Related papers: Navigation Instruction Generation with BEV Percept…

Visual target navigation in unknown environments is a crucial problem in robotics. Despite extensive investigation of classical and learning-based approaches in the past, robots lack common-sense knowledge about household objects and…

Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between point clouds, which…

Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are shown to guide the model to attend to a target region on the…

Autonomous driving stands as a pivotal domain in computer vision, shaping the future of transportation. Within this paradigm, the backbone of the system plays a crucial role in interpreting the complex environment. However, a notable…

End-to-end autonomous driving offers a streamlined alternative to the traditional modular pipeline, integrating perception, prediction, and planning within a single framework. While Deep Reinforcement Learning (DRL) has recently gained…

Localization in GNSS-denied and GNSS-degraded environments is a challenge for the safe widespread deployment of autonomous vehicles. Such GNSS-challenged environments require alternative methods for robust localization. In this work, we…

In recent years, Embodied Artificial Intelligence (Embodied AI) has advanced rapidly, yet the increasing size of models conflicts with the limited computational capabilities of Embodied AI platforms. To address this challenge, we aim to…

Bird's-eye-view (BEV) is a powerful and widely adopted representation for road scenes that captures surrounding objects and their spatial locations, along with overall context in the scene. In this work, we focus on bird's eye semantic…

Semantic segmentation is an effective way to perform scene understanding. Recently, segmentation in 3D Bird's Eye View (BEV) space has become popular as its directly used by drive policy. However, there is limited work on BEV segmentation…

In the Vision-and-Language Navigation (VLN) task, the agent is required to navigate to a destination following a natural language instruction. While learning-based approaches have been a major solution to the task, they suffer from high…

Large Vision-Language Models (LVLMs) have achieved remarkable success in a wide range of multimodal tasks by integrating pre-trained vision encoders and large language models. However, current LVLMs primarily rely on visual features…

Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and…

In recent years, the rapid advancement of Large Language Models (LLMs) such as the Generative Pre-trained Transformer (GPT) has attracted increasing attention due to their potential in a variety of practical applications. The application of…

Multimodal Vision-Language Models (VLMs) enable powerful applications from their fused understanding of images and language, but many perform poorly on UI tasks due to the lack of UI training data. In this paper, we adapt a recipe for…

We present a multi-modal trajectory generation and selection algorithm for real-world mapless outdoor navigation in human-centered environments. Such environments contain rich features like crosswalks, grass, and curbs, which are easily…

Autonomous navigation requires scene understanding of the action-space to move or anticipate events. For planner agents moving on the ground plane, such as autonomous vehicles, this translates to scene understanding in the bird's-eye view…

Vision-and-Language Navigation (VLN) requires the agent to follow language instructions to navigate through 3D environments. One main challenge in VLN is the limited availability of photorealistic training environments, which makes it hard…

Vision-and-Language Navigation (VLN) has gained significant research interest in recent years due to its potential applications in real-world scenarios. However, existing VLN methods struggle with the issue of spurious associations,…

Recently, Multimodal Large Language Models (MLLMs) have sparked great research interests owing to their exceptional content-reasoning and instruction-following capabilities. To effectively instruct an MLLM, in addition to conventional…

Accurate and robust multimodal multi-task perception is crucial for modern autonomous driving systems. However, current multimodal perception research follows independent paradigms designed for specific perception tasks, leading to a lack…