相关论文: PIG-Nav: Key Insights for Pretrained Image Goal Na…
Object Navigation (ObjectNav) is a fundamental task in embodied artificial intelligence. Although significant progress has been made in semantic map construction and target direction prediction in current research, redundant exploration and…
Navigating to instance-level targets in complex environments is a challenging problem. Many existing zero-shot methods achieve strong performance by modeling the entire environment and leveraging large language models for scene…
Recent embodied navigation approaches leveraging Vision-Language Models (VLMs) demonstrate strong generalization in versatile Vision-Language Navigation (VLN). However, reliable path planning in complex environments remains challenging due…
UAV vision-language navigation (VLN) requires an agent to navigate complex 3D environments from an egocentric perspective while following ambiguous multi-step instructions over long horizons. Existing zero-shot methods remain limited, as…
How can we build general-purpose robot systems for open-world semantic navigation, e.g., searching a novel environment for a target object specified in natural language? To tackle this challenge, we introduce OSG Navigator, a modular system…
Embodied navigation holds significant promise for real-world applications such as last-mile delivery. However, most existing approaches are confined to either indoor or outdoor environments and rely heavily on strong assumptions, such as…
The objective in this paper is to improve the performance of text-to-image retrieval. To this end, we introduce a new framework that can boost the performance of large-scale pre-trained vision-language models, so that they can be used for…
Autonomous navigation based on precise localization has been widely developed in both academic research and practical applications. The high demand for localization accuracy has been essential for safe robot planing and navigation while it…
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…
2D top-down maps are commonly used for the navigation and exploration of mobile robots through unknown areas. Typically, the robot builds the navigation maps incrementally from local observations using onboard sensors. Recent works have…
Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…
Visual target navigation is a critical capability for autonomous robots operating in unknown environments, particularly in human-robot interaction scenarios. While classical and learning-based methods have shown promise, most existing…
Navigating complex indoor environments requires a deep understanding of the space the robotic agent is acting into to correctly inform the navigation process of the agent towards the goal location. In recent learning-based navigation…
Zero-shot object-goal navigation aims to find target objects in unseen environments using only egocentric observation. Recent methods leverage foundation models' comprehension and reasoning capabilities to enhance navigation performance.…
Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image…
Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not consider the dynamics in…
Mobile robots exploring indoor environments increasingly rely on vision-language models to perceive high-level semantic cues in camera images, such as object categories. Such models offer the potential to substantially advance robot…
Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navigation policy, which compares the similarities of target and…
Navigation is a fundamental capability for mobile robots. While the current trend is to use learning-based approaches to replace traditional geometry-based methods, existing end-to-end learning-based policies often struggle with 3D spatial…
Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior…