In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environments. However, this process is expensive; massive amounts of interactions are needed for the model to generalize well. Moreover, this process is repeated whenever there is a change in the task type or the goal modality. We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks (e.g., ObjectNav, RoomNav, ViewNav) with various goal modalities (e.g., image, sketch, audio, label). Furthermore, our model enables zero-shot experience learning, whereby it can solve the target tasks without receiving any task-specific interactive training. Our experiments on multiple photorealistic datasets and challenging tasks show that our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
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 …
Learning agents can optimize standard autonomous navigation improving flexibility, efficiency, and computational cost of the system by adopting a wide variety of approaches. This work introduces the \textit{PIC4rl-gym}, a fundamental modular framework to enhance navigation and learning research by mixing ROS2 and Gazebo, the standard tools of the robotics community, with Deep Reinforcement Learning (DRL). The paper describes the whole structure of the PIC4rl-gym, which fully integrates DRL agent's training and testing in several indoor and outdoor navigation scenarios and tasks. A modular appr…
In this paper we propose a new framework - MoViLan (Modular Vision and Language) for execution of visually grounded natural language instructions for day to day indoor household tasks. While several data-driven, end-to-end learning frameworks have been proposed for targeted navigation tasks based on the vision and language modalities, performance on recent benchmark data sets revealed the gap in developing comprehensive techniques for long horizon, compositional tasks (involving manipulation and navigation) with diverse object categories, realistic instructions and visual scenarios with non-re…
Breakthroughs in machine learning in the last decade have led to `digital intelligence', i.e. machine learning models capable of learning from vast amounts of labeled data to perform several digital tasks such as speech recognition, face recognition, machine translation and so on. The goal of this thesis is to make progress towards designing algorithms capable of `physical intelligence', i.e. building intelligent autonomous navigation agents capable of learning to perform complex navigation tasks in the physical world involving visual perception, natural language understanding, reasoning, plan…
Meta AI；UT Austin（德克萨斯大学奥斯汀分校）；UC Berkeley（加州大学伯克利分校）
State-of-the-art approaches to ObjectGoal navigation rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigation with Interaction-free learning (PONI), a modular approach that disentangles the skills of `where to look?' for an object and `how to navigate to (x, y)?'. Our key insight is that `where to look?' can be treated purely as a perception problem, and learned without environment interactions. To address this, we propose a network that predicts two complementary potential functions…
In this work, we propose a new learning approach for autonomous navigation and landing of an Unmanned-Aerial-Vehicle (UAV). We develop a multimodal fusion of deep neural architectures for visual-inertial odometry. We train the model in an end-to-end fashion to estimate the current vehicle pose from streams of visual and inertial measurements. We first evaluate the accuracy of our estimation by comparing the prediction of the model to traditional algorithms on the publicly available EuRoC MAV dataset. The results illustrate a $25 \%$ improvement in estimation accuracy over the baseline. Finally…
This work studies the problem of object goal navigation which involves navigating to an instance of the given object category in unseen environments. End-to-end learning-based navigation methods struggle at this task as they are ineffective at exploration and long-term planning. We propose a modular system called, `Goal-Oriented Semantic Exploration' which builds an episodic semantic map and uses it to explore the environment efficiently based on the goal object category. Empirical results in visually realistic simulation environments show that the proposed model outperforms a wide range of ba…
In Vision-and-Language Navigation (VLN), researchers typically take an image encoder pre-trained on ImageNet without fine-tuning on the environments that the agent will be trained or tested on. However, the distribution shift between the training images from ImageNet and the views in the navigation environments may render the ImageNet pre-trained image encoder suboptimal. Therefore, in this paper, we design a set of structure-encoding auxiliary tasks (SEA) that leverage the data in the navigation environments to pre-train and improve the image encoder. Specifically, we design and customize (1)…
This paper presents a novel approach for aerial drone autonomous navigation along predetermined paths using only visual input form an onboard camera and without reliance on a Global Positioning System (GPS). It is based on using a deep Convolutional Neural Network (CNN) combined with a regressor to output the drone steering commands. Furthermore, multiple auxiliary navigation paths that form a navigation envelope are used for data augmentation to make the system adaptable to real-life deployment scenarios. The approach is suitable for automating drone navigation in applications that exhibit re…
Conventional approaches to vision-and-language navigation (VLN) are trained end-to-end but struggle to perform well in freely traversable environments. Inspired by the robotics community, we propose a modular approach to VLN using topological maps. Given a natural language instruction and topological map, our approach leverages attention mechanisms to predict a navigation plan in the map. The plan is then executed with low-level actions (e.g. forward, rotate) using a robust controller. Experiments show that our method outperforms previous end-to-end approaches, generates interpretable navigati…
Meta AI Research（Meta人工智能研究院）；Carnegie Mellon University（卡内基梅隆大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Realistic long-horizon tasks like image-goal navigation involve exploratory and exploitative phases. Assigned with an image of the goal, an embodied agent must explore to discover the goal, i.e., search efficiently using learned priors. Once the goal is discovered, the agent must accurately calibrate the last-mile of navigation to the goal. As with any robust system, switches between exploratory goal discovery and exploitative last-mile navigation enable better recovery from errors. Following these intuitive guide rails, we propose SLING to improve the performance of existing image-goal naviga…
Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks
Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, School of Computer Science and Technology, Xinjiang University（新疆多模态智能处理与信息安全工程技术创新中心，计算机科学与技术学院，新疆大学）；Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）；School of Electrical Engineering and Automation, Tianjin University of Technology（电气工程与自动化学院，天津工业大学）
SRI International（斯坦福国际研究院）；Center for Vision Technologies（视觉技术中心）
Understanding the geometric relationships between objects in a scene is a core capability in enabling both humans and autonomous agents to navigate in new environments. A sparse, unified representation of the scene topology will allow agents to act efficiently to move through their environment, communicate the environment state with others, and utilize the representation for diverse downstream tasks. To this end, we propose a method to train an autonomous agent to learn to accumulate a 3D scene graph representation of its environment by simultaneously learning to navigate through said environm…
Vision-and-language navigation (VLN), a frontier study aiming to pave the way for general-purpose robots, has been a hot topic in the computer vision and natural language processing community. The VLN task requires an agent to navigate to a goal location following natural language instructions in unfamiliar environments. Recently, transformer-based models have gained significant improvements on the VLN task. Since the attention mechanism in the transformer architecture can better integrate inter- and intra-modal information of vision and language. However, there exist two problems in current t…
RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigation
Space Robotics Research Group, SnT University of Luxembourg（锡尔特大学卢森堡大学空间机器人研究组）；Georgia Tech-Europe IRL2958（佐治亚理工学院欧洲分校IRL2958）；GT-CNRS, Metz, France（GT-CNRS，法国梅茨）；Earth Species Project（地球物种项目）
Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Artificial Intelligence Research Institute（人工智能研究所）
This work studies object goal navigation task, which involves navigating to the closest object related to the given semantic category in unseen environments. Recent works have shown significant achievements both in the end-to-end Reinforcement Learning approach and modular systems, but need a big step forward to be robust and optimal. We propose a hierarchical method that incorporates standard task formulation and additional area knowledge as landmarks, with a way to extract these landmarks. In a hierarchy, a low level consists of separately trained algorithms to the most intuitive skills, and…
Real-time autonomous magnetic microrobot navigation across dynamic and biologically relevant environments
Department of Mechanical Engineering, University of Delaware（德克萨斯大学机械工程系）；Department of Animal and Food Sciences, University of Delaware（德克萨斯大学动物与食品科学系）；School of Civil and Environmental Engineering, Cornell University（康奈尔大学土木与环境工程学院）
Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）；Peng Cheng Laboratory（鹏城实验室）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
While deep neural networks (DNN) based single image super-resolution (SISR) methods are rapidly gaining popularity, they are mainly designed for the widely-used bicubic degradation, and there still remains the fundamental challenge for them to super-resolve low-resolution (LR) image with arbitrary blur kernels. In the meanwhile, plug-and-play image restoration has been recognized with high flexibility due to its modular structure for easy plug-in of denoiser priors. In this paper, we propose a principled formulation and framework by extending bicubic degradation based deep SISR with the help o…
UC San Diego（加州大学圣地亚哥分校）；NEC Labs America（NEC美国实验室）；University of Pennsylvania（宾夕法尼亚大学）
We address key challenges in long-horizon embodied exploration and navigation by proposing a new object transport task and a novel modular framework for temporally extended navigation. Our first contribution is the design of a novel Long-HOT environment focused on deep exploration and long-horizon planning where the agent is required to efficiently find and pick up target objects to be carried and dropped at a goal location, with load constraints and optional access to a container if it finds one. Further, we propose a modular hierarchical transport policy (HTP) that builds a topological graph…
Facebook AI Research（Facebook人工智能研究院）；Georgia Institute of Technology（佐治亚理工学院）
We present a modular approach for learning policies for navigation over long planning horizons from language input. Our hierarchical policy operates at multiple timescales, where the higher-level master policy proposes subgoals to be executed by specialized sub-policies. Our choice of subgoals is compositional and semantic, i.e. they can be sequentially combined in arbitrary orderings, and assume human-interpretable descriptions (e.g. 'exit room', 'find kitchen', 'find refrigerator', etc.). We use imitation learning to warm-start policies at each level of the hierarchy, dramatically increasing…
Georgia Institute of Technology（佐治亚理工学院）；Meta AI Research（Meta人工智能研究院）；University of California, Berkeley（加州大学伯克利分校）；Carnegie Mellon University（卡内基梅隆大学）
Semantic navigation is necessary to deploy mobile robots in uncontrolled environments like our homes, schools, and hospitals. Many learning-based approaches have been proposed in response to the lack of semantic understanding of the classical pipeline for spatial navigation, which builds a geometric map using depth sensors and plans to reach point goals. Broadly, end-to-end learning approaches reactively map sensor inputs to actions with deep neural networks, while modular learning approaches enrich the classical pipeline with learning-based semantic sensing and exploration. But learned visual…
Alternating direction method of multiplier (ADMM) is a widely used algorithm for solving constrained optimization problems in image restoration. Among many useful features, one critical feature of the ADMM algorithm is its modular structure which allows one to plug in any off-the-shelf image denoising algorithm for a subproblem in the ADMM algorithm. Because of the plug-in nature, this type of ADMM algorithms is coined the name "Plug-and-Play ADMM". Plug-and-Play ADMM has demonstrated promising empirical results in a number of recent papers. However, it is unclear under what conditions and by …
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…
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）
VISOR: VIsual Spatial Object Reasoning for Language-driven Object Navigation
Polytechnic of Turin（都灵理工大学）；Simon Fraser University（Simon Fraser大学）；University of Verona（威尼斯大学）；University of Reykjavik（雷克雅未克大学）；University of California, Irvine（加州大学尔湾分校）
ETH Zürich（苏黎世联邦理工学院）；KU Leuven（鲁汶大学）；Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）
Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinder…
Visual question answering (VQA) is a hallmark of vision and language reasoning and a challenging task under the zero-shot setting. We propose Plug-and-Play VQA (PNP-VQA), a modular framework for zero-shot VQA. In contrast to most existing works, which require substantial adaptation of pretrained language models (PLMs) for the vision modality, PNP-VQA requires no additional training of the PLMs. Instead, we propose to use natural language and network interpretation as an intermediate representation that glues pretrained models together. We first generate question-guided informative image captio…
Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation
Sichuan University（四川大学）；Sun Yat-sen University（中山大学）；Australian National University（澳大利亚国立大学）；Peking University（北京大学）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）
his paper presents a simple approach for drone navigation to follow a predetermined path using visual input only without reliance on a Global Positioning System (GPS). A Convolutional Neural Network (CNN) is used to output the steering command of the drone in an end-to-end approach. We tested our approach in two simulated environments in the Unreal Engine using the AirSim plugin for drone simulation. Results show that the proposed approach, despite its simplicity, has average cross track distance less than 2.9 meters in the simulated environment. We also investigate the significance of data au…
NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Intelligent Systems Engineering, Sun Yat-sen University（中山大学智能系统工程学院）
The Anscombe transform offers an approximate conversion of a Poisson random variable into a Gaussian one. This transform is important and appealing, as it is easy to compute, and becomes handy in various inverse problems with Poisson noise contamination. Solution to such problems can be done by first applying the Anscombe transform, then applying a Gaussian-noise-oriented restoration algorithm of choice, and finally applying an inverse Anscombe transform. The appeal in this approach is due to the abundance of high-performance restoration algorithms designed for white additive Gaussian noise (w…
FOM-Nav: Frontier-Object Maps for Object Goal Navigation
Inria（法国国家信息与自动化技术研究院）；Department of Computer Science, École normale supérieure (ENS-PSL, CNRS, Inria)（高等师范学院计算机科学系）；Courant Institute of Mathematical Sciences and Center for Data Science, New York University（纽约大学Courant数学科学研究所和数据科学中心）
