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-occurs with a remote spatially. Both Trial-driven IL and TPN underlie robust navigation policy, instructing the agent to escape from deadlock states, such as looping or being stuck. Specifically, trial-driven IL is a type of supervision used in policy network training, while TPN, mimicking the IL supervision in unseen environment, is applied in testing. Experiment in the artificial environment AI2-Thor validates that each of the techniques is effective. When combined, the techniques bring significantly improvement over baseline methods in navigation effectiveness and efficiency in unseen environments. We report 22.8% and 23.5% increase in success rate and Success weighted by Path Length (SPL), respectively. The code is available at https://github.com/xiaobaishu0097/ECCV-VN.git.
Southern University of Science and Technology（南方科技大学）；University of Technology Sydney（悉尼科技大学）；Baidu Research（百度研究院）
There has been an increasing interest in 3D indoor navigation, where a robot in an environment moves to a target according to an instruction. To deploy a robot for navigation in the physical world, lots of training data is required to learn an effective policy. It is quite labour intensive to obtain sufficient real environment data for training robots while synthetic data is much easier to construct by rendering. Though it is promising to utilize the synthetic environments to facilitate navigation training in the real world, real environment are heterogeneous from synthetic environment in two …
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；University of Adelaide（阿德莱德大学）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）；Nanjing University（南京大学）；University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology（哈尔滨工业大学）；Fudan University（复旦大学）
Learned Neural Network based policies have shown promising results for robot navigation. However, most of these approaches fall short of being used on a real robot due to the extensive simulated training they require. These simulations lack the visuals and dynamics of the real world, which makes it infeasible to deploy on a real robot. We present a novel Neural Net based policy, NavNet, which allows for easy deployment on a real robot. It consists of two sub policies -- a high level policy which can understand real images and perform long range planning expressed in high level commands; a low …
The 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）
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). …
This paper presents a novel end-to-end Unmanned Aerial System (UAS) navigation approach for long-range visual navigation in the real world. Inspired by dual-process visual navigation system of human's instinct: environment understanding and landmark recognition, we formulate the UAS navigation task into two same phases. Our system combines the reinforcement learning (RL) and image matching approaches. First, the agent learns the navigation policy using RL in the specified environment. To achieve this, we design an interactive UASNAV environment for the training process. Once the agent learns t…
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；ETH Zurich（苏黎世联邦理工学院）；Massachusetts Institute of Technology（麻省理工学院）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Vision-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments. One of the key challenges in VLN is how to conduct a robust navigation by mitigating the uncertainty caused by ambiguous instructions and insufficient observation of the environment. Agents trained by current approaches typically suffer from this and would consequently struggle to avoid random and inefficient actions at every step. In contrast, when humans face such a challenge, they can still maintain robust navigation by actively exploring the surroun…
Learning Social Navigation from Internet Videos in the Policy State Space
National University of Singapore（新加坡国立大学）；Singapore Management University（新加坡管理大学）；The Chinese University of Hong Kong（香港中文大学）；Max Planck Institute for Plasma Physics（马克斯·普朗克等离子体物理研究所）
The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL). Street View can be a sensible testbed for such RL agents, because it provides real-world photographic imagery at ground level, with diverse street appearances; it has been made into an interactive environment called StreetLearn and used for research on navigation. However, goal-driven street navigation agents have not so far been able to transfer to unseen areas without extensive retraining, and relying on simulatio…
Dorabot Inc.（Dorabot公司）；City University of Hong Kong（香港城市大学）；Fuzhou University（福州大学）
High-speed, low-latency obstacle avoidance that is insensitive to sensor noise is essential for enabling multiple decentralized robots to function reliably in cluttered and dynamic environments. While other distributed multi-agent collision avoidance systems exist, these systems require online geometric optimization where tedious parameter tuning and perfect sensing are necessary. We present a novel end-to-end framework to generate reactive collision avoidance policy for efficient distributed multi-agent navigation. Our method formulates an agent's navigation strategy as a deep neural network …
University of Pennsylvania（宾夕法尼亚大学）；The University of Chicago（芝加哥大学）
We consider the problems of exploration and point-goal navigation in previously unseen environments, where the spatial complexity of indoor scenes and partial observability constitute these tasks challenging. We argue that learning occupancy priors over indoor maps provides significant advantages towards addressing these problems. To this end, we present a novel planning framework that first learns to generate occupancy maps beyond the field-of-view of the agent, and second leverages the model uncertainty over the generated areas to formulate path selection policies for each task of interest. …
Queensland University of Technology（昆士兰科技大学）；Universidad Nacional de Ingeniería（国立工程大学）
Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end manner, these algorithms require large amounts of experience to learn navigation policies from high-dimensional data, which is generally impractical for real robots due to sample complexity. In this paper, we address these problems with two main contributions. We first leverage place recognition and deep learning techniques combined with goal destination fee…
This work focuses on object goal visual navigation, aiming at finding the location of an object from a given class, where in each step the agent is provided with an egocentric RGB image of the scene. We propose to learn the agent's policy using a reinforcement learning algorithm. Our key contribution is a novel attention probability model for visual navigation tasks. This attention encodes semantic information about observed objects, as well as spatial information about their place. This combination of the "what" and the "where" allows the agent to navigate toward the sought-after object effec…
Georgia Institute of Technology（佐治亚理工学院）；Meta AI；Google Atlanta（谷歌亚特兰大）
We present Variable Experience Rollout (VER), a technique for efficiently scaling batched on-policy reinforcement learning in heterogenous environments (where different environments take vastly different times to generate rollouts) to many GPUs residing on, potentially, many machines. VER combines the strengths of and blurs the line between synchronous and asynchronous on-policy RL methods (SyncOnRL and AsyncOnRL, respectively). VER learns from on-policy experience (like SyncOnRL) and has no synchronization points (like AsyncOnRL). VER leads to significant and consistent speed-ups across a bro…
RSRNav: Reasoning Spatial Relationship for Image-Goal Navigation
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（国家人类-机器混合增强智能重点实验室、视觉信息与应用国家工程研究中心、人工智能与机器人研究所，西安交通大学）
We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a series of 2D navigation tasks. We show how our methods can leverage animal videos to improve performance over RL algorithms that do not leverage such observations.
South China University of Technology（华南理工大学）；Pazhou Laboratory（琶洲实验室）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Information Technology R&D Innovation Center of Peking University（北京大学信息技术研发创新中心）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；UMass Amherst（马萨诸塞大学阿默斯特分校）
Getting robots to navigate to multiple objects autonomously is essential yet difficult in robot applications. One of the key challenges is how to explore environments efficiently with camera sensors only. Existing navigation methods mainly focus on fixed cameras and few attempts have been made to navigate with active cameras. As a result, the agent may take a very long time to perceive the environment due to limited camera scope. In contrast, humans typically gain a larger field of view by looking around for a better perception of the environment. How to make robots perceive the environment as…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Visual navigation in complex environments is inefficient with traditional reactive policy or general-purposed recurrent policy. To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module. The memory construction module builds the topological graph based on supervised learning by taking the exploration prior. Then, guided attention features are extracted with the graph attention module. Finally, the deep reinforcement learning based control module makes decisions based…
Deep imitation learning enables robots to learn from expert demonstrations to perform tasks such as lane following or obstacle avoidance. However, in the traditional imitation learning framework, one model only learns one task, and thus it lacks of the capability to support a robot to perform various different navigation tasks with one model in indoor environments. This paper proposes a new framework, Shared Multi-headed Imitation Learning(SMIL), that allows a robot to perform multiple tasks with one model without switching among different models. We model each task as a sub-policy and design …
University of Padova（帕多瓦大学）；Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会（FBK））；Simon Fraser University（西蒙弗雷泽大学）
Learning how to navigate among humans in an occluded and spatially constrained indoor environment, is a key ability required to embodied agent to be integrated into our society. In this paper, we propose an end-to-end architecture that exploits Proximity-Aware Tasks (referred as to Risk and Proximity Compass) to inject into a reinforcement learning navigation policy the ability to infer common-sense social behaviors. To this end, our tasks exploit the notion of immediate and future dangers of collision. Furthermore, we propose an evaluation protocol specifically designed for the Social Navigat…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Semantic cues and statistical regularities in real-world environment layouts can improve efficiency for navigation in novel environments. This paper learns and leverages such semantic cues for navigating to objects of interest in novel environments, by simply watching YouTube videos. This is challenging because YouTube videos don't come with labels for actions or goals, and may not even showcase optimal behavior. Our method tackles these challenges through the use of Q-learning on pseudo-labeled transition quadruples (image, action, next image, reward). We show that such off-policy Q-learning …
Korea Advanced Institute of Science and Technology（韩国科学技术院）
This paper presents a vision-based modularized drone racing navigation system that uses a customized convolutional neural network (CNN) for the perception module to produce high-level navigation commands and then leverages a state-of-the-art planner and controller to generate low-level control commands, thus exploiting the advantages of both data-based and model-based approaches. Unlike the state-of-the-art method which only takes the current camera image as the CNN input, we further add the latest three drone states as part of the inputs. Our method outperforms the state-of-the-art method in …
What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior
University of Technology Nuremberg（纽伦堡工业大学）；ETH Zürich（苏黎世联邦理工学院）；Inria, Ecole Normale Supérieure, CNRS, PSL Research University（法国国家信息与自动化研究所，巴黎高等师范学校，法国国家科学研究中心，巴黎文理研究大学）
Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation
Sapienza University of Rome（罗马大学）；University of Verona（维罗纳大学）；Polytechnic of Turin（都灵理工大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；Reykjavik University（雷克雅未克大学）
This work presents a modular architecture for simultaneous mapping and target driven navigation in indoors environments. The semantic and appearance stored in 2.5D map is distilled from RGB images, semantic segmentation and outputs of object detectors by convolutional neural networks. Given this representation, the mapping module learns to localize the agent and register consecutive observations in the map. The navigation task is then formulated as a problem of learning a policy for reaching semantic targets using current observations and the up-to-date map. We demonstrate that the use of sema…
DUViN: Diffusion-Based Underwater Visual Navigation via Knowledge-Transferred Depth Features
Department of Electrical and Electronic Engineering, The University of Melbourne, Australia（墨尔本大学电子与电气工程系）；School of Mathematics and Statistics, The University of Melbourne, Australia（墨尔本大学数学与统计学学院）
Learning Vision-Based Omnidirectional Navigation: A Teacher-Student Approach Using Monocular Depth Estimation
Fraunhofer Institute for Material Flow and Logistics（弗劳恩霍夫材料流与物流研究所）；The Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能与机器学习研究所）
Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague（布拉格捷克理工大学信息学、机器人学与控制论研究所）；Department of Control Engineering, Faculty of Electrical Engineering, Czech Technical University in Prague（布拉格捷克理工大学电气工程学院控制工程系）；Cognitive Robotics, Faculty of 3mE, Delft University of Technology（代尔夫特理工大学3mE学院认知机器人学系）
Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing, localization, and planning in one module, which can be trained and therefore optimized for a given environment. However, to date, DRL-based visual navigation was validated exclusively in simulation, where the simulator provides information that is not available in the real world, e.g., the robot's position or image segmentation masks. This precludes the use of the …
