Related papers: ConsistNav: Closing the Action Consistency Gap in …
Recent progress in large vision-language models has driven improvements in language-based semantic navigation, where an embodied agent must reach a target object described in natural language. Yet we still lack a clear, language-focused…
Object navigation (ObjectNav) in real-world environments is a complex problem that requires simultaneously addressing multiple challenges, including complex spatial structure, long-horizon planning and semantic understanding. Recent…
We consider the problem of object goal navigation in unseen environments. Solving this problem requires learning of contextual semantic priors, a challenging endeavour given the spatial and semantic variability of indoor environments.…
Real-time online object tracking in videos constitutes a core task in computer vision, with wide-ranging applications including video surveillance, motion capture, and robotics. Deployed tracking systems usually lack formal safety…
Semantic segmentation is a significant perception task in autonomous driving. It suffers from the risks of adversarial examples. In the past few years, deep learning has gradually transitioned from convolutional neural network (CNN) models…
Object Navigation (ObjectNav) has made great progress with large language models (LLMs), but still faces challenges in memory management, especially in long-horizon tasks and dynamic scenes. To address this, we propose TopoNav, a new…
This work focuses on the problem of visual target navigation, which is very important for autonomous robots as it is closely related to high-level tasks. To find a special object in unknown environments, classical and learning-based…
We present MG-Nav (Memory-Guided Navigation), a dual-scale framework for zero-shot visual navigation that unifies global memory-guided planning with local geometry-enhanced control. At its core is the Sparse Spatial Memory Graph (SMG), a…
Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that have never been seen during training. Most existing methods assume a shared semantic space between seen and unseen actions and intend to directly learn a mapping from…
We introduce LOG-Nav, an efficient layout-aware object-goal navigation approach designed for complex multi-room indoor environments. By planning hierarchically leveraging a global topologigal map with layout information and local imperative…
Recent open-vocabulary robot mapping methods enrich dense geometric maps with pre-trained visual-language features, achieving a high level of detail and guiding robots to find objects specified by open-vocabulary language queries. While the…
Zero-shot object navigation (ZSON) allows robots to find target objects in unfamiliar environments using natural language instructions, without relying on pre-built maps or task-specific training. Recent general-purpose models, such as…
Visual simultaneous localization and mapping (SLAM) systems face challenges in detecting loop closure under the circumstance of large viewpoint changes. In this paper, we present an object-based loop closure detection method based on the…
We present a novel approach for image-goal navigation, where an agent navigates with a goal image rather than accurate target information, which is more challenging. Our goal is to decouple the learning of navigation goal planning,…
As an attempt towards assessing the robustness of embodied navigation agents, we propose RobustNav, a framework to quantify the performance of embodied navigation agents when exposed to a wide variety of visual - affecting RGB inputs - and…
Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. In scenarios such as rapid and less common…
Social navigation in densely populated dynamic environments poses a significant challenge for autonomous mobile robots, requiring advanced strategies for safe interaction. Existing reinforcement learning (RL)-based methods require over…
Visual Semantic Navigation (VSN) is a fundamental problem in robotics, where an agent must navigate toward a target object in an unknown environment, mainly using visual information. Most state-of-the-art VSN models are trained in…
Most recent work in goal oriented visual navigation resorts to large-scale machine learning in simulated environments. The main challenge lies in learning compact representations generalizable to unseen environments and in learning…
Humans acquire semantic object representations from egocentric visual streams with minimal supervision, but the underlying mechanisms remain unclear. Importantly, the visual system only processes the center of its field of view with high…