English
Related papers

Related papers: Policy-Guided World Model Planning for Language-Co…

200 papers

Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be…

Robotics · Computer Science 2018-07-17 Jake Bruce , Niko Sünderhauf , Piotr Mirowski , Raia Hadsell , Michael Milford

World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not sufficient to capture interaction-dependent dynamics. We…

Artificial Intelligence · Computer Science 2026-05-29 Heejeong Nam , Quentin Le Lidec , Lucas Maes , Yann LeCun , Randall Balestriero

Learning predictive world models from unlabelled video is a foundational challenge in artificial intelligence. While Joint Embedding Predictive Architectures (JEPA) have set new benchmarks in semantic classification, they often remain…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Santosh Kumar Paidi

We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions…

Robotics · Computer Science 2022-06-03 Shu Ishida , João F. Henriques

In cluttered environments, motion planners often face a trade-off between safety and speed due to uncertainty caused by occlusions and limited sensor range. In this work, we investigate whether co-pilot instructions can help robots plan…

Robotics · Computer Science 2025-12-29 Rahul Moorthy Mahesh , Oguzhan Goktug Poyrazoglu , Yukang Cao , Volkan Isler

Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often…

Robotics · Computer Science 2024-09-26 Hang Lai , Jiahang Cao , Jiafeng Xu , Hongtao Wu , Yunfeng Lin , Tao Kong , Yong Yu , Weinan Zhang

Conventional visuomotor imitation learning usually predicts future robot actions directly in the time domain. Such formulations often have limited physical scene awareness and weak long-horizon memory. In contrast, world-model-based…

Robotics · Computer Science 2026-05-12 Changchuan Yang , Yuhang Dong , Guanzhong Tian , Haizhou Ge , Hongrui Zhu

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Lorenzo Mur-Labadia , Matthew Muckley , Amir Bar , Mido Assran , Koustuv Sinha , Mike Rabbat , Yann LeCun , Nicolas Ballas , Adrien Bardes

Recent studies have explored pretrained (foundation) models for vision-based robotic navigation, aiming to achieve generalizable navigation and positive transfer across diverse environments while enhancing zero-shot performance in unseen…

Generating user intent from a sequence of user interface (UI) actions is a core challenge in comprehensive UI understanding. Recent advancements in multimodal large language models (MLLMs) have led to substantial progress in this area, but…

Computation and Language · Computer Science 2024-10-03 Yicheng Fu , Raviteja Anantha , Prabal Vashisht , Jianpeng Cheng , Etai Littwin

In this paper, we propose a novel Deep Reinforcement Learning approach to address the mapless navigation problem, in which the locomotion actions of a humanoid robot are taken online based on the knowledge encoded in learned models.…

Robotics · Computer Science 2021-08-10 Andre Brandenburger , Diego Rodriguez , Sven Behnke

Humans can routinely follow a trajectory defined by a list of images/landmarks. However, traditional robot navigation methods require accurate mapping of the environment, localization, and planning. Moreover, these methods are sensitive to…

Robotics · Computer Science 2019-05-30 Noriaki Hirose , Fei Xia , Roberto Martin-Martin , Amir Sadeghian , Silvio Savarese

For safe and efficient planning and control in autonomous driving, we need a driving policy which can achieve desirable driving quality in long-term horizon with guaranteed safety and feasibility. Optimization-based approaches, such as…

Artificial Intelligence · Computer Science 2017-07-11 Liting Sun , Cheng Peng , Wei Zhan , Masayoshi Tomizuka

This paper presents that the masked-modeling principle driving the success of large foundational vision models can be effectively applied to audio by making predictions in a latent space. We introduce Audio-based Joint-Embedding Predictive…

Sound · Computer Science 2024-01-12 Zhengcong Fei , Mingyuan Fan , Junshi Huang

We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided…

To interact effectively with humans in the real world, it is important for agents to understand language that describes the dynamics of the environment--that is, how the environment behaves--rather than just task instructions specifying…

Computation and Language · Computer Science 2025-12-01 Anh Nguyen , Stefan Lee

Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introduces two significant challenges for downstream policy…

Vision-and-Language Navigation (VLN) presents a complex challenge in embodied AI, requiring agents to interpret natural language instructions and navigate through visually rich, unfamiliar environments. Recent advances in large…

Robotics · Computer Science 2025-06-13 Yicheng Duan , Kaiyu tang

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…

Robotics · Computer Science 2020-03-03 Marvin Chancán , Michael Milford

We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to generate contextually coherent navigation instructions solely from egocentric visual observations of initial and goal states. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Fengyi Wu , Yifei Dong , Yilong Dai , Guangyu Chen , Qifeng Wu , Huiting Huang , Hang Wang , Qi Dai , Alexander G. Hauptmann , Zhi-Qi Cheng