2020 Fourth IEEE International Conference on Robotic Computing (IRC)最新文献_第5页

Design of Modular End-effector for Collaborative Robot based on Underactuated Mechanism 基于欠驱动机构的协作机器人模块化末端执行器设计

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00090

Hyeonjun Park, D. Kim, Bumjoo Lee

引用次数: 0

Energy-Aware Design of Vision-Based Autonomous Tracking and Landing of a UAV 基于视觉的无人机自主跟踪与着陆能量感知设计

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00054

G. Zamanakos, Adam Seewald, H. Midtiby, U. Schultz

{"title":"Energy-Aware Design of Vision-Based Autonomous Tracking and Landing of a UAV","authors":"G. Zamanakos, Adam Seewald, H. Midtiby, U. Schultz","doi":"10.1109/IRC.2020.00054","DOIUrl":"https://doi.org/10.1109/IRC.2020.00054","url":null,"abstract":"In this paper, we present the design and evaluation of a vision-based algorithm for autonomous tracking and landing on a moving platform in varying environmental conditions. We use an energy-aware approach, where the design of the algorithm is based on an evaluation of the energy consumption and Quality of Service (QoS) of each computational component. We evaluate our approach with an agricultural use case where a moving platform is tracked using a landing marker and the YOLOv3-tiny CNN is used to detect ground-based hazards. We perform all computations onboard using an NVIDIA Jetson Nano and analyse the impact on the flight time by profiling the energy consumption of the marker detection and the CNN. Experiments are conducted in Gazebo simulation using an energy modeling tool to measure the computational energy cost as a function of QoS. We test the energy efficiency and robustness of our system in various dynamic wind disturbances. We show that the marker detection algorithm can be run at the highest QoS with only a marginal energy overhead whereas adapting the QoS level of CNN results in a considerable power saving. The power saving is significant for a system executing on a fixed-wing UAV.","PeriodicalId":232817,"journal":{"name":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124195624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Non-Prehensile Manipulation Learning through Self-Supervision 自我监督下的非握握性操作学习

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00022

Ziyan Gao, A. Elibol, N. Chong

引用次数: 3

How to find assembly plans (fast): Hierarchical state space partitioning for efficient multi-robot assembly 如何找到装配计划(快速):高效多机器人装配的分层状态空间划分

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00034

A. Hoffmann, Ludwig Nägele, W. Reif

引用次数: 1

Using Active Vision for Enhancing an Surface-based Object Recognition Approach 利用主动视觉增强基于表面的目标识别方法

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00065

Dorian Rohner, D. Henrich

{"title":"Using Active Vision for Enhancing an Surface-based Object Recognition Approach","authors":"Dorian Rohner, D. Henrich","doi":"10.1109/IRC.2020.00065","DOIUrl":"https://doi.org/10.1109/IRC.2020.00065","url":null,"abstract":"For robots, the sensing of their surroundings is a necessary skill in nowadays tasks. One possible realization are one-shot object recognition methods. These may fail due to occlusions within the scene or because of objects that cannot be identified from only one view. This problem may be tackled by utilizing Active Vision methods, which means capturing additional information of the scene from different poses. In this paper, we contribute a novel approach with the goal of increasing the performance of an object recognition method. To do this, we try to identify so called regions of interest that the robot should inspect. We describe, how regions of interest can be determined and how possible views are calculated based on the current representation of the scene. On the one hand, we use the resulting additional views to generate new object hypotheses. On the other hand, they enable the validation of existing hypotheses. We test for each possible view whether it is reasonable regarding distance to the scene and occlusions. For remaining views, the corresponding pose as well as a quality measure is calculated and the best pose is selected as the next view. Evaluation results from our prototype system show that the classification rate increases with additional views.","PeriodicalId":232817,"journal":{"name":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115767990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

UAV Threat Level Assessment based on the Velocity and Distance from Collision 基于碰撞速度和距离的无人机威胁等级评估

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00094

Youlim Ko, K. Ho, Minji Lee, E. Matson

{"title":"UAV Threat Level Assessment based on the Velocity and Distance from Collision","authors":"Youlim Ko, K. Ho, Minji Lee, E. Matson","doi":"10.1109/IRC.2020.00094","DOIUrl":"https://doi.org/10.1109/IRC.2020.00094","url":null,"abstract":"With the growing interest in Unmanned Aerial Vehicles (UAV) complemented by its high functionality and easy accessibility, UAVs are now applied to a variety of fields from delivery services to military surveillance. As much as it holds potential in various positive applications, UAV-associated threats on sensitive facilities and public safety with its increased involvement in illegal activities and terrorist attacks have triggered active research in Counter-Uav(cuav) systems. The velocity of UAVs has a large impact on the collision distance between UAVs and facilities of importance, and with malicious intent, it could cause a disastrous outcome. In this paper, we propose a UAV threat assessment algorithm that classifies the threat level of UAVs based on the velocity change and distance from the facility of importance. The proposed algorithm was tested and compared with our previous algorithm through simulation. From the simulation results, we were able to confirm that analyzing the velocity and the type of velocity variation of a UAV based on its distance from the target can improve the accuracy of UAV threat assessment compared to our previous study that only utilized the different type of velocity variations. The results of this research are expected to be utilized in CUAV systems on predicting the threat of hostile UAVs and securing mitigation time to the posed threat, and research should further be continued on the velocity factor of UAV threat analysis.","PeriodicalId":232817,"journal":{"name":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125857359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Iterative Deep Fusion for 3D Semantic Segmentation 基于迭代深度融合的三维语义分割

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00067

Fabian Duerr, H. Weigel, M. Maehlisch, J. Beyerer

{"title":"Iterative Deep Fusion for 3D Semantic Segmentation","authors":"Fabian Duerr, H. Weigel, M. Maehlisch, J. Beyerer","doi":"10.1109/IRC.2020.00067","DOIUrl":"https://doi.org/10.1109/IRC.2020.00067","url":null,"abstract":"Understanding and interpreting a scene is a key task of environment perception for autonomous driving, which is why autonomous vehicles are equipped with a wide range of different sensors. Semantic segmentation of sensor data provides valuable information for this task and is often seen as key enabler. In this paper, we are presenting a deep learning approach for 3D semantic segmentation of lidar point clouds. The proposed architecture uses a range view representation of 3D point clouds and additionally exploits camera features to increase accuracy and robustness. In contrast to other approaches, which fuse lidar and camera feature maps once, we fuse them iteratively and at different scales inside our network architecture. We demonstrate the benefits of the presented iterative deep fusion approach over single fusion approaches on a large benchmark dataset. Our evaluation shows considerable improvements, resulting from the additional use of camera features. Furthermore, our fusion strategy outperforms the current state-of-the-art strategy by a considerable margin. Despite the use of camera features, the presented approach is also trainable solely with point cloud labels.","PeriodicalId":232817,"journal":{"name":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115233140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Coastal Infrastructure Monitoring through Heterogeneous Autonomous Vehicles 通过异构自动驾驶汽车监测沿海基础设施

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00019

Tauhidul Alam, Alexander Campaneria, Mathew Silva, Leonardo Bobadilla, G. Weaver

引用次数: 2

Comparison of Market-based and DQN methods for Multi-Robot processing Task Allocation (MRpTA) 基于市场和DQN的多机器人加工任务分配方法比较

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00060

Paul Gautier, J. Laurent, J. Diguet

引用次数: 5

Separation of Concerns Within Robotic Systems Through Proactive Computing 通过主动计算实现机器人系统中的关注点分离

2020 Fourth IEEE International Conference on Robotic Computing (IRC) Pub Date : 2020-11-01 DOI: 10.1109/IRC.2020.00039

Alexandre Frantz, D. Zampuniéris

{"title":"Separation of Concerns Within Robotic Systems Through Proactive Computing","authors":"Alexandre Frantz, D. Zampuniéris","doi":"10.1109/IRC.2020.00039","DOIUrl":"https://doi.org/10.1109/IRC.2020.00039","url":null,"abstract":"In this short paper, we first introduce a possible new model for designing and implementing software in robotic systems. This model is based on proactive scenarios, coded through dynamic sets of condition-action rules. Each scenario embeds the required rules and can be assembled dynamically with others, allowing the proactive system to achieve a unique objective or behavior and instruct the robot accordingly. Furthermore, a scenario is not aware of the existence of the other scenarios. In fact, it only contains information about a predefined central scenario, which oversees global decision making. In addition, each scenario knows where to enter its suggestions, thus allowing for a high degree in terms of separating concerns and modularity of code. Consequently, allowing easier development, testing and optimization of each scenario independently, possible reuse in different robots, and finally, a faster achievement of robust and scalable robotics software. We then show how to apply this programming model and its functionalities during runtime, by a proof of concept consisting of a virtual robot deployed in the Webots™ simulator. This simulator is controlled with four proactive scenarios (plus the central one), in charge of three different objectives.","PeriodicalId":232817,"journal":{"name":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","volume":"519 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123119172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2