In many robotic applications, especially those involving humans and the environment, linguistic and visual information must be processed jointly and bound together. Existing works either encode the image or the language into a subsymbolic space, like the CLIP model, or create a symbolic space of extracted information, like the object detection models. In this paper, we propose to describe images by nouns and modifiers and introduce a new embedded binding space where the linguistic and visual cues can effectively be bound. We investigate how state-of-the-art models perform in recognizing nouns and modifiers from images, and propose our method by introducing a dataset and CLIP-like recognition techniques based on transfer learning and metric learning. We show real-world experiments that demonstrate the practical applicability of our approach to robotics applications. Our results indicate that our method can surpass the state-of-the-art in recognizing nouns and modifiers from images. Interestingly, our method exhibits a language characteristic related to context sensitivity.

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.

Autonomous agents embedded in a physical environment need the ability to correctly perceive the state of the environment from sensory data. In partially observable environments, certain properties can be perceived only in specific situations and from certain viewpoints that can be reached by the agent by planning and executing actions. For instance, to understand whether a cup is full of coffee, an agent, equipped with a camera, needs to turn on the light and look at the cup from the top. When the proper situations to perceive the desired properties are unknown, an agent needs to learn them and plan to get in such situations. In this paper, we devise a general method to solve this problem by evaluating the confidence of a neural network online and by using symbolic planning. We experimentally evaluate the proposed approach on several synthetic datasets, and show the feasibility of our approach in a real-world scenario that involves noisy perceptions and noisy actions on a real robot.