检索结果-内蒙古大学图书馆

Resilient Navigation Based on Multimodal Measurements and Degradation Identification for High-Speed Autonomous Race Cars

学校读者我要写书评

暂无评论

Resilient Navigation Based on Multimodal Measurements and De...

IEEE Symposium on Intelligent Vehicle

作者： Daegyu Lee Hyunwoo Nam Chanhoe Ryu Sungwon Nah D. Hyunchul Shim Department of Electrical Engineering Korea Advanced Institute of Science and Technologies (KAIST) Daejeon Republic of Korea Robotics Program KAIST Daejeon Republic of Korea

This paper presents a localization system robust against unreliable measurements and a resilient navigation system recovering from localization failures for Indy autonomous challenge (IAC). The IAC is a competition with full-scale autonomous race cars that drive at speeds up to 300 kph. Owing to high-speed and heavy vibration in the car, a GPS/INS system is prone to degrade causing critical localization errors, which leads to catastrophic *** order to address this issue, we propose a robust localization system that probabilistically evaluates the credibility of multi-modal measurements. At a correction step of the Kalman filter, a degradation identification method with a novel hyper-parameter derived from Bayesian decision theory is introduced to choose the most credible measurement values in real-time. Since the racing condition is so harsh that even our robust localization method can fail for a short period of time, we present a resilient navigation system that enables the race car to continue to follow the race track in the event of a localization failure. Our system uses direct perception information in planning and execution until the completion of localization *** proposed localization system is first validated in a simulation with real measurement data contaminated by large artificial noises. The experimental validation during an actual race is also presented. The last part of our paper shows the results from the real-world tests where our system recovers from failures and prevents accidents in real-time, which proves the resilience of the proposed navigation system.

关键词：

Automatic wall slant angle map generation using 3D point clouds

学校读者我要写书评

暂无评论

Automatic wall slant angle map generation using 3D point clo...

作者： Kim, Jeongyun Yun, Seungsang Jung, Minwoo Kim, Ayoung Cho, Younggun Department of Civil and Environmental Engineering KAIST Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of Department of Robotics Engineering Yeungnam University Gyeongsan Korea Republic of

Recently, quantitative and repetitive inspections of the old urban area were conducted because many structures exceed their designed lifetime. The health of a building can be validated from the condition of the outer wall, while the slant angle of the wall widely serves as an indicator of urban regeneration projects. Mostly, the inspector directly measures the inclination of the wall or partially uses 3D point measurements using a static light detection and ranging (LiDAR). These approaches are costly, time-consuming, and only limited space can be measured. Therefore, we propose a mobile mapping system and automatic slant map generation algorithm, configured to capture urban environments online. Additionally, we use the LiDAR-inertial mapping algorithm to construct raw point clouds with gravity information. The proposed method extracts walls from raw point clouds and measures the slant angle of walls accurately. The generated slant angle map is evaluated in indoor and outdoor environments, and the accuracy is compared with real tiltmeter measurements. 1225-6463/$ © 2021 ETRI

关键词： Conformal mapping

Feature-Based Global Localization for Underwater Terrain Aided Navigation Using Bag of Words

学校读者我要写书评

暂无评论

Feature-Based Global Localization for Underwater Terrain Aid...

OCEANS

作者： Qianyi Zhang Jinwhan Kim The Robotics Program Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea Department of Mechanical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea

ISBN: (数字)9798350362077

ISBN: (纸本)9798350362084

This paper presents a novel feature-based global localization method for underwater terrain aided navigation (UTAN) using Bag of Words (BoW). Before the mission, the prior bathymetric map is segmented into submaps, and the handcrafted terrain gradient features are extracted from the submaps. Subsequently, a BoW is trained using these features, and the submaps are indexed accordingly. During the UTAN mission, place recognition is achieved by matching the index of the newly collected submap with the indexes of the submaps in the database, and the vehicle pose is determined using TEASER++ registration method. Experimental results using a sea trial dataset demonstrate that the proposed method can achieve a fast and robust global localization without requiring the prior initial vehicle pose information, offering robustness against substantial initial positioning and heading errors.

关键词： Location awareness Navigation Filtering Databases Oceans Feature extraction Robustness Indexes

Designing an End-to-End UAV System for Insulator Inspection Under Transmission Tower Environments

学校读者我要写书评

暂无评论

Designing an End-to-End UAV System for Insulator Inspection ...

International Conference on Electronics, Information and Communications (ICEIC)

作者： Jinyeong Jeong Seongsu Park Sanghoon Lee Donghyeon Youn Min Jun Kim School of Electrical Engineering KAIST Daejeon Republic of Korea Robotics Program KAIST Daejeon Republic of Korea KEPCO Research Institute Korea Electric Power Corporation Daejeon Republic of Korea

This paper proposes an unmanned aerial vehicle (UAV) equipped with a rigid contact module and two supplementary forward-direction motors, designed for the contact-based inspection of porcelain insulators. During the free-flight, this aerial robot is controlled by a geometric tracking controller. When approaching and contacting the insulators, the impedance controller generates enough force to sustain contact by using two forward-direction motors, while the geometric tracking controller maintains its orientation. This platform is validated through simulations, demonstrating its effectiveness in performing contact-based inspection tasks.

关键词：

Continuous Adversarial Text Representation Learning for Affective Recognition

学校读者我要写书评

暂无评论

Continuous Adversarial Text Representation Learning for Affe...

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Seungah Son Andres Saurez Dongsoo Har CCS Graduate School of Mobility Korea Advanced Institute of Science and Technology (KAIST) Daejeon Rep. of Korea Robotics Program Korea Advanced Institute of Science and Technology (KAIST) Daejeon Rep. of Korea

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

While pre-trained language models excel at semantic understanding, they often struggle to capture nuanced affective information critical for affective recognition tasks. To address these limitations, we propose a novel framework for enhancing emotion-aware embeddings in transformer-based models. Our approach introduces a continuous valence-arousal labeling system to guide contrastive learning, which captures subtle and multi-dimensional emotional nuances more effectively. Furthermore, we employ a dynamic token perturbation mechanism, using gradient-based saliency to focus on sentiment-relevant tokens, improving model sensitivity to emotional cues. The experimental results demonstrate that the proposed framework outperforms existing methods, achieving up to 15.5% improvement in the emotion classification benchmark, highlighting the importance of employing continuous labels. This improvement demonstrates that the proposed framework is effective in affective representation learning and enables precise and contextually relevant emotional understanding.

关键词： Representation learning Affective computing Sentiment analysis Sensitivity Text recognition Perturbation methods Semantics Contrastive learning Benchmark testing Transformers

A Resilient Navigation and Path Planning System for High-speed Autonomous Race Car

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lee, Daegyu Jung, Chanyoung Finazzi, Andrea Seong, Hyunki Shim, D. Hyunchul Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of

This paper describes a resilient navigation and planning system used in the Indy Autonomous Challenge (IAC) competition. The IAC is a competition where full-scale race cars run autonomously on Indianapolis Motor Speedway(IMS) up to 290 km/h (180 mph). Race cars will experience severe vibrations. Especially at high speeds. These vibrations can degrade standard localization algorithms based on precision GPS-aided inertial measurement units. Degraded localization can lead to serious problems, including collisions. Therefore, we propose a resilient navigation system that enables a race car to stay within the track in the event of localization failures. Our navigation system uses a multi-sensor fusion-based Kalman filter. We detect degradation of the navigation solution using probabilistic approaches to computing optimal measurement values for the correction step of our Kalman filter. In addition, an optimal path planning algorithm for obstacle avoidance is proposed. In this challenge, the track has static obstacles on the track. The vehicle is required to avoid them with minimal time loss. By taking the original optimal racing line, obstacles, and vehicle dynamics into account, we propose a road-graph-based path planning algorithm to ensure that our race car can perform efficient obstacle avoidance. The proposed localization system was successfully validated to show its capability to prevent localization failures in the event of faulty GPS measurements during the historic world’s first autonomous racing at IMS. Owing to our robust navigation and planning algorithm, we were able to finish the race as one of the top four teams while the remaining five teams failed to finish due to collisions or out-of-track violations. © 2022, CC BY-NC-SA.

关键词： Kalman filters

Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling

学校读者我要写书评

暂无评论

arXiv 2022年

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

Existing point cloud feature learning networks often incorporate sequences of sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation to learn high-semantic point features that represent the global context of a point cloud. Unfortunately, such a process may result in a substantial loss of granular information due to the sampling operation. Moreover, the widely-used max-pooling feature aggregation may exacerbate the loss since it completely neglects information from non-maximum point features. Due to the compounded loss of information concerning granularity and non-maximum point features, the resulting high-semantic point features from existing networks could be insufficient to represent the local context of a point cloud, which in turn may hinder the network in distinguishing fine shapes. To cope with this problem, we propose a novel point cloud feature learning network, PointStack, using multi-resolution feature learning and learnable pooling (LP). The multi-resolution feature learning is realized by aggregating point features of various resolutions in the multiple layers, so that the final point features contain both high-semantic and high-resolution information. On the other hand, the LP is used as a generalized pooling function that calculates the weighted sum of multi-resolution point features through the attention mechanism with learnable queries, in order to extract all possible information from all available point features. Consequently, PointStack is capable of extracting high-semantic point features with minimal loss of information concerning granularity and non-maximum point features. Therefore, the final aggregated point features can effectively represent both global and local contexts of a point cloud. In addition, both the global structure and the local shape details of a point cloud can be well comprehended by the network head, which enables PointStack to advance the state-of-the-art of feature learning on point cl

关键词： Semantics

ED-NERF: EFFICIENT TEXT-GUIDED EDITING OF 3D SCENE WITH LATENT SPACE NERF

学校读者我要写书评

暂无评论

arXiv 2023年

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

Recently, there has been a significant advancement in text-to-image diffusion models, leading to groundbreaking performance in 2D image generation. These advancements have been extended to 3D models, enabling the generation of novel 3D objects from textual descriptions. This has evolved into NeRF editing methods, which allow the manipulation of existing 3D objects through textual conditioning. However, existing NeRF editing techniques have faced limitations in their performance due to slow training speeds and the use of loss functions that do not adequately consider editing. To address this, here we present a novel 3D NeRF editing approach dubbed ED-NeRF by successfully embedding real-world scenes into the latent space of the latent diffusion model (LDM) through a unique refinement layer. This approach enables us to obtain a NeRF backbone that is not only faster but also more amenable to editing compared to traditional image space NeRF editing. Furthermore, we propose an improved loss function tailored for editing by migrating the delta denoising score (DDS) distillation loss, originally used in 2D image editing to the three-dimensional domain. This novel loss function surpasses the well-known score distillation sampling (SDS) loss in terms of suitability for editing purposes. Our experimental results demonstrate that ED-NeRF achieves faster editing speed while producing improved output quality compared to state-of-the-art 3D editing models. Code and rendering results are available at our project page1 © 2023, CC BY.

关键词： Distillation

Enhancing Performance of 3D Point Completion Network using Consistency Loss

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wijaya, Kevin Tirta Goenawan, Christofel Rio Kong, Seung-Hyun Computer Graphics Department Max Planck Institute for Informatics Saarbrücken66123 Germany Robotics Master Program KAIST Daejeon34051 Korea Republic of CCS Graduate School of Mobility KAIST Daejeon34051 Korea Republic of

Point cloud completion networks are conventionally trained to minimize the disparities between the completed point cloud and the ground-truth counterpart. However, an incomplete object-level point cloud can have multiple valid completion solutions when it is examined in isolation. This one-to-many mapping issue can cause contradictory supervision signals to the network because the loss function may produce different values for identical input-output pairs of the network. In many cases, this issue could adversely affect the network optimization process. In this work, we propose to enhance the conventional learning objective using a novel completion consistency loss to mitigate the one-to-many mapping problem. Specifically, the proposed consistency loss ensure that a point cloud completion network generates a coherent completion solution for incomplete objects originating from the same source point cloud. Experimental results across multiple well-established datasets and benchmarks demonstrated the proposed completion consistency loss have excellent capability to enhance the completion performance of various existing networks without any modification to the design of the networks. The proposed consistency loss enhances the performance of the point completion network without affecting the inference speed, thereby increasing the accuracy of point cloud completion. Notably, a state-of-the-art point completion network trained with the proposed consistency loss can achieve state-of-the-art accuracy on the challenging new MVP dataset. The code and result of experiment various point completion models using proposed consistency loss will be available at: https://***/kaist-avelab/ConsistencyLoss . © 2024, CC BY.

关键词： Cloud platforms