English
Related papers

Related papers: VUSFA:Variational Universal Successor Features App…

200 papers

End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the…

Robotics · Computer Science 2019-07-19 Lei Tai , Peng Yun , Yuying Chen , Congcong Liu , Haoyang Ye , Ming Liu

Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications. Existing approaches…

Machine Learning · Computer Science 2022-03-17 Keerthiram Murugesan , Vijay Sadashivaiah , Ronny Luss , Karthikeyan Shanmugam , Pin-Yu Chen , Amit Dhurandhar

We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target as inputs at each time step to provide a sequence of actions that move the…

Robotics · Computer Science 2022-05-10 Qiaoyun Wu , Xiaoxi Gong , Kai Xu , Dinesh Manocha , Jingxuan Dong , Jun Wang

Existing multi-agent deep reinforcement learning (MADRL) methods for multi-UAV navigation face challenges in generalization, particularly when applied to unseen complex environments. To address these limitations, we propose a…

Multiagent Systems · Computer Science 2024-10-22 Anning Wei , Jintao Liang , Kaiyuan Lin , Ziyue Li , Rui Zhao

Although numerous recent tracking approaches have made tremendous advances in the last decade, achieving high-performance visual tracking remains a challenge. In this paper, we propose an end-to-end network model to learn reinforced…

Computer Vision and Pattern Recognition · Computer Science 2020-01-03 Peng Gao , Qiquan Zhang , Fei Wang , Liyi Xiao , Hamido Fujita , Yan Zhang

Deep reinforcement learning (DRL) has achieved remarkable progress in online path planning tasks for multi-UAV systems. However, existing DRL-based methods often suffer from performance degradation when tackling unseen scenarios, since the…

Robotics · Computer Science 2024-07-16 Jiafan Zhuang , Zihao Xia , Gaofei Han , Boxi Wang , Wenji Li , Dongliang Wang , Zhifeng Hao , Ruichu Cai , Zhun Fan

Unmanned aerial base stations (UABSs) can be deployed in vehicular wireless networks to support applications such as extended sensing via vehicle-to-everything (V2X) services. A key problem in such systems is designing algorithms that can…

Machine Learning · Computer Science 2022-10-06 Riccardo Marini , Sangwoo Park , Osvaldo Simeone , Chiara Buratti

This paper presents a novel reinforcement learning framework for trajectory tracking of unmanned aerial vehicles in cluttered environments using a dual-agent architecture. Traditional optimization methods for trajectory tracking face…

Robotics · Computer Science 2024-11-01 Shaswat Garg , Houman Masnavi , Baris Fidan , Farrokh Janabi-Sharifi

This work focuses on the problem of visual target navigation, which is very important for autonomous robots as it is closely related to high-level tasks. To find a special object in unknown environments, classical and learning-based…

Robotics · Computer Science 2023-12-27 Bangguo Yu , Hamidreza Kasaei , Ming Cao

Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited…

Robotics · Computer Science 2019-09-18 Xi Chen , Ali Ghadirzadeh , Mårten Björkman , Patric Jensfelt

First-order reinforcement learning with differentiable simulation is promising for quadrotor control, but practical progress remains fragmented across task-specific settings. To support more systematic development and evaluation, we present…

Robotics · Computer Science 2026-03-24 Fanxing Li , Fangyu Sun , Tianbao Zhang , Shuyu Wu , Dexin Zuo , yufei Yan , Wenxian Yu , Danping Zou

Autonomous UAV navigation using reinforcement learning (RL) is vulnerable to adversarial attacks that manipulate sensor inputs, potentially leading to unsafe behavior and mission failure. Although robust RL methods provide partial…

Machine Learning · Computer Science 2025-12-16 Deepak Kumar Panda , Weisi Guo

Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Yiming Li , Changhong Fu , Fangqiang Ding , Ziyuan Huang , Geng Lu

To enhance the cross-target and cross-scene generalization of target-driven visual navigation based on deep reinforcement learning (RL), we introduce an information-theoretic regularization term into the RL objective. The regularization…

Robotics · Computer Science 2022-05-10 Qiaoyun Wu , Kai Xu , Jun Wang , Mingliang Xu , Xiaoxi Gong , Dinesh Manocha

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Wenxuan Song , Han Zhao , Fuhao Li , Ziyang Zhou , Xi Wang , Jing Lyu , Pengxiang Ding , Yan Wang , Donglin Wang , Haoang Li

In this paper, we present our proposed approach for active tracking to increase the autonomy of Unmanned Aerial Vehicles (UAVs) using event cameras, low-energy imaging sensors that offer significant advantages in speed and dynamic range.…

Robotics · Computer Science 2024-10-22 Ala Souissi , Hajer Fradi , Panagiotis Papadakis

An agent that has well understood the environment should be able to apply its skills for any given goals, leading to the fundamental problem of learning the Universal Value Function Approximator (UVFA). A UVFA learns to predict the…

Machine Learning · Computer Science 2019-08-16 Zhiao Huang , Fangchen Liu , Hao Su

While deep reinforcement learning (RL) methods have achieved unprecedented successes in a range of challenging problems, their applicability has been mainly limited to simulation or game domains due to the high sample complexity of the…

Artificial Intelligence · Computer Science 2017-09-26 Siyi Li , Tianbo Liu , Chi Zhang , Dit-Yan Yeung , Shaojie Shen

With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Haonan Zheng , Xinyang Deng , Wen Jiang , Wenrui Li

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 George Adaimi , Sven Kreiss , Alexandre Alahi