Visual navigation is often cast as a reinforcement learning (RL) problem. Current methods typically result in a suboptimal policy that learns general obstacle avoidance and search behaviours. For example, in the target-object navigation setting, the policies learnt by traditional methods often fail to complete the task, even when the target is clearly within reach from a human perspective. In order to address this issue, we propose to learn to imagine a latent representation of the successful (sub-)goal state. To do so, we have developed a module which we call Foresight Imagination (ForeSIT). ForeSIT is trained to imagine the recurrent latent representation of a future state that leads to success, e.g. either a sub-goal state that is important to reach before the target, or the goal state itself. By conditioning the policy on the generated imagination during training, our agent learns how to use this imagination to achieve its goal robustly. Our agent is able to imagine what the (sub-)goal state may look like (in the latent space) and can learn to navigate towards that state. We develop an efficient learning algorithm to train ForeSIT in an on-policy manner and integrate it into our RL objective. The integration is not trivial due to the constantly evolving state representation shared between both the imagination and the policy. We, empirically, observe that our method outperforms the state-of-the-art methods by a large margin in the commonly accepted benchmark AI2THOR environment. Our method can be readily integrated or added to other model-free RL navigation frameworks.
Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation
Sun Yat-sen University（中山大学）；The University of Hong Kong（香港大学）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与高级计算重点实验室）
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；The University of Adelaide（阿德莱德大学）
We humans can impeccably search for a target object, given its name only, even in an unseen environment. We argue that this ability is largely due to three main reasons: the incorporation of prior knowledge (or experience), the adaptation of it to the new environment using the observed visual cues and most importantly optimistically searching without giving up early. This is currently missing in the state-of-the-art visual navigation methods based on Reinforcement Learning (RL). In this paper, we propose to use externally learned prior knowledge of the relative object locations and integrate i…
Schrödinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation
Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai University of International Business and Economics（上海对外经贸大学）；Shanghai Innovation Institute（上海创新研究院）
Seoul National University（首尔国立大学）；Hanyang University（汉阳大学）
The main challenge in vision-and-language navigation (VLN) is how to understand natural-language instructions in an unseen environment. The main limitation of conventional VLN algorithms is that if an action is mistaken, the agent fails to follow the instructions or explores unnecessary regions, leading the agent to an irrecoverable path. To tackle this problem, we propose Meta-Explore, a hierarchical navigation method deploying an exploitation policy to correct misled recent actions. We show that an exploitation policy, which moves the agent toward a well-chosen local goal among unvisited but…
Australian National University（澳大利亚国立大学）；University of Technology Sydney（悉尼科技大学）
Target-driven visual navigation aims at navigating an agent towards a given target based on the observation of the agent. In this task, it is critical to learn informative visual representation and robust navigation policy. Aiming to improve these two components, this paper proposes three complementary techniques, object relation graph (ORG), trial-driven imitation learning (IL), and a memory-augmented tentative policy network (TPN). ORG improves visual representation learning by integrating object relationships, including category closeness and spatial correlations, e.g., a TV usually co-occu…
Ukrainian Catholic University（乌克兰天主教大学）；Georgia Institute of Technology（佐治亚理工学院）；Meta AI
Can an autonomous agent navigate in a new environment without building an explicit map? For the task of PointGoal navigation ('Go to $Δx$, $Δy$') under idealized settings (no RGB-D and actuation noise, perfect GPS+Compass), the answer is a clear 'yes' - map-less neural models composed of task-agnostic components (CNNs and RNNs) trained with large-scale reinforcement learning achieve 100% Success on a standard dataset (Gibson). However, for PointNav in a realistic setting (RGB-D and actuation noise, no GPS+Compass), this is an open question; one we tackle in this paper. The strongest published …
Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation
Fudan University（复旦大学）；Shanghai AI Laboratory（上海人工智能实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所MAIS）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Science and Technology of China（中国科学技术大学）；TeleAI, China Telecom Corp Ltd（中国电信TeleAI）
Images are composed as a hierarchy of object parts. We use this insight to create a generative graphical model that defines a hierarchical distribution over image parts. Typically, this leads to intractable inference due to loops in the graph. We propose an alternative model structure, the Dense Latent Tree (DLT), which avoids loops and allows for efficient exact inference, while maintaining a dense connectivity between parts of the hierarchy. The usefulness of DLTs is shown for the example task of image completion on partially observed MNIST and Fashion-MNIST data. We verify having successful…
University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-尚佩恩分校）；Georgia Institute of Technology（佐治亚理工学院）；Facebook AI Research（Facebook AI研究院）
It is fundamental for personal robots to reliably navigate to a specified goal. To study this task, PointGoal navigation has been introduced in simulated Embodied AI environments. Recent advances solve this PointGoal navigation task with near-perfect accuracy (99.6% success) in photo-realistically simulated environments, assuming noiseless egocentric vision, noiseless actuation, and most importantly, perfect localization. However, under realistic noise models for visual sensors and actuation, and without access to a "GPS and Compass sensor," the 99.6%-success agents for PointGoal navigation on…
Object navigation tasks require agents to locate specific objects in unknown environments based on visual information. Previously, graph convolutions were used to implicitly explore the relationships between objects. However, due to differences in visibility among objects, it is easy to generate biases in object attention. Thus, in this paper, we propose a directed object attention (DOA) graph to guide the agent in explicitly learning the attention relationships between objects, thereby reducing the object attention bias. In particular, we use the DOA graph to perform unbiased adaptive object …
Georgia Institute of Technology（佐治亚理工学院）；Facebook AI Research（脸书人工智能研究院）；Oregon State University（俄勒冈州立大学）；Google（谷歌）
We study the challenging problem of releasing a robot in a previously unseen environment, and having it follow unconstrained natural language navigation instructions. Recent work on the task of Vision-and-Language Navigation (VLN) has achieved significant progress in simulation. To assess the implications of this work for robotics, we transfer a VLN agent trained in simulation to a physical robot. To bridge the gap between the high-level discrete action space learned by the VLN agent, and the robot's low-level continuous action space, we propose a subgoal model to identify nearby waypoints, an…
Vision-and-Language Navigation (VLN) is a task to guide an embodied agent moving to a target position using language instructions. Despite the significant performance improvement, the wide use of fine-grained instructions fails to characterize more practical linguistic variations in reality. To fill in this gap, we introduce a new setting, namely Underspecified vision-and-Language Navigation (ULN), and associated evaluation datasets. ULN evaluates agents using multi-level underspecified instructions instead of purely fine-grained or coarse-grained, which is a more realistic and general setting…
InnoPeak Technology, Inc.（InnoPeak科技公司）；Monash University（莫纳什大学）；The University of Adelaide（阿德莱德大学）
We propose a robotic learning system for autonomous exploration and navigation in unexplored environments. We are motivated by the idea that even an unseen environment may be familiar from previous experiences in similar environments. The core of our method, therefore, is a process for building, predicting, and using probabilistic layout graphs for assisting goal-based visual navigation. We describe a navigation system that uses the layout predictions to satisfy high-level goals (e.g. "go to the kitchen") more rapidly and accurately than the prior art. Our proposed navigation framework compris…
Vision-and-Language Navigation (VLN) is a natural language grounding task where agents have to interpret natural language instructions in the context of visual scenes in a dynamic environment to achieve prescribed navigation goals. Successful agents must have the ability to parse natural language of varying linguistic styles, ground them in potentially unfamiliar scenes, plan and react with ambiguous environmental feedback. Generalization ability is limited by the amount of human annotated data. In particular, \emph{paired} vision-language sequence data is expensive to collect. We develop a di…
Queensland University of Technology（昆士兰科技大学）；Universidad Nacional de Ingeniería（国立工程大学）
Autonomous navigation emerges from both motion and local visual perception in real-world environments. However, most successful robotic motion estimation methods (e.g. VO, SLAM, SfM) and vision systems (e.g. CNN, visual place recognition-VPR) are often separately used for mapping and localization tasks. Conversely, recent reinforcement learning (RL) based methods for visual navigation rely on the quality of GPS data reception, which may not be reliable when directly using it as ground truth across multiple, month-spaced traversals in large environments. In this paper, we propose a novel motion…
Learning to Retrieve Navigable Candidates for Efficient Vision-and-Language Navigation
University of New South Wales, Sydney, Australia（新南威尔士大学）；Macquarie University, Sydney, Australia（麦考瑞大学）；Data61, CSIRO, Sydney, Australia（Data61, CSIRO）；The School of Computer Science（计算机科学学院）
Direct search for objects as part of navigation poses a challenge for small items. Utilizing context in the form of object-object relationships enable hierarchical search for targets efficiently. Most of the current approaches tend to directly incorporate sensory input into a reward-based learning approach, without learning about object relationships in the natural environment, and thus generalize poorly across domains. We present Memory-utilized Joint hierarchical Object Learning for Navigation in Indoor Rooms (MJOLNIR), a target-driven navigation algorithm, which considers the inherent relat…
Oregon State University（俄勒冈州立大学）；Facebook AI Research（脸书人工智能研究院）；Cornell University（康奈尔大学）；Georgia Institute of Technology（佐治亚理工学院）
Little inquiry has explicitly addressed the role of action spaces in language-guided visual navigation -- either in terms of its effect on navigation success or the efficiency with which a robotic agent could execute the resulting trajectory. Building on the recently released VLN-CE setting for instruction following in continuous environments, we develop a class of language-conditioned waypoint prediction networks to examine this question. We vary the expressivity of these models to explore a spectrum between low-level actions and continuous waypoint prediction. We measure task performance and…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Army Research Laboratory（陆军研究实验室）；Sony AI（索尼人工智能）
While imitation learning for vision based autonomous mobile robot navigation has recently received a great deal of attention in the research community, existing approaches typically require state action demonstrations that were gathered using the deployment platform. However, what if one cannot easily outfit their platform to record these demonstration signals or worse yet the demonstrator does not have access to the platform at all? Is imitation learning for vision based autonomous navigation even possible in such scenarios? In this work, we hypothesize that the answer is yes and that recent …
University of Maryland, College Park（马里兰大学帕克分校）；Georgia Institute of Technology（佐治亚理工学院）；Salesforce Research（Salesforce研究院）
As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making. Specifically, the Vision and Language Navigation (VLN) task involves navigating to a goal purely from language instructions and visual information without explicit knowledge of the goal. Recent successful approaches have made in-roads in achieving good success rates for this task but rely on beam search, which thoroughly explores a large number of trajectories and is unrealistic for applications such as robotics. In this paper, inspired b…
In recent years, great efforts have been devoted to deep imitation learning for autonomous driving control, where raw sensory inputs are directly mapped to control actions. However, navigating through densely populated intersections remains a challenging task due to uncertainty caused by uncertain traffic participants. We focus on autonomous navigation at crowded intersections that require interaction with pedestrians. A multi-task conditional imitation learning framework is proposed to adapt both lateral and longitudinal control tasks for safe and efficient interaction. A new benchmark called…
Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation
Adelaide University（阿德莱德大学）；Responsible AI Research Centre, Australian Institute for Machine Learning（负责任人工智能研究中心，澳大利亚机器学习研究所）；Institute for Infocomm Research (I2R), A*STAR（信息与通信研究院（I2R），A*STAR）；iMotion；CSIRO Data61 Project Website（CSIRO Data61项目网站）
Boston University（波士顿大学）；Honda Research Institute USA, Inc.（本田美国研究院）
Vision-and-Language Navigation (VLN) is a challenging task in the field of artificial intelligence. Although massive progress has been made in this task over the past few years attributed to breakthroughs in deep vision and language models, it remains tough to build VLN models that can generalize as well as humans. In this paper, we provide a new perspective to improve VLN models. Based on our discovery that snapshots of the same VLN model behave significantly differently even when their success rates are relatively the same, we propose a snapshot-based ensemble solution that leverages predict…
Columbia University（哥伦比亚大学）；University of Washington（华盛顿大学）
For robots to be generally useful, they must be able to find arbitrary objects described by people (i.e., be language-driven) even without expensive navigation training on in-domain data (i.e., perform zero-shot inference). We explore these capabilities in a unified setting: language-driven zero-shot object navigation (L-ZSON). Inspired by the recent success of open-vocabulary models for image classification, we investigate a straightforward framework, CLIP on Wheels (CoW), to adapt open-vocabulary models to this task without fine-tuning. To better evaluate L-ZSON, we introduce the Pasture ben…
Vision-and-Language Navigation (VLN) tasks such as Room-to-Room (R2R) require machine agents to interpret natural language instructions and learn to act in visually realistic environments to achieve navigation goals. The overall task requires competence in several perception problems: successful agents combine spatio-temporal, vision and language understanding to produce appropriate action sequences. Our approach adapts pre-trained vision and language representations to relevant in-domain tasks making them more effective for VLN. Specifically, the representations are adapted to solve both a cr…
Visual Indoor Navigation (VIN) task has drawn increasing attention from the data-driven machine learning communities especially with the recently reported success from learning-based methods. Due to the innate complexity of this task, researchers have tried approaching the problem from a variety of different angles, the full scope of which has not yet been captured within an overarching report. This survey first summarizes the representative work of learning-based approaches for the VIN task and then identifies and discusses lingering issues impeding the VIN performance, as well as motivates f…
The ability to perform effective planning is crucial for building an instruction-following agent. When navigating through a new environment, an agent is challenged with (1) connecting the natural language instructions with its progressively growing knowledge of the world; and (2) performing long-range planning and decision making in the form of effective exploration and error correction. Current methods are still limited on both fronts despite extensive efforts. In this paper, we introduce the Evolving Graphical Planner (EGP), a model that performs global planning for navigation based on raw s…
We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals. The proposed semi-parametric topological memory (SPTM) consists of a (non-parametric) graph with nodes corresponding to locations in the environment and a (parametric) deep network capable of retrieving nodes from the graph based on observations. The graph stores no metric information, only connectivity of locations corresponding to the nodes. We use SPTM as a planning module in a navigation system. Given only 5 minutes of footage of a previously unseen maz…
Google Research（谷歌研究院）；University of Michigan（密歇根大学）
People navigating in unfamiliar buildings take advantage of myriad visual, spatial and semantic cues to efficiently achieve their navigation goals. Towards equipping computational agents with similar capabilities, we introduce Pathdreamer, a visual world model for agents navigating in novel indoor environments. Given one or more previous visual observations, Pathdreamer generates plausible high-resolution 360 visual observations (RGB, semantic segmentation and depth) for viewpoints that have not been visited, in buildings not seen during training. In regions of high uncertainty (e.g. predictin…
UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigation
Nanjing University of Science and Technology（南京理工大学）；Northwest Polytechnical University（西北工业大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Tsinghua University（清华大学）
From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation
Australian Institute for Machine Learning, Adelaide University（澳大利亚机器学习研究所，阿德莱德大学）；Ruyi Dynamics（如意动力）；Fudan University（复旦大学）；Swiss Federal Institute of Technology Lausanne (EPFL)（瑞士洛桑联邦理工学院）
University of Maryland, College Park（马里兰大学帕克分校）；Amazon Alexa AI（亚马逊Alexa人工智能部门）
Household environments are visually diverse. Embodied agents performing Vision-and-Language Navigation (VLN) in the wild must be able to handle this diversity, while also following arbitrary language instructions. Recently, Vision-Language models like CLIP have shown great performance on the task of zero-shot object recognition. In this work, we ask if these models are also capable of zero-shot language grounding. In particular, we utilize CLIP to tackle the novel problem of zero-shot VLN using natural language referring expressions that describe target objects, in contrast to past work that u…
ZeST: A VLM-based Zero-Shot Traversability Navigation for Unknown Environments
Field Robotics Engineering and Science Hub (FRESH), Illinois Autonomous Farm, University of Illinois at Urbana-Champaign (UIUC), IL（伊利诺伊大学厄巴纳-香槟分校）；Mobile Robotics Group, São Carlos School of Engineering, University of São Paulo (EESC-USP), São Carlos, SP, Brazil（圣保罗大学）
