检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Alsakabi, Mohammed Erickson, Aidan Dolan, John M. Tonguz, Ozan K. Department of Electrical and Computer Engineering College of Engineering The Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States

We present a cost-effective new approach for generating denser depth maps for Autonomous Driving (AD) and Autonomous Vehicles (AVs) by integrating the images obtained from deep neural network (DNN) 4D radar detectors with conventional camera RGB images. Our approach introduces a novel pixel positional encoding algorithm inspired by Bartlett’s spatial spectrum estimation technique. This algorithm transforms both radar depth maps and RGB images into a unified pixel image subspace called the Spatial Spectrum, facilitating effective learning based on their similarities and differences. Our method effectively leverages high-resolution camera images to train radar depth map generative models, addressing the limitations of conventional radar detectors in complex vehicular environments, thus sharpening the radar output. We develop spectrum estimation algorithms tailored for radar depth maps and RGB images, a comprehensive training framework for data-driven generative models, and a camera-radar deployment scheme for AV operation. Our results demonstrate that our approach also outperforms the state-of-the-art (SOTA) by 27.95% in terms of Unidirectional Chamfer Distance (UCD). © 2025, CC BY-NC-ND.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT IMITATION UNDER MISSPECIFICATION

arXiv

引用

arXiv 2025年

作者： Espinosa-Dice, Nicolas Choudhury, Sanjiban Sun, Wen Swamy, Gokul Department of Computer Science Cornell University United States Robotics Institute Carnegie Mellon University United States

We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true in practice due to differences in observation space and action space expressiveness (e.g. perceptual or morphological differences between robots and humans). Given the learner must make some mistakes in the misspecified setting, interaction with the environment is fundamentally required to figure out which mistakes are particularly costly and lead to compounding errors. However, given the computational cost and safety concerns inherent in interaction, we would like to perform as little of it as possible while ensuring we have learned a strong policy. Accordingly, prior work has proposed a flavor of efficient inverse reinforcement learning algorithms that merely perform a computationally efficient local search procedure with strong guarantees in the realizable setting. We first prove that under a novel structural condition we term reward-agnostic policy completeness, these sorts of local-search based IRL algorithms are able to avoid compounding errors. We then consider the question of where we should perform local search in the first place, given the learner may not be able to "walk on a tightrope" as well as the expert in the misspecified setting. We prove that in the misspecified setting, it is beneficial to broaden the set of states on which local search is performed to include states reachable by good policies that the learner can actually play. We then experimentally explore a variety of sources of misspecification and how offline data can be used to effectively broaden where we perform local search from. © 2025, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges

arXiv

引用

arXiv 2025年

作者： Shin, Ukcheol Park, Jinsun Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States School of Computer Science and Engineering Pusan National University Busan Korea Republic of

Achieving robust and accurate spatial perception under adverse weather and lighting conditions is crucial for the high-level autonomy of self-driving vehicles and robots. However, existing perception algorithms relying on the visible spectrum are highly affected by weather and lighting conditions. A long-wave infrared camera (i.e., thermal imaging camera) can be a potential solution to achieve high-level robustness. However, the absence of large-scale datasets and standardized benchmarks remains a significant bottleneck to progress in active research for robust visual perception from thermal images. To this end, this manuscript provides a large-scale Multi-Spectral Stereo (MS2) dataset that consists of stereo RGB, stereo NIR, stereo thermal, stereo LiDAR data, and GNSS/IMU information along with semi-dense depth ground truth. MS2 dataset includes 162K synchronized multimodal data pairs captured across diverse locations (e.g., urban city, residential area, campus, and high-way road) at different times (e.g., morning, daytime, and nighttime) and under various weather conditions (e.g., clear-sky, cloudy, and rainy). Secondly, we conduct a thorough evaluation of monocular and stereo depth estimation networks across RGB, NIR, and thermal modalities to establish standardized benchmark results on MS2 depth test sets (e.g., day, night, and rainy). Lastly, we provide in-depth analyses and discuss the challenges revealed by the benchmark results, such as the performance variability for each modality under adverse conditions, domain shift between different sensor modalities, and potential research direction for thermal perception. Our dataset and source code are publicly available at https://***/view/multi-spectral-stereo-dataset and https://***/UkcheolShin/SupDepth4Thermal. © 2025, CC BY-NC-SA.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Crop Type Classification using Multi-temporal Sentinel-2 Satellite Imagery: A Deep Semantic Segmentation Approach

Crop Type Classification using Multi-temporal Sentinel-2 Sat...

引用

2023 International Conference on robotics and Automation in Industry, ICRAI 2023

作者： Khan, Asim Hameed Zafar, Zuhair Shahzad, Muhammad Berns, Karsten Fraz, Muhammad Moazam Islamabad Pakistan Data Science in Earth Observation Munich Germany University of Reading Department of Computer Science BerkshireRG6 6AH United Kingdom Technical University of Kaiserslautern Robotics Research Lab Germany

ISBN: (纸本)9781665464727

Crop Type classification using Semantic Segmentation and remote sensing data is an important tool for decision-making related to precision agriculture. Such classification remains an unsolved challenge due to the choice of landscape, processing methodology and selected satellite imagery and its optical features, and most importantly the availability and usage of such datasets in a developing country like Pakistan. State-of-the-art semantic segmentation models lack in processing the temporal dimension of time series imagery and evident solution to process multi-spectral bands available in the satellite imagery. We propose a methodology to overcome these shortcomings by selecting appropriate band combinations for crop type classification and treating time series visual data as a single image. The proposed methodology is evaluated on the data set of six different crops collected from National Agriculture Research Center (NARC) Islamabad. The experimental results yield 85% accuracy for classifying various crop types based on the evaluation of five different semantic segmentation models. The code and the trained models are available at https://***/asimniazi63/crop-type-narc for other researchers working in the same domain. © 2023 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Happy: A Debiased Learning Framework for Continual Generalized Category Discovery 38

Happy: A Debiased Learning Framework for Continual Generaliz...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ma, Shijie Zhu, Fei Zhong, Zhun Liu, Wenzhuo Zhang, Xu-Yao Liu, Cheng-Lin MAIS Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS China School of Computer Science and Information Engineering Hefei University of Technology China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

Constantly discovering novel concepts is crucial in evolving environments. This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD), which aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. Although several settings are proposed to study the C-GCD task, they have limitations that do not reflect real-world scenarios. We thus study a more practical C-GCD setting, which includes more new classes to be discovered over a longer period, without storing samples of past classes. In C-GCD, the model is initially trained on labeled data of known classes, followed by multiple incremental stages where the model is fed with unlabeled data containing both old and new classes. The core challenge involves two conflicting objectives: discover new classes and prevent forgetting old ones. We delve into the conflicts and identify that models are susceptible to prediction bias and hardness bias. To address these issues, we introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization. For the prediction bias, we first introduce clustering-guided initialization to provide robust features. In addition, we propose soft entropy regularization to assign appropriate probabilities to new classes, which can significantly enhance the clustering performance of new classes. For the harness bias, we present the hardness-aware prototype sampling, which can effectively reduce the forgetting issue for previously seen classes, especially for difficult classes. Experimental results demonstrate our method proficiently manages the conflicts of C-GCD and achieves remarkable performance across various datasets, e.g., 7.5% overall gains on ImageNet-100. Our code is publicly available at https://***/mashijie1028/Happy-CGCD. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Versatile Navigation Under Partial Observability via Value-Guided Diffusion Policy

Versatile Navigation Under Partial Observability via Value-G...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Gengyu Zhang Hao Tang Yan Yan Department of Computer Science Illinois Institute of Technology USA Robotics Institute Carnegie Mellon University USA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Route planning for navigation under partial observability plays a crucial role in modern robotics and autonomous driving. Existing route planning approaches can be categorized into two main classes: traditional autoregressive and diffusion-based methods. The former often fails due to its myopic nature, while the latter either assumes full observability or struggles to adapt to unfamiliar scenarios, due to strong couplings with behavior cloning from experts. To address these deficiencies, we propose a versatile diffusion-based approach for both 2D and 3D route planning under partial observability. Specifically, our value-guided diffusion policy first generates plans to predict actions across various timesteps, providing ample foresight to the planning. It then employs a differentiable planner with state estimations to derive a value function, directing the agent's exploration and goal-seeking behaviors without seeking experts while explicitly addressing partial observability. During inference, our policy is further enhanced by a best-plan-selection strategy, substantially boosting the planning success rate. Moreover, we propose projecting point clouds, derived from RGB-D inputs, onto 2D grid-based bird-eye- view maps via semantic segmentation, generalizing to 3D environments. This simple yet effective adaption enables zero-shot transfer from 2D-trained policy to 3D, cutting across the laborious training for 3D policy, and thus certifying our versatility. Experimental results demonstrate our superior performance, particularly in navigating situations beyond expert demonstrations, surpassing state-of-the-art autoregressive and diffusion-based baselines for both 2D and 3D scenarios.

关键词： Training Point cloud compression Three-dimensional displays Uncertainty Navigation Semantic segmentation Planning

来源：评论

学校读者我要写书评

暂无评论

Modality-Driven Design for Multi-Step Dexterous Manipulation: Insights from Neuroscience

arXiv

引用

arXiv 2024年

作者： Wake, Naoki Kanehira, Atsushi Saito, Daichi Takamatsu, Jun Sasabuchi, Kazuhiro Koike, Hideki Ikeuchi, Katsushi Applied Robotics Research Microsoft RedmondWA United States Department of Computer Science Institute of Science Tokyo Tokyo Japan

Multi-step dexterous manipulation is a fundamental skill in household scenarios, yet remains an underexplored area in robotics. This paper proposes a modular approach, where each step of the manipulation process is addressed with dedicated policies based on effective modality input, rather than relying on a single end-to-end model. To demonstrate this, a dexterous robotic hand performs a manipulation task involving picking up and rotating a box. Guided by insights from neuroscience, the task is decomposed into three sub-skills—reaching, grasping and lifting, and in-hand rotation—based on the dominant sensory modalities employed in the human brain. Each sub-skill is addressed using distinct methods from a practical perspective: a classical controller, a Vision-Language-Action model, and a reinforcement learning policy with force feedback, respectively. We tested the pipeline on a real robot to demonstrate the feasibility of our approach. The key contribution of this study lies in presenting a neuroscience-inspired, modality-driven methodology for multi-step dexterous manipulation. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

On the 3D trochoidal motion model of LiDAR sensors placed off-centered inside spherical mobile mapping systems

On the 3D trochoidal motion model of LiDAR sensors placed of...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Fabian Arzberger Andreas Nüchter Computer Science XVII – Robotics Julius-Maximilians-Universität Würzburg Am Hubland Germany

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

We study the motion model of a sensor rigidly mounted inside a ball. Due to the rigid placement inside the ball, the geometry of the sensor trajectory resembles a 3D curate trochoid. A new calibration method for spherical systems estimates the extrinsic parameters of the sensor with respect to the balls center of rotation. We deploy the calibration and motion model on our spherical mobile mapping platform to estimate the trajectory of a LiDAR sensor and compare it to trajectories of state-of-the-art LiDAR-Inertial odometry (LIO) methods. The motion model, which is solely based on IMU measurements, produces comparable results to the LIO methods, sometimes even outperforming them in positional accuracy. Although the LIO methods provide better rotational accuracy due to the utilization of LiDAR data, they struggle to reproduce the trochoidal nature of the trajectory and only provide pose estimations at the LiDAR frequency, whereas the motion model produces a more consistent trochoidal trajectory at the much higher IMU frequency. The results demonstrate the difficulty that current LIO methods have on spherical systems and indicate that our motion model is suitable for overcoming these issues.

关键词： Point cloud compression Geometry Laser radar Image color analysis Predictive models Three-dimensional printing Frequency estimation Data models Trajectory Calibration

来源：评论

学校读者我要写书评

暂无评论

Resilient Consensus in Opinion Dynamics Under Adversarial Epidemics

引用

IFAC-PapersOnLine 2023年第2期56卷 1841-1846页

作者： Tatsuya Masada Yuan Wang Hideaki Ishii Department of Computer Science Tokyo Institute of Technology Yokohama Japan Department of Robotics Hunan University Changsha China

In this paper, we discuss the opinion dynamics with bounded confidence in multi-agent systems under an infection spreading environment. The dynamics of the infection spreading processes follows the so-called susceptible-infected-recovered (SIR) model. Here, the infection induces faulty behaviors in the agents whose opinions may deviate from their true opinions. Cooperating with infection suppression policies and the resilient algorithm based on the mean sub-sequence reduced (MSR) approach, resilient consensus can be attained by the regular agents within a safe region. In particular, we establish sufficient conditions for resilient consensus of opinion dynamics with large bounded confidence. A numerical example is provided to verify the effectiveness of our proposed approach.

关键词： Multi-agent systems Opinion dynamics Resilient consensus SIR epidemic model

来源：评论

学校读者我要写书评

暂无评论

Passively Adapting External Force Compensation System for Serial Manipulators 16th

Passively Adapting External Force Compensation System for S...

引用

16th International Federation of Theory of Machines and Mechanisms World Congress, IFToMM WC 2023

作者： Demian, Albert Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis420500 Russia School of Computer Science College of Science University of Lincoln Brayford Pool Lincolnshire LincolnLN6 7TS United Kingdom

ISBN: (纸本)9783031457692

This paper proposes a design approach for a spring-based compensator that passively adapts to external loadings. The proposed compensator is based on a combination of spring-lever mechanisms that are adjustable to the robot’s configuration. Springs in this arrangement are mounted on sliding pivots that connected to springs that allow passive adjustment of the value of the counter-torque. While previous research is either concerned with gravity compensation or with variable stiffness actuators, the proposed approach deals with the variation of external loadings. The proposed force compensator can be used in robotics applications where the robot experiences high external loads during operation. The model was tested in simulation for a planar 2-DoF manipulator and a planar redundant 3-DoF manipulator. The presented results show 58.5% torque reduction for 2-DoF and 55.2% reduction for 3-DoF. Robot redundancy can enhance counter-balancing since the compensation level is configuration-dependent. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：