaboration. In the second, it further reasons about these states to anticipate the human's true need for help. Our contribution lies in the ability of our model to handle these unexpected conditions: 1) when the human's intention is estimated to be irrelevant to the assigned task and may be unknown to the robot, e.g., motivation is lost, another assignment is received, onset of tiredness, and 2) when the human's intention is relevant but the human doesn't want the robot's assistance in the given context, e.g., because of the human's changing emotional states or the human's task-relevant distrust for the robot. Our results show that integrating this model into a robot's decision-making process increases the efficiency and naturalness of the collaboration.
As a key component of collaborative robots (cobots) working with humans, existing decision-making approaches try to model the uncertainty in human behaviors as latent variables. However, as more possible contingencies are covered by such... more
As a key component of collaborative robots (cobots) working with humans, existing decision-making approaches try to model the uncertainty in human behaviors as latent variables. However, as more possible contingencies are covered by such intention-aware models , they face slow convergence times and less accurate responses. For this purpose, we present a novel anticipatory policy selection mechanism built on existing intention-aware models, where a robot is required to choose from an existing set of policies based on an estimate of the human. Each of these intention-aware robot models anticipates and adapts to a different human's short-term changing behaviors. Our contribution is the Anticipatory Bayesian Policy Selection (ABPS) mechanism which selects from a library of different response policies that are generated from such models, and converges to a reliable policy after as few interactions as possible when faced with unknown humans. The selection is based on the estimation of the human in terms of long-term workplace characteristics that we call types, such as level of expertise, stamina, attention and collaborativeness. Our results show that incorporating this policy selection mechanism contributes positively to the efficiency and naturalness of the collaboration, when compared to the best intention-aware model in hindsight running alone.