检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Krinner, Maria Romero, Angel Bauersfeld, Leonard Zeilinger, Melanie Carron, Andrea Scaramuzza, Davide Institute for Dynamics Systems and Control ETH Zurich Switzerland Robotics and Perception Group University of Zurich Switzerland

Quadrotor flight is an extremely challenging problem due to the limited control authority encountered at the limit of handling. Model Predictive Contouring Control (MPCC) has emerged as a promising model-based approach for time optimization problems such as drone racing. However, the standard MPCC formulation used in quadrotor racing introduces the notion of the gates directly in the cost function, creating a multi-objective optimization that continuously trades off between maximizing progress and tracking the path accurately. This paper introduces three key components that enhance the state-of-the-art MPCC approach for drone racing. First and foremost, we provide safety guarantees in the form of a track constraint and terminal set. The track constraint is designed as a spatial constraint which prevents gate collisions while allowing for time optimization only in the cost function. Second, we augment the existing first principles dynamics with a residual term that captures complex aerodynamic effects and thrust forces learned directly from real-world data. Third, we use Trust Region Bayesian Optimization (TuRBO), a state-of-the-art global Bayesian Optimization algorithm, to tune the hyperparameters of the MPCC controller given a sparse reward based on lap time minimization. The proposed approach achieves similar lap times to the best-performing RL policy and outperforms the best model-based controller while satisfying constraints. In both simulation and real world, our approach consistently prevents gate crashes with 100% success rate, while pushing the quadrotor to its physical limits reaching speeds of more than 80km/h. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

RaNDT SLAM: Radar SLAM Based on Intensity-Augmented Normal Distributions Transform

RaNDT SLAM: Radar SLAM Based on Intensity-Augmented Normal D...

引用

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

作者： Maximilian Hilger Nils Mandischer Burkhard Corves Institute of Mechanism Theory Machine Dynamics and Robotics RWTH Aachen University Aachen Germany Chair of Perception for Intelligent Systems Munich Institute of Robotics and Machine Intelligence Technical University of Munich Munich Germany Chair of Mechatronics University of Augsburg Augsburg Germany

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Rescue robotics sets high requirements to perception algorithms due to the unstructured and potentially vision-denied environments. Pivoting Frequency-Modulated Continuous Wave radars are an emerging sensing modality for SLAM in this kind of environment. However, the complex noise characteristics of radar SLAM makes, particularly indoor, applications computationally demanding and slow. In this work, we introduce a novel radar SLAM framework, RaNDT SLAM, that operates fast and generates accurate robot trajectories. The method is based on the Normal Distributions Transform augmented by radar intensity measures. Motion estimation is based on fusion of motion model, IMU data, and registration of the intensity-augmented Normal Distributions Transform. We evaluate RaNDT SLAM in a new benchmark dataset and the Oxford Radar RobotCar dataset. The new dataset contains indoor and outdoor environments besides multiple sensing modalities (LiDAR, radar, and IMU).

关键词： Simultaneous localization and mapping Laser radar Radar measurements Motion estimation Noise Radar Transforms Gaussian distribution Sensors Trajectory

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning for Cooperative Vehicle Motion Control

Multi-Agent Reinforcement Learning for Cooperative Vehicle M...

引用

International Conference on Intelligent Transportation

作者： Kenan Ahmic Johannes Ultsch Jonathan Brembeck Darius Burschka Institute of System Dynamics and Control at the German Aerospace Center (DLR) Wessling Germany Chair of Robotics Artificial Intelligence and Embedded Systems Technical University of Munich (TUM) Munich Germany

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

The longitudinal and lateral low-level motion control of multiple vehicles within a platoon is a challenging task, since several different control objectives need to be solved: (i) Each vehicle in the platoon needs to follow the reference path, (ii) the leading vehicle needs to drive with a desired reference velocity, and (iii) the following vehicles need to maintain a safe spacing distance to their respective preceding vehicle. Typically, several distinct controllers are developed for each task individually, which increases both the engineering effort as well as the susceptibility to errors. We address this issue and present a cooperative low-level vehicle motion controller based on Multi-Agent Reinforcement Learning (MARL) that is able to solve all of the above-mentioned control objectives for both the leading vehicle and the following vehicles. Therefore, we apply parameter sharing within MARL to update a single control policy in a centralized fashion using the experiences of all vehicles in the environment. Additionally, we utilize the concept of agent indication during the training process and enable the policy to specialize on the control objectives of the vehicle it is currently controlling. This leads to a unifying control approach and makes the development of further controllers redundant. The simulative assessment demonstrates the effectiveness of learned policy and shows that it is able to successfully solve all of the above-mentioned control objectives for both vehicles roles, even on unseen paths.

关键词： Training Process control Reinforcement learning Drives Vectors Robustness Collision avoidance Intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

MMX Rover Locomotion Subsystem-Development and Testing towards the Flight Model

MMX Rover Locomotion Subsystem-Development and Testing towar...

引用

2022 IEEE Aerospace Conference, AERO 2022

作者： Barthelmes, Stefan Bahls, Thomas Bayer, Ralph Bertleff, Wieland Bihler, Markus Buse, Fabian Chalon, Maxime Hacker, Franz Holderried, Roman Langofer, Viktor Lichtenheldt, Roy Moser, Sascha Sasaki, Kaname Sedlmayr, Hans-Jurgen Skibbe, Juliane Stubbig, Leon Vodermayer, Bernhard Institute of System Dynamics and Control Munchener Str. 20 Weßling 82234 Germany Institute of Robotics and Mechatronics Munchener Str. 20 WeBling 82234 Germany Institute of Space Systems Robert-Hooke-Str. 7 Bremen28359 Germany

ISBN: (纸本)9781665437608

Wheeled rovers have been successfully used as mobile landers on Mars and Moon and more such missions are in the planning. For the Martian Moon eXploration (MMX) mission of the Japan Aerospace Exploration Agency (JAXA), such a wheeled rover will be used on the Marsian Moon Phobos. This is the first rover that will be used under such low gravity, called milli-g, which imposes many challenges to the design of the locomotion subsystem (LSS). The LSS is used for unfolding, standing up, driving, aligning and lowering the rover on Phobos. It is a entirely new developed highly-integrated mechatronic system that is specifically designed for Phobos. Since the Phase A concept of the LSS, which was presented two years ago [1], a lot of testing, optimization and design improvements have been done. Following the tight mission schedule, the LSS qualification and flight models (QM and FM) assembly has started in Summer 2021. In this work, the final FM design is presented together with selected test and optimization results that led to the final state. More specifically, advances in the mechanics, electronics, thermal, sensor, firmware and software design are presented. The LSS QM and FM will undergo a comprehensive qualification and acceptance testing campaign, respectively, in the first half of 2022 before the FM will be integrated into the rover. © 2022 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Teaching Concept for the Practical Application of Product Development and Project Management Methods 3rd

Teaching Concept for the Practical Application of Product De...

引用

3rd International Symposium on the Education in Mechanism and Machine Science, ISEMMS 2022

作者： Knobloch, Thomas Mandischer, Nils Merz, Judith Wiartalla, Jan Hüsing, Mathias Corves, Burkhard Lüke, Sebastian Kurtenbach, Stefan Paris, Jascha Institute of Mechanism Theory Machine Dynamics and Robotics RWTH Aachen University Eilfschornsteinstr. 18 Aachen52062 Germany TRAPO GmbH Industriestr. 1 Gescher-Hochmoor48712 Germany Demcon Systec Industrial Systems GmbH Wilhelm-Schickard-Str. 6 Münster48149 Germany

ISBN: (纸本)9783031257292

In the renewed master’s program in product development at RWTH Aachen University, a new teaching concept has been introduced with the course "Applied Design and Product Development I and II". Students can apply the knowledge they have acquired during their studies in the fields of design, product development and project management in an industry-oriented manner. Together with an industry partner from the mechanical engineering industry who provides a design assignment, the product development process takes place over the course of a year—from the blank sheet of paper to a finished prototype. The industrial partner benefits from the students’ knowledge and performance thanks to their advanced academic background and their ability to view the project from a different perspective. This results in a practical experience for the students. Thus, the course "Applied Design and Product Development I and II" represents a synergy for the university students and industrial researchers. In this paper, the teaching concept is presented based on the project task from 2020. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Product development

来源：评论

学校读者我要写书评

暂无评论

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learning

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem w...

引用

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

作者： Yifan Guo Zhongqiang Ren Chen Wang Flight Dynamics & Control/Hybrid Systems Lab Purdue University West Lafayette IN Robotics Institute Carnegie Mellon University Pittsburgh PA USA Department of Computer Science and Engineering Spatial AI & Robotics (SAIR) Lab University at Buffalo NY USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper considers a Min-Max Multiple Traveling Salesman Problem (MTSP), where the goal is to find a set of tours, one for each agent, to collectively visit all the cities while minimizing the length of the longest tour. Though MTSP has been widely studied, obtaining near-optimal solutions for large-scale problems is still challenging due to its NP-hardness. Recent efforts in data-driven methods face challenges of the need for hard-to-obtain supervision and issues with high variance in gradient estimations, leading to slow convergence and highly sub-optimal solutions. We address these issues by reformulating MTSP as a bilevel optimization problem, using the concept of imperative learning (IL). This involves introducing an allocation network that decomposes the MTSP into multiple single-agent traveling salesman problems (TSPs). The longest tour from these TSP solutions is then used to self-supervise the allocation network, resulting in a new self-supervised, bilevel, end-to-end learning framework, which we refer to as imperative MTSP (iMTSP). Additionally, to tackle the high-variance gradient issues during the optimization, we introduce a control variate-based gradient estimation algorithm. Our experiments showed that these innovative designs enable our gradient estimator to converge 20× faster than the advanced reinforcement learning baseline, and find up to 80% shorter tour length compared with Google OR-Tools MTSP solver, especially in large-scale problems (e.g. 1000 cities and 15 agents).

关键词： Urban areas Estimation Reinforcement learning Traveling salesman problems Internet Resource management Optimization Intelligent robots Faces Convergence

来源：评论

学校读者我要写书评

暂无评论

Lessons Learned from two Iterations of LLAMA, an Electrically Powered, Dynamic Quadruped Robot

Field Robotics

引用

Field robotics 2025年 2卷 325-355页

作者： Jay Jasper Ara Kourchians Mark Gonzalez Blair Emanuel John Nicholson Greg McCutcheon Max Austin Matt Kozlowski Emma Holmes Rachel Hegeman Stephen McCrory Michael Zeher David Handelman Robert Griffin Sisir Karumanchi Christian Hubicki Brett Kennedy Jonathan Clark Jerry Pratt Dilip Patel Jason Pusey Jet Propulsion Laboratory California Institute of Technology General Dynamics Land Systems STRIDe Lab Florida State University Optimal Robotics Lab Florida State University Applied Physics Laboratory John Hopkin's University Institute for Human and Machine Cognition U.S. Army Research Laboratory

This paper presents the design, control, and initial performance from two iterations of human-scale (∼75 kg) quadrupedal robots built under the U.S. Army Research Laboratory (ARL) robotics Collaborative Technology Alliance (RCTA) LLAMA (Legged Locomotion and Movement Adaptation) project. These all-electric, quadruped robots are designed with custom quasi-direct-drive actuators powering 3-DOF, serial-parallel legs. To our knowledge, this is the first all-electric quadruped robot of this mass scale. The centralized energy management system uses a capacitor bank to supply burst loads and buffer regenerated energy. A hierarchical control scheme enables rapid motions (up to 1.8 m/s) over a variety of terrains. The onboard sensing suite enables deliberate, autonomous operation across rubble fields. In addition, we report on practical observations, lessons learned from field testing of two generations of the platform, and current drawbacks, such as low absolute payload (9 kg) and battery life (35 minutes). These lessons include strategies to address secondary effects at larger scales and parameters with the most impact to improve future designs.

关键词： Robots Actuators Torque Legged locomotion Quadrupedal robots Batteries Foot Force Robustness Payloads

来源：评论

学校读者我要写书评

暂无评论

Qualification of the MMX Rover Locomotion Subsystem for the Martian Moon Phobos

Qualification of the MMX Rover Locomotion Subsystem for the ...

引用

IEEE Conference on Aerospace

作者： Stefan Barthelmes Ralph Bayer Wieland Bertleff Markus Bihler Fabian Buse Maxime Chalon Günther Geyer Franz Hacker Cynthia Hofmann Roman Holderried Alexander Kolb Erich Krämer Viktor Langofer Roy Lichtenheldt Sascha Moser André Fonseca Prince Kaname Sasaki Hans-Jürgen Sedlmayr Juliane Skibbe Bernhard Vodermayer German Aerospace Center (DLR) Institute of System Dynamics and Control Weßling German Aerospace Center (DLR) Institute of Robotics and Mechatronics Weßling German Aerospace Center (DLR) Institute of Space Systems Bremen

Planetary rovers have proven their function and value for the Earth moon as well as Mars in the past decades. While these celestial bodies have a gravity of the same order of magnitude as the Earth, wheeled locomotion has never been performed on a body with much lower gravity. Within the Japanese Martian Moon eXploration (MMX) mission, a wheeled rover will land on the Martian Moon Phobos with a gravity of about 1/2000 of the Earth gravity. The Robotic and Mechatronics Center of the German Aerospace Center (DLR-RMC) has designed and built the locomotion subsystem (LSS) for this rover. As the first ever driving gear for milli-gravity, the LSS needed to undergo a comprehensive qualification campaign. Due to the very challenging timeline of this project, the extent of the campaign needed to be carefully tailored to the needs of the mission. This work describes the concept of the verification including some crucial tailoring choices that have been made. The individual domains of verification are then described in detail with their scope, setup, procedure and results. The goal of this publication is to give a good overview and a detailed insight into the verification of the LSS for milli-gravity. Besides follow-up missions to Phobos, this work is also a good foundation for the qualification of future driving gears for low gravity environments or small rovers in general.

关键词： Earth Space vehicles Mars Mechatronics Gears Moon Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Low Friction Rigid-Soft Hybrid Mechanism for Hand Exoskeletons with Finite Element Analysis

Design and Evaluation of a Low Friction Rigid-Soft Hybrid Me...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Liu, Sihui Duan, Pu Han, Jianda Yu, Ningbo Nankai University College of Artificial Intelligence Tianjin300350 China Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300350 China Xeno Dynamics Co. Ltd Guangdong Shenzhen518055 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute Nankai University Guangdong Shenzhen518083 China

ISBN: (纸本)9781665481090

Hand exoskeletons are attracting rising research interest for assistance in daily life. Friction is a critical issue for hand exoskeletons intended to enable dexterous finger movements. This paper presents a rigid-soft hybrid assistive hand exoskeleton using a low friction mechanism based on the multi-layered springs with rolling contact. The low friction designs not only facilitate the high transparency of the device, but also the possibility of accurate modeling in mechanics. Regarding the large deformation nature of the nonlinear mechanism, finite element analysis (FEA) has been used to explore its kinematic and kinetic characteristics. Experiments were carried out on the implemented prototype to compare the numerical results with the measured. The results demonstrate that this modeling method can provide valuable guidance for better parameter selection and optimization. © 2022 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learning

arXiv

引用

arXiv 2024年

作者： Guo, Yifan Ren, Zhongqiang Wang, Chen The Flight Dynamics & Control/Hybrid Systems Lab Purdue University West LafayetteIN47907 United States Robotics Institute Carnegie Mellon University PittsburghPA15213 United States Lab Department of Computer Science and Engineering University at Buffalo NY14260 United States

关键词： Traveling salesman problem

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：