paper-with-me

Papers

ENTL: Embodied Navigation Trajectory Learner

2023-04-05 · ICCV 2023 1 · Klemen Kotar, Aaron Walsman, Roozbeh Mottaghi

We propose Embodied Navigation Trajectory Learner (ENTL), a method for extracting long sequence representations for embodied navigation. Our approach unifies world modeling, localization and imitation learning into a single sequence prediction task. We train our model using vector-quantized predictions of future states conditioned on current states and actions. ENTL's generic architecture enables sharing of the spatio-temporal sequence encoder for multiple challenging embodied tasks. We achieve competitive performance on navigation tasks using significantly less data than strong baselines while performing auxiliary tasks such as localization and future frame prediction (a proxy for world modeling). A key property of our approach is that the model is pre-trained without any explicit reward signal, which makes the resulting model generalizable to multiple tasks and environments.

📄 PDF Abstract BibTeX arXiv:2304.02639

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

BIT-Nav: Brain-Inspired Trajectory Memory for Embodied Navigation

2026-06-19 · Rithvik Jonna, Aakash Gurram, Man Namgung, Wyatt Mackey 외 arxiv

Vision-Language Models (VLMs) for embodied navigation rely on selecting a fixed number of frames from a growing trajectory history. As episodes extend, this selection grows increasingly sparse, yet prior work shows no ac…

NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks

2025-08-04 · Zhihao Luo, Wentao Yan, Jingyu Gong, Min Wang 외 arxiv

Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and training paradigms. In this paper, we obser…

Reinforcement Learning

WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models

2026-04-09 · Hongjin Chen, Shangyun Jiang, Tonghua Su, Chen Gao 외 arxiv

Vision-language models (VLMs) and generative world models are opening new opportunities for embodied navigation. VLMs are increasingly used as direct planners or trajectory predictors, while world models support look-ahe…

Vision-Language NavigationTrajectory Prediction

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions

2025-10-09 · Haolin Yang, Yuxing Long, Zhuoyuan Yu, Zihan Yang 외 arxiv

Instruction-following navigation is a key step toward embodied intelligence. Prior benchmarks mainly focus on semantic understanding but overlook systematically evaluating navigation agents' spatial perception and reason…

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation

2022-06-12 · Chengyang Ying, You Qiaoben, Xinning Zhou, Hang Su 외

Embodied agents in vision navigation coupled with deep neural networks have attracted increasing attention. However, deep neural networks have been shown vulnerable to malicious adversarial noises, which may potentially …