Related papers: Map Induction: Compositional spatial submap learni…

Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research. Existing methods often focus on state-based metrics, which do not consider the underlying causal structures of…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Discovering symbolic representations for skills is essential for abstract reasoning and efficient planning in robotics. Previous neuro-symbolic robotic studies mostly focused on discovering perceptual symbolic categories given a pre-defined…

In robot navigation, generalizing quickly to unseen environments is essential. Hierarchical methods inspired by human navigation have been proposed, typically consisting of a high-level landmark proposer and a low-level controller. However,…

Robots are often required to operate in environments where humans are not present, but yet require the human context information for better human-robot interaction. Even when humans are present in the environment, detecting their presence…

We address the problem of autonomous exploration and mapping for a mobile robot using visual inputs. Exploration and mapping is a well-known and key problem in robotics, the goal of which is to enable a robot to explore a new environment…

Active inference, a neurally-inspired model for inferring actions based on the free energy principle (FEP), has been proposed as a unifying framework for understanding perception, action, and learning in the brain. Active inference has…

A comprehensive artificial intelligence system needs to not only perceive the environment with different `senses' (e.g., seeing and hearing) but also infer the world's conditional (or even causal) relations and corresponding uncertainty.…

Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…

Typical models of learning assume incremental estimation of continuously-varying decision variables like expected rewards. However, this class of models fails to capture more idiosyncratic, discrete heuristics and strategies that people and…

It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around:…

Effective robotic autonomy in unknown environments demands proactive exploration and precise understanding of both geometry and semantics. In this paper, we propose ActiveSGM, an active semantic mapping framework designed to predict the…

Recently, there has been extensive research on the capabilities of biologically plausible algorithms. In this work, we show how one of such algorithms, called predictive coding, is able to perform causal inference tasks. First, we show how…

Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment…

Humans are remarkable in their ability to navigate without metric information. We can read abstract 2D maps, such as floor-plans or hand-drawn sketches, and use them to navigate in unseen rich 3D environments, without requiring prior…

In biological systems, the capacity of anticipation--that is, entertaining a model of the system within the system--can be considered as naturally given. Human languages enable psychological systems to construct and exchange mental models…

Memory is inherently entangled with prediction and planning. Flexible behavior in biological and artificial agents depends on the interplay of learning from the past and predicting the future in ever-changing environments. This chapter…

Both scientists and children make important structural discoveries, yet their computational underpinnings are not well understood. Structure discovery has previously been formalized as probabilistic inference about the right structural form…

Human behavior emerges from planning over elaborate decompositions of tasks into goals, subgoals, and low-level actions. How are these decompositions created and used? Here, we propose and evaluate a normative framework for task…