embodied ai - 2024_12
Navigation
Home / Papers / embodied ai
- Part 1
Papers
Image quality assessment (IQA) of user-generated content (UGC) is a critical technique for human quality of experience (QoE). However, for robot-generated content (RGC), will its image quality be consistent with the Moravec paradox and counter to human common sense? Human subjective scoring is more based on the attractiveness of the image. Embodied agent are required to interact and perceive in the environment, and finally perform specific tasks. Visual images as inputs directly influence downstream tasks. In this paper, we first propose an embodied image quality assessment (EIQA) frameworks. We establish assessment metrics for input images based on the downstream tasks of robot. In addition, we construct an Embodied Preference Database (EPD) containing 5,000 reference and distorted image annotations. The performance of mainstream IQA algorithms on EPD dataset is finally verified. The experiments demonstrate that quality assessment of embodied images is different from that of humans. We sincerely hope that the EPD can contribute to the development of embodied AI by focusing on image quality assessment. The benchmark is available at https://github.com/Jianbo-maker/EPD_benchmark.
We introduce UnrealZoo, a rich collection of photo-realistic 3D virtual worlds built on Unreal Engine, designed to reflect the complexity and variability of the open worlds. Additionally, we offer a variety of playable entities for embodied AI agents. Based on UnrealCV, we provide a suite of easy-to-use Python APIs and tools for various potential applications, such as data collection, environment augmentation, distributed training, and benchmarking. We optimize the rendering and communication efficiency of UnrealCV to support advanced applications, such as multi-agent interaction. Our experiments benchmark agents in various complex scenes, focusing on visual navigation and tracking, which are fundamental capabilities for embodied visual intelligence. The results yield valuable insights into the advantages of diverse training environments for reinforcement learning (RL) agents and the challenges faced by current embodied vision agents, including those based on RL and large vision-language models (VLMs), in open worlds. These challenges involve latency in closed-loop control in dynamic scenes and reasoning about 3D spatial structures in unstructured terrain.
Low altitude economy (LAE) holds immense potential to drive urban development across various sectors. However, LAE also faces challenges in data collection and processing efficiency, flight control precision, and network performance. The challenges could be solved by realizing an integration of sensing, communications, computation, and control (ISC3) for LAE. In this regard, embodied artificial intelligence (EAI), with its unique perception, planning, and decision-making capabilities, offers a promising solution to realize ISC3. Specifically, this paper investigates an application of EAI into ISC3 to support LAE, exploring potential research focuses, solutions, and case study. We begin by outlining rationales and benefits of introducing EAI into LAE, followed by reviewing research directions and solutions for EAI in ISC3. We then propose a framework of an EAI-enabled ISC3 for LAE. The framework's effectiveness is evaluated through a case study of express delivery utilizing an EAI-enabled UAV. Finally, we discuss several future research directions for advancing EAI-enabled LAE.
Significant advances have been made in developing general-purpose embodied AI in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. While these approaches, which combine high-level planners with low-level controllers, show promise, low-level controllers frequently become performance bottlenecks due to repeated failures. In this paper, we argue that the primary cause of failure in many low-level controllers is the absence of an episodic memory system. To address this, we introduce MrSteve (Memory Recall Steve-1), a novel low-level controller equipped with Place Event Memory (PEM), a form of episodic memory that captures what, where, and when information from episodes. This directly addresses the main limitation of the popular low-level controller, Steve-1. Unlike previous models that rely on short-term memory, PEM organizes spatial and event-based data, enabling efficient recall and navigation in long-horizon tasks. Additionally, we propose an Exploration Strategy and a Memory-Augmented Task Solving Framework, allowing agents to alternate between exploration and task-solving based on recalled events. Our approach significantly improves task-solving and exploration efficiency compared to existing methods. We will release our code and demos on the project page: https://sites.google.com/view/mr-steve.
In the rapidly evolving landscape of GameFi, a fusion of gaming and decentralized finance (DeFi), there exists a critical need to enhance player engagement and economic interaction within gaming ecosystems. Our GameFi ecosystem aims to fundamentally transform this landscape by integrating advanced embodied AI agents into GameFi platforms. These AI agents, developed using cutting-edge large language models (LLMs), such as GPT-4 and Claude AI, are capable of proactive, adaptive, and contextually rich interactions with players. By going beyond traditional scripted responses, these agents become integral participants in the game's narrative and economic systems, directly influencing player strategies and in-game economies. We address the limitations of current GameFi platforms, which often lack immersive AI interactions and mechanisms for community engagement or creator monetization. Through the deep integration of AI agents with blockchain technology, we establish a consensus-driven, decentralized GameFi ecosystem. This ecosystem empowers creators to monetize their contributions and fosters democratic collaboration among players and creators. Furthermore, by embedding DeFi mechanisms into the gaming experience, we enhance economic participation and provide new opportunities for financial interactions within the game. Our approach enhances player immersion and retention and advances the GameFi ecosystem by bridging traditional gaming with Web3 technologies. By integrating sophisticated AI and DeFi elements, we contribute to the development of more engaging, economically robust, and community-centric gaming environments. This project represents a significant advancement in the state-of-the-art in GameFi, offering insights and methodologies that can be applied throughout the gaming industry.
Human-scene interaction (HSI) generation is crucial for applications in embodied AI, virtual reality, and robotics. While existing methods can synthesize realistic human motions in 3D scenes and generate plausible human-object interactions, they heavily rely on datasets containing paired 3D scene and motion capture data, which are expensive and time-consuming to collect across diverse environments and interactions. We present ZeroHSI, a novel approach that enables zero-shot 4D human-scene interaction synthesis by integrating video generation and neural human rendering. Our key insight is to leverage the rich motion priors learned by state-of-the-art video generation models, which have been trained on vast amounts of natural human movements and interactions, and use differentiable rendering to reconstruct human-scene interactions. ZeroHSI can synthesize realistic human motions in both static scenes and environments with dynamic objects, without requiring any ground-truth motion data. We evaluate ZeroHSI on a curated dataset of different types of various indoor and outdoor scenes with different interaction prompts, demonstrating its ability to generate diverse and contextually appropriate human-scene interactions.
Point goal navigation (PGN) is a mapless navigation approach that trains robots to visually navigate to goal points without relying on pre-built maps. Despite significant progress in handling complex environments using deep reinforcement learning, current PGN methods are designed for single-robot systems, limiting their generalizability to multi-robot scenarios with diverse platforms. This paper addresses this limitation by proposing a knowledge transfer framework for PGN, allowing a teacher robot to transfer its learned navigation model to student robots, including those with unknown or black-box platforms. We introduce a novel knowledge distillation (KD) framework that transfers first-person-view (FPV) representations (view images, turning/forward actions) to universally applicable third-person-view (TPV) representations (local maps, subgoals). The state is redefined as reconstructed local maps using SLAM, while actions are mapped to subgoals on a predefined grid. To enhance training efficiency, we propose a sampling-efficient KD approach that aligns training episodes via a noise-robust local map descriptor (LMD). Although validated on 2D wheeled robots, this method can be extended to 3D action spaces, such as drones. Experiments conducted in Habitat-Sim demonstrate the feasibility of the proposed framework, requiring minimal implementation effort. This study highlights the potential for scalable and cross-platform PGN solutions, expanding the applicability of embodied AI systems in multi-robot scenarios.
The integration of large language models (LLMs) into the planning module of Embodied Artificial Intelligence (Embodied AI) systems has greatly enhanced their ability to translate complex user instructions into executable policies. In this paper, we demystified how traditional LLM jailbreak attacks behave in the Embodied AI context. We conducted a comprehensive safety analysis of the LLM-based planning module of embodied AI systems against jailbreak attacks. Using the carefully crafted Harmful-RLbench, we accessed 20 open-source and proprietary LLMs under traditional jailbreak attacks, and highlighted two key challenges when adopting the prior jailbreak techniques to embodied AI contexts: (1) The harmful text output by LLMs does not necessarily induce harmful policies in Embodied AI context, and (2) even we can generate harmful policies, we have to guarantee they are executable in practice. To overcome those challenges, we propose Policy Executable (POEX) jailbreak attacks, where harmful instructions and optimized suffixes are injected into LLM-based planning modules, leading embodied AI to perform harmful actions in both simulated and physical environments. Our approach involves constraining adversarial suffixes to evade detection and fine-tuning a policy evaluater to improve the executability of harmful policies. We conducted extensive experiments on both a robotic arm embodied AI platform and simulators, to validate the attack and policy success rates on 136 harmful instructions from Harmful-RLbench. Our findings expose serious safety vulnerabilities in LLM-based planning modules, including the ability of POEX to be transferred across models. Finally, we propose mitigation strategies, such as safety-constrained prompts, pre- and post-planning checks, to address these vulnerabilities and ensure the safe deployment of embodied AI in real-world settings.
High-quality benchmarks are the foundation for embodied AI research, enabling significant advancements in long-horizon navigation, manipulation and rearrangement tasks. However, as frontier tasks in robotics get more advanced, they require faster simulation speed, more intricate test environments, and larger demonstration datasets. To this end, we present MS-HAB, a holistic benchmark for low-level manipulation and in-home object rearrangement. First, we provide a GPU-accelerated implementation of the Home Assistant Benchmark (HAB). We support realistic low-level control and achieve over 3x the speed of previous magical grasp implementations at similar GPU memory usage. Second, we train extensive reinforcement learning (RL) and imitation learning (IL) baselines for future work to compare against. Finally, we develop a rule-based trajectory filtering system to sample specific demonstrations from our RL policies which match predefined criteria for robot behavior and safety. Combining demonstration filtering with our fast environments enables efficient, controlled data generation at scale.
3D scene understanding is an important task, and there has been a recent surge of research interest in aligning 3D representations of point clouds with text to empower embodied AI. However, due to the lack of comprehensive 3D benchmarks, the capabilities of 3D models in real-world scenes, particularly those that are challenging with subtly distinguished objects, remain insufficiently investigated. To facilitate a more thorough evaluation of 3D models' capabilities, we propose a scheme, ObjVariantEnsemble, to systematically introduce more scenes with specified object classes, colors, shapes, quantities, and spatial relationships to meet model evaluation needs. More importantly, we intentionally construct scenes with similar objects to a certain degree and design an LLM-VLM-cooperated annotator to capture key distinctions as annotations. The resultant benchmark can better challenge 3D models, reveal their shortcomings in understanding, and potentially aid in the further development of 3D models.
Experience Goal Visual Rearrangement task stands as a foundational challenge within Embodied AI, requiring an agent to construct a robust world model that accurately captures the goal state. The agent uses this world model to restore a shuffled scene to its original configuration, making an accurate representation of the world essential for successfully completing the task. In this work, we present a novel framework that leverages on 3D Gaussian Splatting as a 3D scene representation for experience goal visual rearrangement task. Recent advances in volumetric scene representation like 3D Gaussian Splatting, offer fast rendering of high quality and photo-realistic novel views. Our approach enables the agent to have consistent views of the current and the goal setting of the rearrangement task, which enables the agent to directly compare the goal state and the shuffled state of the world in image space. To compare these views, we propose to use a dense feature matching method with visual features extracted from a foundation model, leveraging its advantages of a more universal feature representation, which facilitates robustness, and generalization. We validate our approach on the AI2-THOR rearrangement challenge benchmark and demonstrate improvements over the current state of the art methods
In simultaneous localization and mapping, active loop closing (ALC) is an active vision problem that aims to visually guide a robot to maximize the chances of revisiting previously visited points, thereby resetting the drift errors accumulated in the incrementally built map during travel. However, current mainstream navigation strategies that leverage such incomplete maps as workspace prior knowledge often fail in modern long-term autonomy long-distance travel scenarios where map accumulation errors become significant. To address these limitations of map-based navigation, this paper is the first to explore mapless navigation in the embodied AI field, in particular, to utilize object-goal navigation (commonly abbreviated as ON, ObjNav, or OGN) techniques that efficiently explore target objects without using such a prior map. Specifically, in this work, we start from an off-the-shelf mapless ON planner, extend it to utilize a prior map, and further show that the performance in long-distance ALC (LD-ALC) can be maximized by minimizing ``ALC loss" and ``ON loss". This study highlights a simple and effective approach, called ALC-ON (ALCON), to accelerate the progress of challenging long-distance ALC technology by leveraging the growing frontier-guided, data-driven, and LLM-guided ON technologies.
Constructing compact and informative 3D scene representations is essential for effective embodied exploration and reasoning, especially in complex environments over extended periods. Existing representations, such as object-centric 3D scene graphs, oversimplify spatial relationships by modeling scenes as isolated objects with restrictive textual relationships, making it difficult to address queries requiring nuanced spatial understanding. Moreover, these representations lack natural mechanisms for active exploration and memory management, hindering their application to lifelong autonomy. In this work, we propose 3D-Mem, a novel 3D scene memory framework for embodied agents. 3D-Mem employs informative multi-view images, termed Memory Snapshots, to represent the scene and capture rich visual information of explored regions. It further integrates frontier-based exploration by introducing Frontier Snapshots-glimpses of unexplored areas-enabling agents to make informed decisions by considering both known and potential new information. To support lifelong memory in active exploration settings, we present an incremental construction pipeline for 3D-Mem, as well as a memory retrieval technique for memory management. Experimental results on three benchmarks demonstrate that 3D-Mem significantly enhances agents' exploration and reasoning capabilities in 3D environments, highlighting its potential for advancing applications in embodied AI.
In recent years, as robotics has advanced, human-robot collaboration has gained increasing importance. However, current robots struggle to fully and accurately interpret human intentions from voice commands alone. Traditional gripper and suction systems often fail to interact naturally with humans, lack advanced manipulation capabilities, and are not adaptable to diverse tasks, especially in unstructured environments. This paper introduces the Embodied Dexterous Grasping System (EDGS), designed to tackle object grasping in cluttered environments for human-robot interaction. We propose a novel approach to semantic-object alignment using a Vision-Language Model (VLM) that fuses voice commands and visual information, significantly enhancing the alignment of multi-dimensional attributes of target objects in complex scenarios. Inspired by human hand-object interactions, we develop a robust, precise, and efficient grasping strategy, incorporating principles like the thumb-object axis, multi-finger wrapping, and fingertip interaction with an object's contact mechanics. We also design experiments to assess Referring Expression Representation Enrichment (RERE) in referring expression segmentation, demonstrating that our system accurately detects and matches referring expressions. Extensive experiments confirm that EDGS can effectively handle complex grasping tasks, achieving stability and high success rates, highlighting its potential for further development in the field of Embodied AI.
This paper introduces the human-like embodied AI interviewer which integrates android robots equipped with advanced conversational capabilities, including attentive listening, conversational repairs, and user fluency adaptation. Moreover, it can analyze and present results post-interview. We conducted a real-world case study at SIGDIAL 2024 with 42 participants, of whom 69% reported positive experiences. This study demonstrated the system's effectiveness in conducting interviews just like a human and marked the first employment of such a system at an international conference. The demonstration video is available at https://youtu.be/jCuw9g99KuE.
Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRDF) that generates high-quality and large-scale navigational instruction-trajectory pairs by iteratively refining the data pool through the collaboration between two models, the instruction generator and the navigator, without any human-in-the-loop annotation. Specifically, SRDF starts with using a base generator to create an initial data pool for training a base navigator, followed by applying the trained navigator to filter the data pool. This leads to higher-fidelity data to train a better generator, which can, in turn, produce higher-quality data for training the next-round navigator. Such a flywheel establishes a data self-refining process, yielding a continuously improved and highly effective dataset for large-scale language-guided navigation learning. Our experiments demonstrate that after several flywheel rounds, the navigator elevates the performance boundary from 70% to 78% SPL on the classic R2R test set, surpassing human performance (76%) for the first time. Meanwhile, this process results in a superior generator, evidenced by a SPICE increase from 23.5 to 26.2, better than all previous VLN instruction generation methods. Finally, we demonstrate the scalability of our method through increasing environment and instruction diversity, and the generalization ability of our pre-trained navigator across various downstream navigation tasks, surpassing state-of-the-art methods by a large margin in all cases.
We examine the capability of Multimodal Large Language Models (MLLMs) to tackle diverse domains that extend beyond the traditional language and vision tasks these models are typically trained on. Specifically, our focus lies in areas such as Embodied AI, Games, UI Control, and Planning. To this end, we introduce a process of adapting an MLLM to a Generalist Embodied Agent (GEA). GEA is a single unified model capable of grounding itself across these varied domains through a multi-embodiment action tokenizer. GEA is trained with supervised learning on a large dataset of embodied experiences and with online RL in interactive simulators. We explore the data and algorithmic choices necessary to develop such a model. Our findings reveal the importance of training with cross-domain data and online RL for building generalist agents. The final GEA model achieves strong generalization performance to unseen tasks across diverse benchmarks compared to other generalist models and benchmark-specific approaches.
Object goal navigation (ObjectNav) is a fundamental task of embodied AI that requires the agent to find a target object in unseen environments. This task is particularly challenging as it demands both perceptual and cognitive processes for effective perception and decision-making. While perception has gained significant progress powered by the rapidly developed visual foundation models, the progress on the cognitive side remains limited to either implicitly learning from massive navigation demonstrations or explicitly leveraging pre-defined heuristic rules. Inspired by neuroscientific evidence that humans consistently update their cognitive states while searching for objects in unseen environments, we present CogNav, which attempts to model this cognitive process with the help of large language models. Specifically, we model the cognitive process with a finite state machine composed of cognitive states ranging from exploration to identification. The transitions between the states are determined by a large language model based on an online built heterogeneous cognitive map containing spatial and semantic information of the scene being explored. Extensive experiments on both synthetic and real-world environments demonstrate that our cognitive modeling significantly improves ObjectNav efficiency, with human-like navigation behaviors. In an open-vocabulary and zero-shot setting, our method advances the SOTA of the HM3D benchmark from 69.3% to 87.2%. The code and data will be released.
In this paper, we discuss the conceptualisation and design of embodied AI within an inclusive music-making project. The central case study is Jess+ an intelligent digital score system for shared creativity with a mixed ensemble of non-disabled and disabled musicians. The overarching aim is that the digital score enables disabled musicians to thrive in a live music conversation with other musicians regardless of the potential barriers of disability and music-making. After defining what we mean by embodied AI and how this approach supports the aims of the Jess+ project, we outline the main design features of the system. This includes several novel approaches such as its modular design, an AI Factory based on an embodied musicking dataset, and an embedded belief system. Our findings showed that the implemented design decisions and embodied-AI approach led to rich experiences for the musicians which in turn transformed their practice as an inclusive ensemble.
Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains, including Embodied AI. In this work, we study how to best ground a MLLM into different embodiments and their associated action spaces, with the goal of leveraging the multimodal world knowledge of the MLLM. We first generalize a number of methods through a unified architecture and the lens of action space adaptors. For continuous actions, we show that a learned tokenization allows for sufficient modeling precision, yielding the best performance on downstream tasks. For discrete actions, we demonstrate that semantically aligning these actions with the native output token space of the MLLM leads to the strongest performance. We arrive at these lessons via a thorough study of seven action space adapters on five different environments, encompassing over 114 embodied tasks.
InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction
Realizing scaling laws in embodied AI has become a focus. However, previous work has been scattered across diverse simulation platforms, with assets and models lacking unified interfaces, which has led to inefficiencies in research. To address this, we introduce InfiniteWorld, a unified and scalable simulator for general vision-language robot interaction built on Nvidia Isaac Sim. InfiniteWorld encompasses a comprehensive set of physics asset construction methods and generalized free robot interaction benchmarks. Specifically, we first built a unified and scalable simulation framework for embodied learning that integrates a series of improvements in generation-driven 3D asset construction, Real2Sim, automated annotation framework, and unified 3D asset processing. This framework provides a unified and scalable platform for robot interaction and learning. In addition, to simulate realistic robot interaction, we build four new general benchmarks, including scene graph collaborative exploration and open-world social mobile manipulation. The former is often overlooked as an important task for robots to explore the environment and build scene knowledge, while the latter simulates robot interaction tasks with different levels of knowledge agents based on the former. They can more comprehensively evaluate the embodied agent's capabilities in environmental understanding, task planning and execution, and intelligent interaction. We hope that this work can provide the community with a systematic asset interface, alleviate the dilemma of the lack of high-quality assets, and provide a more comprehensive evaluation of robot interactions.
In ObjectNav, agents must locate specific objects within unseen environments, requiring effective perception, prediction, localization and planning capabilities. This study finds that state-of-the-art embodied AI agents compete for higher navigation quality, but often compromise the computational efficiency. To address this issue, we introduce "Skip-SCAR," an optimization framework that builds computationally and memory-efficient embodied AI agents to accomplish high-quality visual navigation tasks. Skip-SCAR opportunistically skips the redundant step computations during semantic segmentation and local re-planning without hurting the navigation quality. Skip-SCAR also adopts a novel hybrid sparse and dense network for object prediction, optimizing both the computation and memory footprint. Tested on the HM3D ObjectNav datasets and real-world physical hardware systems, Skip-SCAR not only minimizes hardware resources but also sets new performance benchmarks, demonstrating the benefits of optimizing both navigation quality and computational efficiency for robotics.
The prominence of embodied Artificial Intelligence (AI), which empowers robots to navigate, perceive, and engage within virtual environments, has attracted significant attention, owing to the remarkable advances in computer vision and large language models. Privacy emerges as a pivotal concern within the realm of embodied AI, as the robot accesses substantial personal information. However, the issue of privacy leakage in embodied AI tasks, particularly concerning reinforcement learning algorithms, has not received adequate consideration in research. This paper aims to address this gap by proposing an attack on the training process of the value-based algorithm and the gradient-based algorithm, utilizing gradient inversion to reconstruct states, actions, and supervisory signals. The choice of using gradients for the attack is motivated by the fact that commonly employed federated learning techniques solely utilize gradients computed based on private user data to optimize models, without storing or transmitting the data to public servers. Nevertheless, these gradients contain sufficient information to potentially expose private data. To validate our approach, we conducted experiments on the AI2THOR simulator and evaluated our algorithm on active perception, a prevalent task in embodied AI. The experimental results demonstrate the effectiveness of our method in successfully reconstructing all information from the data in 120 room layouts. Check our website for videos.
Large Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images. In this paper, we propose TANGO, an approach that extends the program composition via LLMs already observed for images, aiming to integrate those capabilities into embodied agents capable of observing and acting in the world. Specifically, by employing a simple PointGoal Navigation model combined with a memory-based exploration policy as a foundational primitive for guiding an agent through the world, we show how a single model can address diverse tasks without additional training. We task an LLM with composing the provided primitives to solve a specific task, using only a few in-context examples in the prompt. We evaluate our approach on three key Embodied AI tasks: Open-Set ObjectGoal Navigation, Multi-Modal Lifelong Navigation, and Open Embodied Question Answering, achieving state-of-the-art results without any specific fine-tuning in challenging zero-shot scenarios.
We introduce a data capture system and a new dataset, HO-Cap, for 3D reconstruction and pose tracking of hands and objects in videos. The system leverages multiple RGB-D cameras and a HoloLens headset for data collection, avoiding the use of expensive 3D scanners or mocap systems. We propose a semi-automatic method for annotating the shape and pose of hands and objects in the collected videos, significantly reducing the annotation time compared to manual labeling. With this system, we captured a video dataset of humans interacting with objects to perform various tasks, including simple pick-and-place actions, handovers between hands, and using objects according to their affordance, which can serve as human demonstrations for research in embodied AI and robot manipulation. Our data capture setup and annotation framework will be available for the community to use in reconstructing 3D shapes of objects and human hands and tracking their poses in videos.
Understanding functionalities in 3D scenes involves interpreting natural language descriptions to locate functional interactive objects, such as handles and buttons, in a 3D environment. Functionality understanding is highly challenging, as it requires both world knowledge to interpret language and spatial perception to identify fine-grained objects. For example, given a task like 'turn on the ceiling light', an embodied AI agent must infer that it needs to locate the light switch, even though the switch is not explicitly mentioned in the task description. To date, no dedicated methods have been developed for this problem. In this paper, we introduce Fun3DU, the first approach designed for functionality understanding in 3D scenes. Fun3DU uses a language model to parse the task description through Chain-of-Thought reasoning in order to identify the object of interest. The identified object is segmented across multiple views of the captured scene by using a vision and language model. The segmentation results from each view are lifted in 3D and aggregated into the point cloud using geometric information. Fun3DU is training-free, relying entirely on pre-trained models. We evaluate Fun3DU on SceneFun3D, the most recent and only dataset to benchmark this task, which comprises over 3000 task descriptions on 230 scenes. Our method significantly outperforms state-of-the-art open-vocabulary 3D segmentation approaches. Project page: https://jcorsetti.github.io/fun3du
3D scene reconstruction is a foundational problem in computer vision. Despite recent advancements in Neural Implicit Representations (NIR), existing methods often lack editability and compositional flexibility, limiting their use in scenarios requiring high interactivity and object-level manipulation. In this paper, we introduce the Gaussian Object Carver (GOC), a novel, efficient, and scalable framework for object-compositional 3D scene reconstruction. GOC leverages 3D Gaussian Splatting (GS), enriched with monocular geometry priors and multi-view geometry regularization, to achieve high-quality and flexible reconstruction. Furthermore, we propose a zero-shot Object Surface Completion (OSC) model, which uses 3D priors from 3d object data to reconstruct unobserved surfaces, ensuring object completeness even in occluded areas. Experimental results demonstrate that GOC improves reconstruction efficiency and geometric fidelity. It holds promise for advancing the practical application of digital twins in embodied AI, AR/VR, and interactive simulation environments.
Performing complex tasks in open environments remains challenging for robots, even when using large language models (LLMs) as the core planner. Many LLM-based planners are inefficient due to their large number of parameters and prone to inaccuracies because they operate in open-loop systems. We think the reason is that only applying LLMs as planners is insufficient. In this work, we propose DaDu-E, a robust closed-loop planning framework for embodied AI robots. Specifically, DaDu-E is equipped with a relatively lightweight LLM, a set of encapsulated robot skill instructions, a robust feedback system, and memory augmentation. Together, these components enable DaDu-E to (i) actively perceive and adapt to dynamic environments, (ii) optimize computational costs while maintaining high performance, and (iii) recover from execution failures using its memory and feedback mechanisms. Extensive experiments on real-world and simulated tasks show that DaDu-E achieves task success rates comparable to embodied AI robots with larger models as planners like COME-Robot, while reducing computational requirements by $6.6 \times$. Users are encouraged to explore our system at: \url{https://rlc-lab.github.io/dadu-e/}.
3D scene understanding is a long-standing challenge in computer vision and a key component in enabling mixed reality, wearable computing, and embodied AI. Providing a solution to these applications requires a multifaceted approach that covers scene-centric, object-centric, as well as interaction-centric capabilities. While there exist numerous datasets approaching the former two problems, the task of understanding interactable and articulated objects is underrepresented and only partly covered by current works. In this work, we address this shortcoming and introduce (1) an expertly curated dataset in the Universal Scene Description (USD) format, featuring high-quality manual annotations, for instance, segmentation and articulation on 280 indoor scenes; (2) a learning-based model together with a novel baseline capable of predicting part segmentation along with a full specification of motion attributes, including motion type, articulated and interactable parts, and motion parameters; (3) a benchmark serving to compare upcoming methods for the task at hand. Overall, our dataset provides 8 types of annotations - object and part segmentations, motion types, movable and interactable parts, motion parameters, connectivity, and object mass annotations. With its broad and high-quality annotations, the data provides the basis for holistic 3D scene understanding models. All data is provided in the USD format, allowing interoperability and easy integration with downstream tasks. We provide open access to our dataset, benchmark, and method's source code.
Research on 3D Vision-Language Models (3D-VLMs) is gaining increasing attention, which is crucial for developing embodied AI within 3D scenes, such as visual navigation and embodied question answering. Due to the high density of visual features, especially in large 3D scenes, accurately locating task-relevant visual information is challenging. Existing works attempt to segment all objects and consider their features as scene representations. However, these task-agnostic object features include much redundant information and missing details for the task-relevant area. To tackle these problems, we propose LSceneLLM, an adaptive framework that automatically identifies task-relevant areas by leveraging LLM's visual preference for different tasks, followed by a plug-and-play scene magnifier module to capture fine-grained details in focused areas. Specifically, a dense token selector examines the attention map of LLM to identify visual preferences for the instruction input. It then magnifies fine-grained details of the focusing area. An adaptive self-attention module is leveraged to fuse the coarse-grained and selected fine-grained visual information. To comprehensively evaluate the large scene understanding ability of 3D-VLMs, we further introduce a cross-room understanding benchmark, XR-Scene, which contains a series of large scene understanding tasks including XR-QA, XR-EmbodiedPlanning, and XR-SceneCaption. Experiments show that our method surpasses existing methods on both large scene understanding and existing scene understanding benchmarks. Plunging our scene magnifier module into the existing 3D-VLMs also brings significant improvement.
ObjectNav is a popular task in Embodied AI, where an agent navigates to a target object in an unseen environment. Prior literature makes the assumption of a static environment with stationary objects, which lacks realism. To address this, we present a novel formulation to generalize ObjectNav to dynamic environments with non-stationary objects, and refer to it as Portable ObjectNav or P-ObjectNav. In our formulation, we first address several challenging issues with dynamizing existing topological scene graphs by developing a novel method that introduces multiple transition behaviors to portable objects in the scene. We use this technique to dynamize Matterport3D, a popular simulator for evaluating embodied tasks. We then present a benchmark for P-ObjectNav using a combination of heuristic, reinforcement learning, and Large Language Model (LLM)-based navigation approaches on the dynamized environment, while introducing novel evaluation metrics tailored for our task. Our work fundamentally challenges the "static-environment" notion of prior ObjectNav work; the code and dataset for P-ObjectNav will be made publicly available to foster research on embodied navigation in dynamic scenes. We provide an anonymized repository for our code and dataset: https://anonymous.4open.science/r/PObjectNav-1C6D.