中文
相关论文

相关论文: Reasoning in visual navigation of end-to-end train…

200 篇论文

State abstraction is an effective technique for planning in robotics environments with continuous states and actions, long task horizons, and sparse feedback. In object-oriented environments, predicates are a particularly useful form of…

机器人学 · 计算机科学 2023-06-21 Amber Li , Tom Silver

Embodiment is an important characteristic for all intelligent agents (creatures and robots), while existing scene description tasks mainly focus on analyzing images passively and the semantic understanding of the scenario is separated from…

机器人学 · 计算机科学 2020-05-08 Sinan Tan , Huaping Liu , Di Guo , Xinyu Zhang , Fuchun Sun

The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing…

计算机视觉与模式识别 · 计算机科学 2025-05-12 Siyuan Zhou , Yilun Du , Yuncong Yang , Lei Han , Peihao Chen , Dit-Yan Yeung , Chuang Gan

We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…

人工智能 · 计算机科学 2018-03-09 M Ferguson , K. H. Law

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 -- also build implicit…

人工智能 · 计算机科学 2023-02-01 Erik Wijmans , Manolis Savva , Irfan Essa , Stefan Lee , Ari S. Morcos , Dhruv Batra

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution. While goal conditioning of policies has been studied in the RL literature,…

Being able to perceive the semantics and the spatial structure of the environment is essential for visual navigation of a household robot. However, most existing works only employ visual backbones pre-trained either with independent images…

计算机视觉与模式识别 · 计算机科学 2023-07-25 Yicong Hong , Yang Zhou , Ruiyi Zhang , Franck Dernoncourt , Trung Bui , Stephen Gould , Hao Tan

Navigation and manipulation are core capabilities in Embodied AI, yet training agents with these capabilities in the real world faces high costs and time complexity. Therefore, sim-to-real transfer has emerged as a key approach, yet the…

机器人学 · 计算机科学 2025-05-06 Lik Hang Kenny Wong , Xueyang Kang , Kaixin Bai , Jianwei Zhang

Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the…

人工智能 · 计算机科学 2025-07-15 Di Wu , Jiaxin Fan , Junzhe Zang , Guanbo Wang , Wei Yin , Wenhao Li , Bo Jin

Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate…

机器人学 · 计算机科学 2018-03-05 Felipe Codevilla , Matthias Müller , Antonio López , Vladlen Koltun , Alexey Dosovitskiy

Vision guided navigation requires processing complex visual information to inform task-orientated decisions. Applications include autonomous robots, self-driving cars, and assistive vision for humans. A key element is the extraction and…

机器人学 · 计算机科学 2022-09-20 Jaime Ruiz-Serra , Jack White , Stephen Petrie , Tatiana Kameneva , Chris McCarthy

What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way through a complex environment to a target object, e.g. go to…

计算机视觉与模式识别 · 计算机科学 2019-07-04 Arsalan Mousavian , Alexander Toshev , Marek Fiser , Jana Kosecka , Ayzaan Wahid , James Davidson

In Vision-and-Language Navigation (VLN), an embodied agent needs to reach a target destination with the only guidance of a natural language instruction. To explore the environment and progress towards the target location, the agent must…

计算机视觉与模式识别 · 计算机科学 2019-09-26 Federico Landi , Lorenzo Baraldi , Massimiliano Corsini , Rita Cucchiara

The reasoning capabilities of embodied agents introduce a critical, under-explored inferential privacy challenge, where the risk of an agent generate sensitive conclusions from ambient data. This capability creates a fundamental tension…

人机交互 · 计算机科学 2025-09-24 Shuning Zhang , Hong Jia , Simin Li , Ting Dang , Yongquan `Owen' Hu , Xin Yi , Hewu Li

The pursuit of artificial general intelligence (AGI) has placed embodied intelligence at the forefront of robotics research. Embodied intelligence focuses on agents capable of perceiving, reasoning, and acting within the physical world.…

Understanding and mapping a new environment are core abilities of any autonomously navigating agent. While classical robotics usually estimates maps in a stand-alone manner with SLAM variants, which maintain a topological or metric…

计算机视觉与模式识别 · 计算机科学 2023-09-28 Pierre Marza , Laetitia Matignon , Olivier Simonin , Christian Wolf

Large vision-language models have recently demonstrated impressive performance in planning and control tasks, driving interest in their application to real-world robotics. However, deploying these models for reasoning in embodied contexts…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Karmesh Yadav , Yusuf Ali , Gunshi Gupta , Yarin Gal , Zsolt Kira

The common approach for local navigation on challenging environments with legged robots requires path planning, path following and locomotion, which usually requires a locomotion control policy that accurately tracks a commanded velocity.…

机器人学 · 计算机科学 2022-09-27 Nikita Rudin , David Hoeller , Marko Bjelonic , Marco Hutter

Autonomous driving is a multi-task problem requiring a deep understanding of the visual environment. End-to-end autonomous systems have attracted increasing interest as a method of learning to drive without exhaustively programming…

计算机视觉与模式识别 · 计算机科学 2019-09-12 Alexander Makrigiorgos , Ali Shafti , Alex Harston , Julien Gerard , A. Aldo Faisal

Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. Such a trend underscored the potential of training LLMs with…

计算机视觉与模式识别 · 计算机科学 2023-10-20 Gengze Zhou , Yicong Hong , Qi Wu