相关论文: NanoMVG: USV-Centric Low-Power Multi-Task Visual G…

Visual grounding is a promising path toward more robust and accurate Natural Language Processing (NLP) models. Many multimodal extensions of BERT (e.g., VideoBERT, LXMERT, VL-BERT) allow a joint modeling of texts and images that lead to…

Nano-size unmanned aerial vehicles (UAVs), with few centimeters of diameter and sub-10 Watts of total power budget, have so far been considered incapable of running sophisticated visual-based autonomous navigation software without external…

This extended abstract presents the design and evaluation of AgriOne, an automated unmanned ground vehicle (UGV) platform for high precision sensing of soil moisture in large agricultural fields. The developed robotic system is equipped…

Visual grounding aims to align visual information of specific regions of images with corresponding natural language expressions. Current visual grounding methods leverage pre-trained visual and language backbones independently to obtain…

Vision-and-language navigation (VLN) stands as a key research problem of Embodied AI, aiming at enabling agents to navigate in unseen environments following linguistic instructions. In this field, generalization is a long-standing…

The remarkable growth of unmanned aerial vehicles (UAVs) has also sparked concerns about safety measures during their missions. To advance towards safer autonomous aerial robots, this work presents a vision-based solution to ensuring safe…

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to…

The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges:…

Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions. Owing to the vast spatial scale and high semantic ambiguity of remote sensing scenes, these…

Accurate motion state estimation of Vulnerable Road Users (VRUs), is a critical requirement for autonomous vehicles that navigate in urban environments. Due to their computational efficiency, many traditional autonomy systems perform…

Visual grounding refers to the ability of a model to identify a region within some visual input that matches a textual description. Consequently, a model equipped with visual grounding capabilities can target a wide range of applications in…

To address the challenge of autonomous UGV localization in GNSS-denied off-road environments,this study proposes a matching-based localization method that leverages BEV perception image and satellite map within a road similarity space to…

Visual grounding (VG) aims at locating the foreground entities that match the given natural language expressions. Previous datasets and methods for classic VG task mainly rely on the prior assumption that the given expression must literally…

Experimental testing of an unmanned surface vehicle (USV) has been performed to evaluate the performance of two low-level controllers when displacement and drag properties are time-varying and uncertain. The USV is a 4.3 meter long, 150…

This paper introduces an innovative application of foundation models, enabling Unmanned Ground Vehicles (UGVs) equipped with an RGB-D camera to navigate to designated destinations based on human language instructions. Unlike learning-based…

Interpreting natural-language commands to localize target objects is critical for autonomous driving (AD). Existing visual grounding (VG) methods for autonomous vehicles (AVs) typically struggle with ambiguous, context-dependent…

Due to the limitations of a single autonomous vehicle, Cellular Vehicle-to-Everything (C-V2X) technology opens a new window for achieving fully autonomous driving through sensor information sharing. However, real-world datasets supporting…

A practical navigation agent must be capable of handling a wide range of interaction demands, such as following instructions, searching objects, answering questions, tracking people, and more. Existing models for embodied navigation fall…

In this paper we propose an effective vision-based navigation method that allows a multirotor vehicle to simultaneously reach a desired goal pose in the environment while constantly facing a target object or landmark. Standard techniques…

3D Visual Grounding (3DVG) involves localizing target objects in 3D point clouds based on natural language. While prior work has made strides using textual descriptions, leveraging spoken language-known as Audio-based 3D Visual…