paper-with-me

Papers PointGoal Navigation

“PointGoal Navigation” 태그가 달린 논문 27편 · 필터 해제

Robust Scene Transfer for PointGoal Navigation via Privileged Sensor Guided Contrastive Learning

2026-06-03 · Amirhossein Zhalehmehrabi, Tiziano Tezze, Alberto Castelini, Alessandro Farinelli arxiv

We propose a sensor-guided adaptive contrastive learning framework for visual representation learning in PointGoal navigation. During training, privileged LiDAR sensing guides the contrastive objective through a geometry…

Representation LearningReinforcement LearningContrastive LearningPointGoal Navigation

IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation

2025-11-21 · Yifan Li, Lichi Li, Anh Dao, Xinyu Zhou 외 arxiv

While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reasoning. Existing embodied benchmarks largely focus on passive, static household…

PointGoal NavigationCollision AvoidanceSpatial Reasoning

TANGO: Training-free Embodied AI Agents for Open-world Tasks

2024-12-05 · CVPR 2025 1 · Filippo Ziliotto, Tommaso Campari, Luciano Serafini, Lamberto Ballan

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 appro…

Embodied Question AnsweringObjectGoal NavigationPointGoal NavigationQuestion Answering

MPVO: Motion-Prior based Visual Odometry for PointGoal Navigation

2024-11-07 · Sayan Paul, Ruddra dev Roychoudhury, Brojeshwar Bhowmick

Visual odometry (VO) is essential for enabling accurate point-goal navigation of embodied agents in indoor environments where GPS and compass sensors are unreliable and inaccurate. However, traditional VO methods face ch…

PointGoal NavigationVisual Odometry

MOPA: Modular Object Navigation with PointGoal Agents

2023-04-07 · Sonia Raychaudhuri, Tommaso Campari, Unnat Jain, Manolis Savva 외

We propose a simple but effective modular approach MOPA (Modular ObjectNav with PointGoal agents) to systematically investigate the inherent modularity of the object navigation task in Embodied AI. MOPA consists of four …

NavigateObjectobject-detectionObject Detection+1

Emergence of Maps in the Memories of Blind Navigation Agents

2023-01-30 · Erik Wijmans, Manolis Savva, Irfan Essa, Stefan Lee 외

Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial intelligence (AI) navigation agents -- a…

Inductive BiasPointGoal Navigation

Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation

2022-12-17 · Yimeng Li, Arnab Debnath, Gregory J. Stein, Jana Kosecka

In recent years several learning approaches to point goal navigation in previously unseen environments have been proposed. They vary in the representations of the environments, problem decomposition, and experimental eva…

Deep Reinforcement LearningmodelPointGoal NavigationProblem Decomposition+4

VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement

2022-10-11 · Erik Wijmans, Irfan Essa, Dhruv Batra

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 generat…

GPUNavigateObjectGoal NavigationOut-of-Distribution Generalization+1

Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment

2022-10-02 · Yijun Cao, Xianshi Zhang, Fuya Luo, Chuan Lin 외

PointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point. Recent studies solved this PointGoal navigation task with near-perfect success rate in photo-realisti…

NavigatePointGoal NavigationVisual Odometry

Is Mapping Necessary for Realistic PointGoal Navigation?

2022-06-02 · CVPR 2022 1 · Ruslan Partsey, Erik Wijmans, Naoki Yokoyama, Oles Dobosevych 외

Can an autonomous agent navigate in a new environment without building an explicit map? For the task of PointGoal navigation ('Go to $\Delta x$, $\Delta y$') under idealized settings (no RGB-D and actuation noise, perfec…

Data AugmentationNavigateOpen-Ended Question AnsweringPointGoal Navigation+1

Embodied Navigation at the Art Gallery

2022-04-19 · Roberto Bigazzi, Federico Landi, Silvia Cascianelli, Marcella Cornia 외

Embodied agents, trained to explore and navigate indoor photorealistic environments, have achieved impressive results on standard datasets and benchmarks. So far, experiments and evaluations have involved domestic and wo…

NavigatePointGoal Navigation

Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation

2022-02-02 · Marco Rosano, Antonino Furnari, Luigi Gulino, Corrado Santoro 외

Navigating complex indoor environments requires a deep understanding of the space the robotic agent is acting into to correctly inform the navigation process of the agent towards the goal location. In recent learning-bas…

PointGoal NavigationScene Understanding

Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge

2021-09-22 · Naoki Yokoyama, Qian Luo, Dhruv Batra, Sehoon Ha

Recent advances in deep reinforcement learning and scalable photorealistic simulation have led to increasingly mature embodied AI for various visual tasks, including navigation. However, while impressive progress has bee…

BenchmarkingData AugmentationDeep Reinforcement LearningImage Augmentation+4

Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck

2021-09-17 · Guillermo Grande, Dhruv Batra, Erik Wijmans

We propose a novel architecture and training paradigm for training realistic PointGoal Navigation -- navigating to a target coordinate in an unseen environment under actuation and sensor noise without access to ground-tr…

PointGoal Navigation

Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI

2021-09-16 · Santhosh K. Ramakrishnan, Aaron Gokaslan, Erik Wijmans, Oleksandr Maksymets 외

We present the Habitat-Matterport 3D (HM3D) dataset. HM3D is a large-scale dataset of 1,000 building-scale 3D reconstructions from a diverse set of real-world locations. Each scene in the dataset consists of a textured 3…

PointGoal NavigationSurface Reconstruction

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

2021-08-26 · ICCV 2021 10 · Xiaoming Zhao, Harsh Agrawal, Dhruv Batra, Alexander Schwing

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 nav…

NavigatePointGoal NavigationVisual Odometry

Out of the Box: Embodied Navigation in the Real World

2021-05-12 · Roberto Bigazzi, Federico Landi, Marcella Cornia, Silvia Cascianelli 외

The research field of Embodied AI has witnessed substantial progress in visual navigation and exploration thanks to powerful simulating platforms and the availability of 3D data of indoor and photorealistic environments.…

PointGoal NavigationVisual Navigation

GridToPix: Training Embodied Agents with Minimal Supervision

2021-04-14 · ICCV 2021 10 · Unnat Jain, Iou-Jen Liu, Svetlana Lazebnik, Aniruddha Kembhavi 외

While deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via carefully shaped rewards. Indeed, without sh…

Deep Reinforcement LearningPointGoal NavigationReinforcement Learning (RL)Task 2

Large Batch Simulation for Deep Reinforcement Learning

2021-03-12 · ICLR 2021 1 · Brennan Shacklett, Erik Wijmans, Aleksei Petrenko, Manolis Savva 외

We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19,000 frames of experience per second…

Deep Reinforcement LearningGPUPointGoal Navigationreinforcement-learning+2

THDA: Treasure Hunt Data Augmentation for Semantic Navigation

2021-01-01 · ICCV 2021 10 · Oleksandr Maksymets, Vincent Cartillier, Aaron Gokaslan, Erik Wijmans 외

Can general-purpose neural models learn to navigate? For PointGoal navigation (""go to x, y""), the answer is a clear `yes' -- mapless neural models composed of task-agnostic components (CNNs and RNNs) trained with l…

Data AugmentationNavigateObjectGoal NavigationOpen-Ended Question Answering+1
1–20 / 27 다음 →