Automatic selection of coordinate systems for learning relative and absolute spatial concepts

Robots employed in homes and offices need to adaptively learn spatial concepts using user utterances. To learn and represent spatial concepts, the robot must estimate the coordinate system used by humans. For example, to represent spatial concept “left,” which is one of the relative spatial concepts (defined as a spatial concept depending on the object’s location), humans use a coordinate system based on the direction of a reference object. As another example, to represent spatial concept “living room,” which is one of the absolute spatial concepts (defined as a spatial concept that does not depend on the object’s location), humans use a coordinate system where a point on a map constitutes the origin. Because humans use these concepts in daily life, it is important for the robot to understand the spatial concepts in different coordinate systems. However, it is difficult for robots to learn these spatial concepts because humans do not clarify the coordinate system. Therefore, we propose a method (RASCAM) that enables a robot to simultaneously estimate the coordinate system and spatial concept. The proposed method is based on ReSCAM+O, which is a learning method for relative spatial concepts based on a probabilistic model. The proposed method introduces a latent variable that represents a coordinate system for simultaneous learning. This method can simultaneously estimate three types of unspecified information: coordinate systems, reference objects, and the relationship between concepts and words. No other method can estimate all these three types. Experiments using three different coordinate systems demonstrate that the proposed method can learn both relative and absolute spatial concepts while accurately selecting the coordinate system. The proposed approach can be beneficial for service robots to flexibly understand a new environment through the interactions with humans.

Learning Actions From Natural Language Instructions Using an ON-World Embodied Cognitive Architecture

Endowing robots with the ability to view the world the way humans do, to understand natural language and to learn novel semantic meanings when they are deployed in the physical world, is a compelling problem. Another significant aspect is linking language to action, in particular, utterances involving abstract words, in artificial agents. In this work, we propose a novel methodology, using a brain-inspired architecture, to model an appropriate mapping of language with the percept and internal motor representation in humanoid robots. This research presents the first robotic instantiation of a complex architecture based on the Baddeley's Working Memory (WM) model. Our proposed method grants a scalable knowledge representation of verbal and non-verbal signals in the cognitive architecture, which supports incremental open-ended learning. Human spoken utterances about the workspace and the task are combined with the internal knowledge map of the robot to achieve task accomplishment goals. We train the robot to understand instructions involving higher-order (abstract) linguistic concepts of developmental complexity, which cannot be directly hooked in the physical world and are not pre-defined in the robot's static self-representation. Our proposed interactive learning method grants flexible run-time acquisition of novel linguistic forms and real-world information, without training the cognitive model anew. Hence, the robot can adapt to new workspaces that include novel objects and task outcomes. We assess the potential of the proposed methodology in verification experiments with a humanoid robot. The obtained results suggest robust capabilities of the model to link language bi-directionally with the physical environment and solve a variety of manipulation tasks, starting with limited knowledge and gradually learning from the run-time interaction with the tutor, past the pre-trained stage.

Robots Learning to Say “No”

“No” is one of the first ten words used by children and embodies the first form of linguistic negation. Despite its early occurrence, the details of its acquisition remain largely unknown. The circumstance that “no” cannot be construed as a label for perceptible objects or events puts it outside the scope of most modern accounts of language acquisition. Moreover, most symbol grounding architectures will struggle to ground the word due to its non-referential character. The presented work extends symbol grounding to encompass affect and motivation. In a study involving the child-like robot iCub, we attempt to illuminate the acquisition process of negation words. The robot is deployed in speech-wise unconstrained interaction with participants acting as its language teachers. The results corroborate the hypothesis that affect or volition plays a pivotal role in the acquisition process. Negation words are prosodically salient within prohibitive utterances and negative intent interpretations such that they can be easily isolated from the teacher’s speech signal. These words subsequently may be grounded in negative affective states. However, observations of the nature of prohibition and the temporal relationships between its linguistic and extra-linguistic components raise questions over the suitability of Hebbian-type algorithms for certain types of language grounding.