Related papers: Where are the Keys? -- Learning Object-Centric Nav…

A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

Deep learning models as an emerging topic have shown great progress in various fields. Especially, visualization tools such as class activation mapping methods provided visual explanation on the reasoning of convolutional neural networks…

Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets,…

We propose PermaKey, a novel approach to representation learning based on object keypoints. It leverages the predictability of local image regions from spatial neighborhoods to identify salient regions that correspond to object parts, which…

We introduce a learning-based approach for room navigation using semantic maps. Our proposed architecture learns to predict top-down belief maps of regions that lie beyond the agent's field of view while modeling architectural and stylistic…

Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a…

Mapping and localization are two essential tasks for mobile robots in real-world applications. However, largescale and dynamic scenes challenge the accuracy and robustness of most current mature solutions. This situation becomes even worse…

In recent years, data-driven methods have shown great success for extracting information about the infrastructure in urban areas. These algorithms are usually trained on large datasets consisting of thousands or millions of labeled training…

Safe and efficient navigation in dynamic environments shared with humans remains an open and challenging task for mobile robots. Previous works have shown the efficacy of using reinforcement learning frameworks to train policies for…

Geometric variations like rotation, scaling, and viewpoint changes pose a significant challenge to visual understanding. One common solution is to directly model certain intrinsic structures, e.g., using landmarks. However, it then becomes…

Object Goal Navigation (ObjectNav) task is to navigate an agent to an object category in unseen environments without a pre-built map. In this paper, we solve this task by predicting the distance to the target using semantically-related…

Graph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the Self-Constructing…

In order to operate in human environments, a robot's semantic perception has to overcome open-world challenges such as novel objects and domain gaps. Autonomous deployment to such environments therefore requires robots to update their…

Reliable and accurate localization and mapping are key components of most autonomous systems. Besides geometric information about the mapped environment, the semantics plays an important role to enable intelligent navigation behaviors. In…

Rearranging deformable objects is a long-standing challenge in robotic manipulation for the high dimensionality of configuration space and the complex dynamics of deformable objects. We present a novel framework, Graph-Transporter, for…

Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the…

Traditional Simultaneous Localization and Mapping (SLAM) algorithms rely heavily on the static environment assumption, which severely limits their applicability in real-world spaces populated by moving entities, such as pedestrians. In this…

Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new…

This paper introduces a novel method for determining the best room to place an object in, for embodied scene rearrangement. While state-of-the-art approaches rely on large language models (LLMs) or reinforcement learned (RL) policies for…