检索结果-内蒙古大学图书馆

Multi-Target Tracking Considering the Uncertainty of Deep Learning-based Object Detection of Marine Radar Images

学校读者我要写书评

暂无评论

Multi-Target Tracking Considering the Uncertainty of Deep Le...

International Conference on Ubiquitous Robots (UR)

作者： Eunghyun Kim Jonghwi Kim Jinwhan Kim Robotics Program KAIST Daejeon Korea The Department of Mechanical Engineering KAIST Daejeon Korea

In this paper, a multi-target tracking approach that integrates the extended Kalman filter and deep learning-based object detection in marine radar images is presented. The Gaussian YOLOv3 method is utilized for object detection, providing both position measurements and their uncertainties. The extended Kalman filter is employed to estimate the position, heading, and speed of each detected target considering the uncertainty values obtained from the object-detection process. The global nearest neighbor-based data association and a dual filter structure composed of a confirmed track and a reserved track are applied to enhance the robustness of the tracking process. The feasibility of the proposed algorithm is validated through a real-world marine radar dataset collected in a coastal environment.

关键词：

Learning-based Adaptive Control of Quadruped Robots for Active Stabilization on Moving Platforms

学校读者我要写书评

暂无评论

Learning-based Adaptive Control of Quadruped Robots for Acti...

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

作者： Minsung Yoon Heechan Shin Jeil Jeong Sung-Eui Yoon School of Computing at Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea Robotics Program at the Same Institute KAIST

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

A quadruped robot faces balancing challenges on a six-degrees-of-freedom moving platform, like subways, buses, airplanes, and yachts, due to independent platform motions and resultant diverse inertia forces on the robot. To alleviate these challenges, we present the Learning-based Active Stabilization on Moving Platforms (LAS-MP), featuring a self-balancing policy and system state estimators. The policy adaptively adjusts the robot’s posture in response to the platform’s motion. The estimators infer robot and platform states based on proprioceptive sensor data. For a systematic training scheme across various platform motions, we introduce platform trajectory generation and scheduling methods. Our evaluation demonstrates superior balancing performance across multiple metrics compared to three baselines. Furthermore, we conduct a detailed analysis of the LAS-MP, including ablation studies and evaluation of the estimators, to validate the effectiveness of each component.

关键词： Training Measurement Systematics Propioception Trajectory Steady-state Safety Quadrupedal robots Public transportation Intelligent robots

Unified Editing of Panorama, 3D Scenes, and Videos Through Disentangled Self-Attention Injection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kwon, Gihyun Park, Jangho Ye, Jong Chul Kim Jaechul Graduate School of AI KAIST Korea Republic of Department of Bio and Brain Engineering KAIST Korea Republic of Robotics Program KAIST Korea Republic of

While text-to-image models have achieved impressive capabilities in image generation and editing, their application across various modalities often necessitates training separate models. Inspired by existing method of single image editing with self attention injection and video editing with shared attention, we propose a novel unified editing framework that combines the strengths of both approaches by utilizing only a basic 2D image text-to-image (T2I) diffusion model. Specifically, we design a sampling method that facilitates editing consecutive images while maintaining semantic consistency utilizing shared self-attention features during both reference and consecutive image sampling processes. Experimental results confirm that our method enables editing across diverse modalities including 3D scenes, videos, and panorama images. © 2024, CC BY.

关键词： Semantics

Multi-View Node Pruning for Accurate Graph Representation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Park, Jiseong Kim, Hanjin Kim, Seojin Choi, Jueun BBE KAIST Daejeon Korea Republic of Div. Supercomputing KISTI Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of

Graph pooling, which compresses a whole graph into a smaller coarsened graph, is an essential component of graph representation learning. To efficiently compress a given graph, graph pooling methods often drop their nodes with attention-based scoring with the task loss. However, this often results in simply removing nodes with lower degrees without consideration of their feature-level relevance to the given task. To fix this problem, we propose a Multi-View Pruning (MVP), a graph pruning method based on a multi-view framework and reconstruction loss. Given a graph, MVP first constructs multiple graphs for different views either by utilizing the predefined modalities or by randomly partitioning the input features, to consider the importance of each node in diverse perspectives. Then, it learns the score for each node by considering both the reconstruction and the task loss. MVP can be incorporated with any hierarchical pooling framework to score the nodes. We validate MVP on multiple benchmark datasets by coupling it with two graph pooling methods, and show that it significantly improves the performance of the base graph pooling method, outperforming all baselines. Further analysis shows that both the encoding of multiple views and the consideration of reconstruction loss are the key to the success of MVP, and that it indeed identifies nodes that are less important according to domain knowledge. © 2025, CC BY-NC-ND.

关键词： Knowledge graph

ELiOT: End-to-end Lidar Odometry using Transformer Framework

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lee, Daegyu Nam, Hyunwoo Hyunchul Shim, D. Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of

In recent years, deep-learning-based point cloud registration methods have shown significant promise. Furthermore, learning-based 3D detectors have demonstrated their effectiveness in encoding semantic information from LiDAR data. In this paper, we introduce ELiOT, an end-to-end LiDAR odometry framework built on a transformer architecture. Our proposed Self-attention flow embedding network implicitly represents the motion of sequential LiDAR scenes, bypassing the need for 3D-2D projections traditionally used in such tasks. The network pipeline, composed of a 3D transformer encoder-decoder, has shown effectiveness in predicting poses on urban datasets. In terms of translational and rotational errors, our proposed method yields encouraging results, with 7.59% and 2.67% respectively on the KITTI odometry dataset. Our end-to-end approach forgoes conventional geometric concepts and leverages positional embedding networks to identify motion flow and emphasize key features, achieving geometric motion in a seamless manner. © 2023, CC BY-NC-SA.

关键词： Optical radar

Multiview Attention for 3D Object Detection in Lidar Point Cloud 4

学校读者我要写书评

暂无评论

Multiview Attention for 3D Object Detection in Lidar Point C...

4th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2022

作者： Wijaya, Kevin Tirta Paek, Donghee Kong, Seung-Hyun The Robotics Program KAIST Daejeon Korea Republic of The Cho Chun Shik Graduate School of Green Transportation KAIST Daejeon Korea Republic of The Cho Chun Shik Graduate School of Green Transportation KAIST Daejeon Korea Republic of

ISBN: (纸本)9781665458184

Prior works in voxel-based Lidar 3D object detection have demonstrated promising results in detecting a variety of road objects such as cars, pedestrians, and cyclists. However, these works generally reduce the feature space from a 3D volume into a 2D bird eye view (BEV) map before generating object proposals to speed up the inference runtime. As a result, the resolution of information in the z-axis is reduced significantly. In this work, we hypothesize that augmenting the BEV features with features obtained from a front view (FV) map may provide a way for the network to partially recover the high-resolution z-axis information. The augmentation allows object proposals to be inferred in the BEV, maintaining the fast runtime, and simultaneously improving the 3D detection performance. To support our hypothesis, we design a multi-view attention module that augments the BEV features with the FV features and conduct extensive experiments on the widely used KITTI dataset. Based on the experimental results, our method successfully improves various existing voxel-based 3D object detection networks by a significant margin. © 2022 IEEE.

关键词： Object detection

Enhanced K-Radar: Optimal Density Reduction to Improve Detection Performance and Accessibility of 4D Radar Tensor-based Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Paek, Dong-Hee Kong, Seung-Hyun Wijaya, Kevin Tirta CCS Graduate School of Mobility KAIST Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of

Recent works have shown the superior robustness of four-dimensional (4D) Radar-based three-dimensional (3D) object detection in adverse weather conditions. However, processing 4D Radar data remains a challenge due to the large data size, which require substantial amount of memory for computing and storage. In previous work, an online density reduction is performed on the 4D Radar Tensor (4DRT) to reduce the data size, in which the density reduction level is chosen arbitrarily. However, the impact of density reduction on the detection performance and memory consumption remains largely unknown. In this paper, we aim to address this issue by conducting extensive hyperparamter tuning on the density reduction level. Experimental results show that increasing the density level from 0.01% to 50% of the original 4DRT density level proportionally improves the detection performance, at a cost of memory consumption. However, when the density level is increased beyond 5%, only the memory consumption increases, while the detection performance oscillates below the peak point. In addition to the optimized density hyperparameter, we also introduce 4D Sparse Radar Tensor (4DSRT), a new representation for 4D Radar data with offline density reduction, leading to a significantly reduced raw data size. An optimized development kit for training the neural networks is also provided, which along with the utilization of 4DSRT, improves training speed by a factor of 17.1 compared to the state-of-the-art 4DRT-based neural networks. All codes are available at: https://***/kaist-avelab/K-Radar. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

Enhanced K-Radar: Optimal Density Reduction to Improve Detection Performance and Accessibility of 4D Radar Tensor-based Object Detection

学校读者我要写书评

暂无评论

Enhanced K-Radar: Optimal Density Reduction to Improve Detec...

IEEE Symposium on Intelligent Vehicle

作者： Dong-Hee Paek Seung-Hyun Kong Kevin Tirta Wijaya CCS Graduate School of Mobility KAIST Daejeon Republic of Korea Robotics Program KAIST Daejeon Republic of Korea

关键词：

K-Radar: 4D radar object detection for autonomous driving in various weather conditions 22

学校读者我要写书评

暂无评论

K-Radar: 4D radar object detection for autonomous driving in...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Dong-Hee Paek Seung-Hyun Kong Kevin Tirta Wijaya CCS Graduate School of Mobility KAIST Robotics Program KAIST

ISBN: (纸本)9781713871088

Unlike RGB cameras that use visible light bands (384~769 THz) and Lidars that use infrared bands (361~331 THz), Radars use relatively longer wavelength radio bands (77~81 GHz), resulting in robust measurements in adverse weathers. Unfortunately, existing Radar datasets only contain a relatively small number of samples compared to the existing camera and Lidar datasets. This may hinder the development of sophisticated data-driven deep learning techniques for Radar-based perception. Moreover, most of the existing Radar datasets only provide 3D Radar tensor (3DRT) data that contain power measurements along the Doppler, range, and azimuth dimensions. As there is no elevation information, it is challenging to estimate the 3D bounding box of an object from 3DRT. In this work, we introduce kaist-Radar (K-Radar), a novel large-scale object detection dataset and benchmark that contains 35K frames of 4D Radar tensor (4DRT) data with power measurements along the Doppler, range, azimuth, and elevation dimensions, together with carefully annotated 3D bounding box labels of objects on the roads. K-Radar includes challenging driving conditions such as adverse weathers (fog, rain, and snow) on various road structures (urban, suburban roads, alleyways, and highways). In addition to the 4DRT, we provide auxiliary measurements from carefully calibrated high-resolution Lidars, surround stereo cameras, and RTK-GPS. We also provide 4DRT-based object detection baseline neural networks (baseline NNs) and show that the height information is crucial for 3D object detection. And by comparing the baseline NN with a similarly-structured Lidar-based neural network, we demonstrate that 4D Radar is a more robust sensor for adverse weather conditions.

关键词：