Related papers: RoboTidy : A 3D Gaussian Splatting Household Tidyi…
Vision-language models demonstrate unprecedented performance and generalization across a wide range of tasks and scenarios. Integrating these foundation models into robotic navigation systems opens pathways toward building general-purpose…
Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, single-platform constraints, and small scale. We introduce…
We address the challenge of task-oriented navigation in unstructured and unknown environments, where robots must incrementally build and reason on rich, metric-semantic maps in real time. Since tasks may require clarification or…
We introduce a visually-guided and physics-driven task-and-motion planning benchmark, which we call the ThreeDWorld Transport Challenge. In this challenge, an embodied agent equipped with two 9-DOF articulated arms is spawned randomly in a…
Are current Vision Language Models (VLMs) ready to comprehend and reason about complex embodied interactions in 3D environments? We introduce Embodied3DBench, a robot-centric benchmark targeting low-level spatial intelligence in embodied 3D…
Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…
Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliably ground language into spatially coherent, plausibly executable actions in 3D digital…
Embodied AI benchmarks have advanced navigation, manipulation, and reasoning, but most target complex humanoid agents or large-scale simulations that are far from real-world deployment. In contrast, mobile cleaning robots with dual mode…
While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reasoning. Existing embodied benchmarks largely focus on passive, static household environments and…
Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus…
Visual navigation models often struggle in real-world dynamic environments due to limited robustness to the sim-to-real gap and the difficulty of training policies tailored to target deployment environments (e.g., households, restaurants,…
In language-guided visual navigation, agents locate target objects in unseen environments using natural language instructions. For reliable navigation in unfamiliar scenes, agents should possess strong perception, planning, and prediction…
Virtual reality (VR) has seen increased use for training and instruction. Designers can enable VR users to gain insights into their own performance by visualizing telemetry data from their actions in VR. Our ability to detect patterns and…
Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning between air and water. To address this, we introduce BALTIC, a controlled benchmark…
Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…
Navigation is a fundamental capability in embodied AI, representing the intelligence required to perceive and interact within physical environments following language instructions. Despite significant progress in large Vision-Language…
Recently, natural language has been the primary medium for human-robot interaction. However, its inherent lack of spatial precision introduces challenges for robotic task definition such as ambiguity and verbosity. Moreover, in some public…
Image-goal navigation enables a robot to reach the location where a target image was captured, using visual cues for guidance. However, current methods either rely heavily on data and computationally expensive learning-based approaches or…
Object navigation is a core capability of embodied intelligence, enabling an agent to locate target objects in unknown environments. Recent advances in vision-language models (VLMs) have facilitated zero-shot object navigation (ZSON).…
To enable AI agents to interact seamlessly with both humans and 3D environments, they must not only perceive the 3D world accurately but also align human language with 3D spatial representations. While prior work has made significant…