Efficient ObjectGoal navigation (ObjectNav) in novel environments requires an understanding of the spatial and semantic regularities in environment layouts. In this work, we present a straightforward method for learning these regularities by predicting the locations of unobserved objects from incomplete semantic maps. Our method differs from previous prediction-based navigation methods, such as frontier potential prediction or egocentric map completion, by directly predicting unseen targets while leveraging the global context from all previously explored areas. Our prediction model is lightweight and can be trained in a supervised manner using a relatively small amount of passively collected data. Once trained, the model can be incorporated into a modular pipeline for ObjectNav without the need for any reinforcement learning. We validate the effectiveness of our method on the HM3D and MP3D ObjectNav datasets. We find that it achieves the state-of-the-art on both datasets, despite not using any additional data for training.
AirDreamer: Generalist Drone Navigation with World Models
Institute for AI Industry Research, Tsinghua University, Beijing, China（人工智能产业研究院，清华大学，北京，中国）；Department of Electronic Engineering, Tsinghua University, Beijing, China（电子工程系，清华大学，北京，中国）；School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China（遥感与信息工程学院，武汉大学，武汉，中国）
Object Goal Navigation (ObjectNav) task is to navigate an agent to an object category in unseen environments without a pre-built map. In this paper, we solve this task by predicting the distance to the target using semantically-related objects as cues. Based on the estimated distance to the target object, our method directly choose optimal mid-term goals that are more likely to have a shorter path to the target. Specifically, based on the learned knowledge, our model takes a bird's-eye view semantic map as input, and estimates the path length from the frontier map cells to the target object. W…
Integration of reinforcement learning with unmanned aerial vehicles (UAVs) to achieve autonomous flight has been an active research area in recent years. An important part focuses on obstacle detection and avoidance for UAVs navigating through an environment. Exploration in an unseen environment can be tackled with Deep Q-Network (DQN). However, value exploration with uniform sampling of actions may lead to redundant states, where often the environments inherently bear sparse rewards. To resolve this, we present two techniques for improving exploration for UAV obstacle avoidance. The first is …
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…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）
Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through interaction with the environment. We created a synthetic block stacking environment with physics simulation in which the agent can learn a policy end-to-end through trial and error. Thereby, we bypass to explicitly model physical knowledge within the policy. We are specifically interested in tasks that require the agent to reach a given goal state that may b…
Navigating and understanding the real world remains a key challenge in machine learning and inspires a great variety of research in areas such as language grounding, planning, navigation and computer vision. We propose an instruction-following task that requires all of the above, and which combines the practicality of simulated environments with the challenges of ambiguous, noisy real world data. StreetNav is built on top of Google Street View and provides visually accurate environments representing real places. Agents are given driving instructions which they must learn to interpret in order …
Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos
Chung-Ang University（中央大学）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））；Electronics and Telecommunications Research Institute (ETRI)（电子通信研究院（ETRI））
University of Hong Kong（香港大学）；Baidu Research（百度研究院）；Fuzhou University（福州大学）；University of Maryland, College Park（马里兰大学帕克分校）
Deep reinforcement learning has great potential to acquire complex, adaptive behaviors for autonomous agents automatically. However, the underlying neural network polices have not been widely deployed in real-world applications, especially in these safety-critical tasks (e.g., autonomous driving). One of the reasons is that the learned policy cannot perform flexible and resilient behaviors as traditional methods to adapt to diverse environments. In this paper, we consider the problem that a mobile robot learns adaptive and resilient behaviors for navigating in unseen uncertain environments whi…
Contact-Aided Navigation of Flexible Robotic Endoscope Using Deep Reinforcement Learning in Dynamic Stomach
Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong, China（电子工程系，香港中文大学（深圳）沙田分校，香港，中国）；Department of Mechanical Engineering, Stanford University（机械工程系，斯坦福大学）
Adobe Systems（奥多比系统公司）；Mila, Université de Montréal（米拉-蒙特利尔大学）
In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in an environment. The agent receives visual information through raw pixels and a natural language instruction telling what task needs to be achieved and is trained in an end-to-end way. We develop an attention mechanism for multi-modal fusion of visual and textual modalities that allows the agent to learn to complete the task and achieve language grounding. Our experimental results show that our attention mechanism outperforms the ex…
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…
Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations. These step-by-step navigational instructions are crucial when the agent is navigating new environments about which it has no prior knowledge. Most recent works that study VLN observe a significant performance drop when tested on unseen environments (i.e., environments not used in training), indicating that the neural agent models are highly biased towards training environments. Although this issue is considered as one of the maj…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Microsoft Research, Redmond（微软研究院雷德蒙德分院）；Duke University（杜克大学）
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to address three critical challenges for this task: the cross-modal grounding, the ill-posed feedback, and the generalization problems. First, we propose a novel Reinforced Cross-Modal Matching (RCM) approach that enforces cross-modal grounding both locally and globally via reinforcement learning (RL). Particularly, a matching critic is used to provide an intrinsic reward to encourage global matching between instruction…
Facebook AI Research（脸书人工智能研究院）；Carnegie Mellon University（卡内基梅隆大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）
This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment. To tackle this problem, we design topological representations for space that effectively leverage semantics and afford approximate geometric reasoning. At the heart of our representations are nodes with associated semantic features, that are interconnected using coarse geometric information. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation. Experimental st…
Vision-and-Language Navigation (VLN) tasks require an agent to navigate through the environment based on language instructions. In this paper, we aim to solve two key challenges in this task: utilizing multilingual instructions for improved instruction-path grounding and navigating through new environments that are unseen during training. To address these challenges, we propose CLEAR: Cross-Lingual and Environment-Agnostic Representations. First, our agent learns a shared and visually-aligned cross-lingual language representation for the three languages (English, Hindi and Telugu) in the Room-…
University of Washington（华盛顿大学）；Microsoft Research AI（微软研究院人工智能）；Allen Institute for Artificial Intelligence（艾伦人工智能研究院）
We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) Vision-and-Language navigation challenge of Anderson et. al. (2018). Given a natural language instruction and photo-realistic image views of a previously unseen environment, the agent was tasked with navigating from source to target location as quickly as possible. While all current approaches make local action decisions or score entire trajectories using beam search, ours balances local and global signals when explor…
Simon Fraser University（西蒙弗雷泽大学）；University of California, Berkeley（加州大学伯克利分校）
In Bansal et al. (2019), a novel visual navigation framework that combines learning-based and model-based approaches has been proposed. Specifically, a Convolutional Neural Network (CNN) predicts a waypoint that is used by the dynamics model for planning and tracking a trajectory to the waypoint. However, the CNN inevitably makes prediction errors which often lead to collisions in cluttered and tight spaces. In this paper, we present a novel Hamilton-Jacobi (HJ) reachability-based method to generate supervision for the CNN for waypoint prediction in an unseen environment. By modeling CNN predi…
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…
Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation
School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）；Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore（新加坡南洋理工大学交叉学科研究生项目）；University College London（伦敦大学学院）
With the rapidly growing expansion in the use of UAVs, the ability to autonomously navigate in varying environments and weather conditions remains a highly desirable but as-of-yet unsolved challenge. In this work, we use Deep Reinforcement Learning to continuously improve the learning and understanding of a UAV agent while exploring a partially observable environment, which simulates the challenges faced in a real-life scenario. Our innovative approach uses a double state-input strategy that combines the acquired knowledge from the raw image and a map containing positional information. This po…
Scaling Data Generation in Vision-and-Language Navigation
OpenGVLab, Shanghai AI Laboratory（上海人工智能实验室OpenGVLab）；University of Adelaide（阿德莱德大学）；UNC, Chapel Hill（北卡罗来纳大学教堂山分校）；The Australian National University（澳大利亚国立大学）；Adobe Research（奥多比研究部）
University of Electronic Science and Technology of China（电子科技大学）
Embodied artificial intelligence (AI) tasks shift from tasks focusing on internet images to active settings involving embodied agents that perceive and act within 3D environments. In this paper, we investigate the target-driven visual navigation using deep reinforcement learning (DRL) in 3D indoor scenes, whose navigation task aims to train an agent that can intelligently make a series of decisions to arrive at a pre-specified target location from any possible starting positions only based on egocentric views. However, most navigation methods currently struggle against several challenging prob…
