检索结果-内蒙古大学图书馆

16th Brazilian Symposium on Robotics and 15th Workshop on Robotics in Education, SBR-WRE 2024

作者： Freiberger, Andrei Maximo, Marcos R.O.A. Loubach, Denis Autonomous Computational Systems Lab SP São José dos Campos Brazil Autonomous Computational Systems Lab Aeronautics Institute of Technology SP São José dos Campos Brazil Computer Science Division Aeronautics Institute of Technology SP São José dos Campos Brazil

ISBN: (纸本)9798350391084

This article presents the implementation of a real-time operating system (RTOS) on ITAndroids Small Size League (SSL) category robots, a significant advancement for the team’s participation in the Robocup SSL. The transition to using the STM32H753BI microcontroller and FreeRTOS on the second-generation Mainboard enhances temporal predictability and determinism, crucial for real-time systems. This development allows more efficient task management, including motor control, kicker charging, telemetry transmission, and fault handling, leading to improved robot performance and reliability during matches. The detailed system description and task implementation showcase how the Mainboard efficiently handles various functions such as motor control in a constant rate, responsive kicking mechanisms, and real-time telemetry collection and transmission. The work contributes by proposing a real-time operating system for a robot designed to participate in the RoboCup Small Size League (SSL). Despite the implementation being dependent on our team’s design decisions, the concepts presented here can be adapted by other teams. ©2024 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Improved Defensive Strategy in RoboCup Small Size League using Deep Reinforcement Learning

Improved Defensive Strategy in RoboCup Small Size League usi...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Adrisson R. Samersla Marcos R. O. A. Maximo Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division (IEC) Aeronautics Institute of Technology (ITA) São José dos Campos Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

The Small Size League (SSL) is one of the old-est leagues in RoboCup, an international scientific initiative whose objective is to advance the state-of-the-art in robotics. The matches are highly dynamic and competitive, an excellent environment to exercise and extend the latest decision-making techniques. In this work, we focus on the planning problem of the defense strategy in the SSL context. Our contribution lies in proposing a method for learning such behaviors using Deep Reinforcement Learning (DRL) algorithms. Through this technique, we intend to apply a more automated process than manually adjusting the heuristics used to handcraft such skills in code. For this purpose, the RoboCup Small Size League standard simulator grSim was adapted in order to implement a synchronous mode. Furthermore, we integrated this new simulator with ITAndroids team's code base and with the DRL algorithms provided by the Stable Baselines 3 library. With this setup, we successfully trained an agent using Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC), the state-of-the-art for continuous control reinforcement learning algorithms. Moreover, we demonstrate that the resulting policies outperform the hand-coded counterparts, showing potential to improve the team's overall defense strategy.

关键词： Codes Deep reinforcement learning Libraries Planning Reliability Robots Standards Optimization Sports Overfitting

来源：评论

学校读者我要写书评

暂无评论

Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning

Motion Consistency Loss for Monocular Visual Odometry with A...

引用

IEEE Latin American Robotics Symposium, LARS

作者： André O. Françani R. O. A. Marcos Maximo Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil

Deep learning algorithms have driven expressive progress in many complex tasks. The loss function is a core component of deep learning techniques, guiding the learning process of neural networks. This paper contributes by introducing a consistency loss for visual odometry with deep learning-based approaches. The motion consistency loss explores repeated motions that appear in consecutive overlapped video clips. Experimental results show that our approach increased the performance of a model on the KITTI odometry benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Firmware Based on Real-Time Operating System for Small Size League Robot

Implementation of Firmware Based on Real-Time Operating Syst...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Andrei Freiberger Marcos R. O. A. Maximo Denis Loubach Autonomous Computational Systems Lab São José Dos Campos SP Brazil Autonomous Computational Systems Lab Aeronautics Institute of Technology São José dos Campos SP Brazil Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

This article presents the implementation of a real-time operating system (RTOS) on ITAndroids Small Size League (SSL) category robots, a significant advancement for the team's participation in the Robocup SSL. The transition to using the STM32H753BI microcontroller and FreeRTOS on the second-generation Mainboard enhances temporal predictability and de-terminism, crucial for real-time systems. This development allows more efficient task management, including motor control, kicker charging, telemetry transmission, and fault handling, leading to improved robot performance and reliability during matches. The detailed system description and task implementation showcase how the Mainboard efficiently handles various functions such as motor control in a constant rate, responsive kicking mechanisms, and real-time telemetry collection and transmission. The work contributes by proposing a real-time operating system for a robot designed to participate in the RoboCup Small Size League (SSL). Despite the implementation being dependent on our team's design decisions, the concepts presented here can be adapted by other teams.

关键词： Motor drives Operating systems System performance Motors Real-time systems Hardware Telemetry Voltage control Robots Tuning

来源：评论

学校读者我要写书评

暂无评论

Feasibility-Aware Plan Adaptation in Humanoid Gait Generation

Feasibility-Aware Plan Adaptation in Humanoid Gait Generatio...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Michele Cipriano Marcos R. O. A. Maximo Nicola Scianca Leonardo Lanari Giuseppe Oriolo Dipartimento di Ingegneria Informatica Automatica e Gestionale Sapienza Università di Roma Italy Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology Brazil

Most available schemes used for humanoid walking rely on the separation into a planning phase, typically offline, and a Model Predictive Controller (MPC). Moreover, in order for the MPC to work in real time, simplifying assumptions are made both on the template model and on the constraints so that the underlying optimization problem is a Quadratic Programming (QP). The planner is unaware of the underlying humanoid dynamics and of any disturbance acting on the robot. We present an online Feasibility-Aware Plan Adaptation (FAPA) module which can locally adapt footsteps (positions, timings and orientation) in such a way that it guarantees feasibility of the subsequent Intrinsically Stable MPC (IS-MPC) stage. We present two versions of the proposed scheme: one with a fixed regions assignment for placing the footstep and another one where the regions are selected automatically through mixed-integer programming. Simulation results show the effectiveness of the FAPA scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry

Dense Prediction Transformer for Scale Estimation in Monocul...

引用

IEEE Latin American Robotics Symposium, LARS

作者： André O. Françani Marcos R. O. A. Maximo Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

Monocular visual odometry consists of the estimation of the position of an agent through images of a single camera, and it is applied in autonomous vehicles, medical robots, and augmented reality. However, monocular systems suffer from the scale ambiguity problem due to the lack of depth information in 2D frames. This paper contributes by showing an application of the dense prediction transformer model for scale estimation in monocular visual odometry systems. Experimental results show that the scale drift problem of monocular systems can be reduced through the accurate estimation of the depth map by this model, achieving competitive state-of-the-art performance on a visual odometry benchmark.

关键词： Visualization Robot vision systems Estimation Benchmark testing Predictive models Transformers Cameras

来源：评论

学校读者我要写书评

暂无评论

A Novel Line of Sight Constraint for Mixed-Integer Programming Models with Applications to Multi-Agent Motion Planning

A Novel Line of Sight Constraint for Mixed-Integer Programmi...

引用

European Control Conference (ECC)

作者： Angelo Caregnato-Neto Marcos R. O. A. Maximo Rubens J. M. Afonso Electronik Engineering Division Instituto Tecnológico de Aeronáutica (ITA) São José dos Campos Brazil Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Instituto Tecnológico de Aeronáutica (ITA) São José dos Campos Brazil

Mixed-Integer Programming (MIP) is an established method used to develop Multi-Agent System (MAS) motion planning algorithms under particular requirements, such as Line of Sight (LOS) connectivity. However, maintaining the tractability of the ensuing models is a known issue. In this paper, we propose a novel sufficient condition for LOS between agents of a MAS and discuss its implementation in a (MIP) model as constraints. The functionality of the proposal is demonstrated through simulations in a connectivity-constrained motion planning and decision-making problem. A comparison between the novel method and an earlier approach shows that the new proposal requires fewer optimization variables and constraints to be implemented. Finally, we employ Monte Carlo simulations to demonstrate that this reduction in the complexity of the models consistently decreases the time required to solve them.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Learning for Intelligent Surveillance

Semi-Supervised Learning for Intelligent Surveillance

引用

IEEE Latin American Robotics Symposium, LARS

作者： Guilherme Corrêa de Freitas Marcos R. O. A. Maximo Filipe A. N. Verri Computer Vision Department ALTAVE São José dos Campos SP Brazil Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology São José dos Campos SP Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

Semi-supervised Learning (SSL) has shown promising improvements when used for the Object Detection (OD) task. Existing works detected some unique challenges associated with this setting and discussed how they differ from the classification paradigm. In this work, we revisit two of the first approaches used for OD, namely, Self-Training and Augmentation driven Consistency (STAC) and Unbiased Teacher. Our work was made in partnership with ALTAVE, a Brazilian company focused on intelligent surveillance. By using their in-house dataset we show that relative performance refinement follows the findings from the original authors and propose an improved augmentation method that boosts both approaches, obtaining an overall improvement of 4.4% in the mAP, while using no additional labels for training.

关键词： Training Terminology Surveillance Object detection Companies Machine learning Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning

arXiv

引用

arXiv 2023年

作者： Müller, Jens Kühmichel, Lars Rohbeck, Martin Radev, Stefan T. Köthe, Ullrich Computer Vision and Learning Lab Heidelberg University Germany Division of Computational Genomics and Systems Genetics DKFZ Germany Department of Cognitive Science Rensselaer Polytechnic Institute NY United States

In this work, we analyze the conditions under which information about the context of an input X can improve the predictions of deep learning models in new domains. Following work in marginal transfer learning in Domain Generalization (DG), we formalize the notion of context as a permutation-invariant representation of a set of data points that originate from the same domain as the input itself. We offer a theoretical analysis of the conditions under which this approach can, in principle, yield benefits, and formulate two necessary criteria that can be easily verified in practice. Additionally, we contribute insights into the kind of distribution shifts for which the marginal transfer learning approach promises robustness. Empirical analysis shows that our criteria are effective in discerning both favorable and unfavorable scenarios. Finally, we demonstrate that we can reliably detect scenarios where a model is tasked with unwarranted extrapolation in out-of-distribution (OOD) domains, identifying potential failure cases. Consequently, we showcase a method to select between the most predictive and the most robust model, circumventing the well-known trade-off between predictive performance and robustness. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Thermal Modeling of Electric Motors Used in Very Small Size Soccer Robots

Thermal Modeling of Electric Motors Used in Very Small Size ...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Guilherme Reis Miguel Marcos R. O. A. Maximo Izabela Batista Henriques Autonomous Computational Systems Lab Computer Science Division Aeronautics Institute of Technology São Josè dos Campos SP Brazil Mechanical Engineering Division Aeronautics Institute of Technology São Josè dos Campos SP Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

This paper presents a study of the thermophysical properties of electric motors and of the structure of the robots used by ITAndroids' Very Small Size (VSS) team. To perform the modeling of the robot structure, the General Lumped Capacitance Analysis was used, assuming that the motor's internal temperature can be considered approximately uniform. This hypothesis was validated by means of Biot's Number, and the heat source term was evaluated in order to define which energy dissipation sources would be considered in the modeling. The obtained model was evaluated through numerical simulations to analyze the motors' temperature profile for different current values. We compared the obtained results with similar experiments found in the literature, concluding that the model could predict the system's behavior in a satisfactory manner. Therefore, this work contributes to the research area by providing a model able to predict the temperature of the electric motor under different workloads, thus, allowing the team to anticipate its overheating and prevent its premature burnout.

关键词： Analytical models Biological system modeling Windings Predictive models Capacitance Numerical models Thermal analysis

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：