Real-time and high-precision situational awareness technology is critical for autonomous navigation of unmanned surface vehicles (USVs). In particular, robust and fast obstacle semantic segmentation methods are essential. However, distinguishing between the sea and the sky is challenging due to the differences between port and maritime environments. In this study, we built a dataset that captured perspectives from USVs and unmanned aerial vehicles in a maritime port environment and analysed the data features. Statistical analysis revealed a high correlation between the distribution of the sea and sky and row positional information. Based on this finding, a three-branch semantic segmentation network with a row position encoding module (RPEM) was proposed to improve the prediction accuracy between the sea and the sky. The proposed RPEM highlights the effect of row coordinates on feature extraction. Compared to the baseline, the three-branch network with RPEM significantly improved the ability to distinguish between the sea and the sky without significantly reducing the computational speed.
A Dual-Branch Framework for Semantic Change Detection with Boundary and Temporal Awareness
School of Information Science and Technology, Southwest Jiaotong University（信息科学与技术学院，西南交通大学）；School of Computer Science and Technology, Xidian University（计算机科学与技术学院，西安电子科技大学）
NavEYE: Vision-Centered Multi-Sensor Fusion-Based Situational Awareness System for Intelligent Surface Vehicles
Sanya Science and Education Innovation Park, Wuhan University of Technology（武汉理工大学三亚科教创新园）；School of Navigation, Wuhan University of Technology（武汉理工大学航运学院）；State Key Laboratory of Maritime Technology and Safety（船舶技术与安全国家重点实验室）
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Tongji University（同济大学）
Navigational perception for visually impaired people has been substantially promoted by both classic and deep learning based segmentation methods. In classic visual recognition methods, the segmentation models are mostly object-dependent, which means a specific algorithm has to be devised for the object of interest. In contrast, deep learning based models such as instance segmentation and semantic segmentation allow to individually recognize part of the entire scene, namely things or stuff, for blind individuals. However, both of them can not provide a holistic understanding of the surrounding…
We present a new four-pronged approach to build firefighter's situational awareness for the first time in the literature. We construct a series of deep learning frameworks built on top of one another to enhance the safety, efficiency, and successful completion of rescue missions conducted by firefighters in emergency first response settings. First, we used a deep Convolutional Neural Network (CNN) system to classify and identify objects of interest from thermal imagery in real-time. Next, we extended this CNN framework for object detection, tracking, segmentation with a Mask RCNN framework, an…
Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院人机与机器人研究所）；Sino-German School, Tongji University（同济大学中德学院）；Hangzhou SurImage Technology Company Ltd.（杭州 SurImage 科技有限公司）；Hangzhou KrVision Technology Company Ltd.（杭州 KrVision 科技有限公司）
Classic computer vision algorithms, instance segmentation, and semantic segmentation can not provide a holistic understanding of the surroundings for the visually impaired. In this paper, we utilize panoptic segmentation to assist the navigation of visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired efficiently. To this end, we propose an efficient Attention module -- Lintention which can model long-range interactions in linear time using linear space. Based on Lintention, we then devise a novel panoptic segmentation model which we ter…
Dynamic Topology Awareness: Breaking the Granularity Rigidity in Vision-Language Navigation
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空航天信息研究所）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
Autonomous Navigation of Cloud-Controlled Quadcopters in Confined Spaces Using Multi-Modal Perception and LLM-Driven High Semantic Reasoning
Department of Mechanical Engineering（机械工程系）；Rajshahi University of Engineering and Technology（拉贾沙希工程与技术大学）；Department of Industrial and Production Engineering（工业与生产工程系）；Shahjalal University of Science and Technology（沙赫jalal科学与技术大学）；Bangladesh University of Engineering and Technology（孟加拉工程与技术大学）；Department of Urban and Regional Planning（城市与区域规划系）；Department of Computer Science Engineering（计算机科学与工程系）；United International University（联合国际大学）
SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家重点实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究所）；The State Key Laboratory of Internet of Things for Smart City（智能城市物联网国家重点实验室）；Centre for Artificial Intelligence and Robotics（人工智能与机器人中心）；University of Macau（澳门大学）；Xiaomi EV（小i EV）；School of Automation（自动化学院）；Beijing Institute of Technology（北京理工大学）；Institute of Automation（自动化研究所）；Chinese Academy of Sciences（中国科学院）
School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；Rolls-Royce Plc（劳斯莱斯公司）；Rolls-Royce Derby（劳斯莱斯德比）
This paper presents a multi-sensor architecture with an adaptive multi-sensor management system suitable for control and navigation of autonomous maritime vessels in hazy and poor-visibility conditions. This architecture resides in the autonomous maritime vessels. It augments the data from on-board imaging sensors and weather sensors with the AIS data and weather data from sensors on other vessels and the on-shore vessel traffic surveillance system. The combined data is analyzed using computational intelligence and data analytics to determine suitable course of action while utilizing historica…
Sun Yat-sen University（中山大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Imitation learning for end-to-end autonomous driving has drawn attention from academic communities. Current methods either only use images as the input which is ambiguous when a car approaches an intersection, or use additional command information to navigate the vehicle but not automated enough. Focusing on making the vehicle drive along the given path, we propose a new navigation command that does not require human's participation and a novel model architecture called angle branched network. Both the new navigation command and the angle branched network are easy to understand and effective. …
In this paper, emerging deep learning techniques are leveraged to deal with Mars visual navigation problem. Specifically, to achieve precise landing and autonomous navigation, a novel deep neural network architecture with double branches and non-recurrent structure is designed, which can represent both global and local deep features of Martian environment images effectively. By employing this architecture, Mars rover can determine the optimal navigation policy to the target point directly from original Martian environment images. Moreover, compared with the existing state-of-the-art algorithm,…
Democritus University of Thrace（色雷斯德谟克利特大学）；Information Technologies Institute, The Centre for Research & Technology, Hellas（信息技术研究所，研究与技术中心，希腊）
This paper tackles the problem of positioning a swarm of UAVs inside a completely unknown terrain, having as objective to maximize the overall situational awareness. The situational awareness is expressed by the number and quality of unique objects of interest, inside the UAVs' fields of view. YOLOv3 and a system to identify duplicate objects of interest were employed to assign a single score to each UAVs' configuration. Then, a novel navigation algorithm, capable of optimizing the previously defined score, without taking into consideration the dynamics of either UAVs or environment, is propos…
Object navigation tasks require agents to locate specific objects in unknown environments based on visual information. Previously, graph convolutions were used to implicitly explore the relationships between objects. However, due to differences in visibility among objects, it is easy to generate biases in object attention. Thus, in this paper, we propose a directed object attention (DOA) graph to guide the agent in explicitly learning the attention relationships between objects, thereby reducing the object attention bias. In particular, we use the DOA graph to perform unbiased adaptive object …
Swiss Federal School of Technology in Lausanne - EPFL（洛桑联邦理工学院）；University of Tsukuba（筑波大学）；Swiss Federal School of Technology in Zurich - ETH Zurich（苏黎世联邦理工学院）
Autonomous navigation in highly populated areas remains a challenging task for robots because of the difficulty in guaranteeing safe interactions with pedestrians in unstructured situations. In this work, we present a crowd navigation control framework that delivers continuous obstacle avoidance and post-contact control evaluated on an autonomous personal mobility vehicle. We propose evaluation metrics for accounting efficiency, controller response and crowd interactions in natural crowds. We report the results of over 110 trials in different crowd types: sparse, flows, and mixed traffic, with…
University of New Mexico（新墨西哥大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Sandia National Labs（桑迪亚国家实验室）
Firefighting is a dynamic activity, in which numerous operations occur simultaneously. Maintaining situational awareness (i.e., knowledge of current conditions and activities at the scene) is critical to the accurate decision-making necessary for the safe and successful navigation of a fire environment by firefighters. Conversely, the disorientation caused by hazards such as smoke and extreme heat can lead to injury or even fatality. This research implements recent advancements in technology such as deep learning, point cloud and thermal imaging, and augmented reality platforms to improve a fi…
