Related papers: Navigation Instruction Generation with BEV Percept…

Unlocking spatial reasoning in Multimodal Large Language Models (MLLMs) is crucial for enabling intelligent interaction with 3D environments. While prior efforts often rely on explicit 3D inputs or specialized model architectures, we ask:…

Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be associated with different visual signals, causing severe…

Large Vision-Language Models (VLMs) have demonstrated potential in enhancing mobile robot navigation in human-centric environments by understanding contextual cues, human intentions, and social dynamics while exhibiting reasoning…

Bird's-eye-view (BEV) perception has emerged as a cornerstone of autonomous driving systems, providing a structured, ego-centric representation critical for downstream planning and control. However, real-world deployment faces challenges…

Beam prediction is critical for reducing beam-training overhead in millimeter-wave (mmWave) systems, especially in high-mobility vehicular scenarios. This paper presents a BEV-Fusion based framework that unifies camera, LiDAR, radar, and…

The Visual-and-Language Navigation (VLN) task requires understanding a textual instruction to navigate a natural indoor environment using only visual information. While this is a trivial task for most humans, it is still an open problem for…

This paper introduces MM-Instruct, a large-scale dataset of diverse and high-quality visual instruction data designed to enhance the instruction-following capabilities of large multimodal models (LMMs). While existing visual instruction…

Accurate LiDAR-camera calibration is fundamental to fusing multi-modal perception in autonomous driving and robotic systems. Traditional calibration methods require extensive data collection in controlled environments and cannot compensate…

Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with camera features. However, the camera-to-LiDAR projection…

The Bird's-Eye-View (BEV) representation is a critical factor that directly impacts the 3D object detection performance, but the traditional BEV grid representation induces quadratic computational cost as the spatial resolution grows. To…

BEV perception is of great importance in the field of autonomous driving, serving as the cornerstone of planning, controlling, and motion prediction. The quality of the BEV feature highly affects the performance of BEV perception. However,…

In the last few years, the research interest in Vision-and-Language Navigation (VLN) has grown significantly. VLN is a challenging task that involves an agent following human instructions and navigating in a previously unknown environment…

Humans can collaborate and complete tasks based on visual signals and instruction from the environment. Training such a robot is difficult especially due to the understanding of the instruction and the complicated environment. Previous…

Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection, demonstrating impressive perceptual capabilities. However, existing methods overlook the geometric quality of BEV representation,…

Detecting diverse objects within complex indoor 3D point clouds presents significant challenges for robotic perception, particularly with varied object shapes, clutter, and the co-existence of static and dynamic elements where traditional…

Bird's Eye View (BEV) representations are tremendously useful for perception-related automated driving tasks. However, generating BEVs from surround-view fisheye camera images is challenging due to the strong distortions introduced by such…

Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual information received in real-time. Prior works have…

Recently, 3D understanding has become popular to facilitate autonomous agents to perform further decisionmaking. However, existing 3D datasets and methods are often limited to specific tasks. On the other hand, recent progress in Large…

Place recognition is a key module for long-term SLAM systems. Current LiDAR-based place recognition methods usually use representations of point clouds such as unordered points or range images. These methods achieve high recall rates of…

Cross-modal Unsupervised Domain Adaptation (UDA) aims to exploit the complementarity of 2D-3D data to overcome the lack of annotation in a new domain. However, UDA methods rely on access to the target domain during training, meaning the…