AM-Traj is a C++11 header-only library for generating large-scale piecewise polynomial trajectories for aggressive autonomous flights, with highlights on its superior computational efficiency and simultaneous spatial-temporal optimality. Besides, an extremely fast feasibility checker is designed for various kinds of constraints. All components in this framework leverage the algebraic convenience of the polynomial trajectory optimization problem, thus our method is capable of computing a spatial-temporal optimal trajectory with 60 pieces within 5ms, i.e., 150Hz at least. You just need to include “am_traj.hpp” and “root_finder.hpp” in your code. Please use the up-to-date master branch which may have a better performance than the one in our paper. Author: Zhepei Wang and Fei Gao from the ZJU Fast Lab. Related Papers: • Alternating Minimization Based Trajectory Generation for Quadrotor Aggressive Flight, Zhepei Wang, Xin Zhou, Chao Xu, Jian Chu, and Fei Gao, submitted to RA-L/IROS 2020. • Detailed Proofs of Alternating Minimization Based Trajectory Generation for Quadrotor Aggressive Flight, Zhepei Wang, Xin Zhou, Chao Xu, and Fei Gao, the supplementary material. Video Links: youtube or bilibili
ccxu
浙江大学控制科学与工程学院(下面简称控制学院)始建于1956年,建有控制科学与工程、网络空间安全(共建)2个一级学科,其中控制科学与工程学科1988年被确定为国家重点学科,2007年被批准为国家一级重点学科,是国家首批一级学科博士授予点;拥有“工业控制技术国家重点实验室”“工业自动化国家工程研究中心”“工业控制系统安全技术国家工程实验室”和“流程质量优化与控制国际联合研究中心”4个国家级平台和多个省部级基地;2017年,入选国家“双一流”学科建设名单,第四轮全国学科评估为“A+”。 无人系统与自主计算实验室(Field Autonomous Systems & compuTing)主要方向:1)智能无人系统;2)工业智能技术。现承担国家重点研发计划项目(科技部)、工业互联网创新发展工程项目(工信部)、基金项目(国家自然科学基金委)、国家电网项目、大疆(DJI)联合研发项目等;实验室与产业界合作密切、与国外同类顶尖实验室保持紧密合作关系;曾获国际空中机器人大赛冠军(2014年 – 2018年第七代任务)、DJI机甲大师全球人工智能挑战赛一等奖(2019年)、世界机器人帆船大赛总冠军(2019年)等荣誉。更多信息请访问:www.kivact.com。目前招聘博士后若干名,研究方向为 无人系统实时导航与控制(运动控制、视觉导航、轨迹规划等) 工业智能系统与信息处理(工业视觉、机器学习、控制系统等) 申请条件(应同时具备) 欢迎控制、应用数学、计算机、电子信息、电气、机械、航空航天等(但不限于以上)跨学科优秀博士毕业生联系申请。 具有良好师德师风,有较好的学术发展潜力和合作精神。 申请者一般应为毕业3年内的优秀博士毕业生,身体健康,年龄原则上不超过35周岁。 工作待遇 博士后年薪一般为15 – 30万,学院提供一定的科研启动经费。 博士后在站时间由学院、合作导师和博士后本人根据研究项目和内容需要在2 – 6年内灵活确定,在站期间可申请租住学校教师公寓,人事关系进入学校后从事博士后研究工作3年及以上的博士后,可按学校相关规定申报学校高级专业技术职务。 学校和学院鼓励博士后出站后积极应聘校内外专业技术岗位,并将博士后作为学校教学、科研、成果转化等岗位选聘的重要来源。 鼓励和支持博士后研究人员申报博士后国际交流计划、博士后科学基金以及其他国家与地方的科技项目和博士后资助项目。 材料(含简历、代表作)请寄wuwenjuan@zju.edu.cn,并注明“FAST-Lab Postdoc Application”,招满为止;咨询请联系cxu@zju.edu.cn(许超)、fgaoaa@zju.edu.cn(高飞)
ZJU was founded in 1897, which is one of the oldest and most prestigious institutions of higher education in China. It is considered a top university in the Chinese mainland, which is ranked #6 in Asia and #54 worldwide according to the QS University Rankings for 2020. The FAST Lab is the recipients of the Champion of the International Aerial Robotics Competition (2018), the First Prize of the DJI RoboMaster AI Global Challenges (2019), as well as the Champion of the World Robotic Sailing Competition (2019). The FACT Lab has a close collaborative relationship with industrial companies such as the Supcon and the DJI, etc. For more information about the FAST Lab, please visit www.kivact.com. The FAST Lab is calling for applications for several postdoc positions in the areas of unmanned systems (e.g., mechatronic control, autonomous navigation & planning) and industrial intelligence (e.g., industrial vision systems, machine learning and control systems). Successful applicants should hold a Ph.D. in the areas of engineering or science disciplines, such as control science & engineering, robotics, applied math, computing, electrical engineering, electronics, mechanical & aerospace engineering, but not limited to these. Application packages should send a CV and sample publications to wuwenjuan@zju.edu.cn entitled by “FAST Postdoc Application”. Positions remain open until filled. If you have any questions regarding the postdoc positions, please do not hesitate to contact cxu@zju.edu.cn (Chao Xu) and fgaoaa@zju.edu.cn (Fei Gao). The Chinese version is available on this page.
Chao Xu received a congratulatory letter from Ruben Barrera-Michel, Chair of IEEE Admission and Advancement Committee, mentioning that Chao Xu was elevated to the IEEE Senior member.
ZMART received an A rating in the technical solution evaluation of the 2020 Robomaster AI Challenge won an AI robot as a reward. For more information about RoboMater AI Challenge, please refer to this link.
F. Gao, L. Wang, B. Zhou, L. Han, J. Pan and S. Shen’s work on ‘Teach-Repeat-Replan: A Complete and Robust System for Aggressive Flight in Complex Environments’ is conditionally accepted by IEEE Transactions on Robotics (T-RO). Introduction Teach-Repeat-Replan is a complete and robust system enables Autonomous Drone Race. It contains all components for UAV aggressive flight in complex environments. It is built upon the classical robotics teach-and-repeat framework, which is widely adopted in infrastructure inspection, aerial transportation, and search-and-rescue. Our system can capture users’ intention of a flight mission, convert an arbitrarily jerky teaching trajectory to a guaranteed smooth and safe repeating trajectory, and generate safe local re-plans to avoid unmapped or moving obstacles on the flight. Code: https://github.com/USTfgaoaa/Teach-Repeat-Replan/
Jiaming Liang’s article entitled “Filtering enhanced tomographic PIV reconstruction based on deep neural networks” has been accepted for oral presentation by the committee of the International Symposium on High-Fidelity Computational Methods & Applications 2019, which will be held in Shanghai during December 14-16, 2019. The symposium is to enhance deployment and applications of the high-fidelity methods in complex industrial fluid flows. (For more information, please refer to https://www.ishfcma.org/ ).
ZMART is the abbreviation for the ZJU Micro-Aerial Robotics Team, majorly for the International Aerial Robotics Competition in the Asia-Pacific Venue. ZMART won the Best System Design Award (2015 in Beihang University) and the First Prize Award (2016 in Beihang University). 2018年8月27日,经国际空中机器人大赛(IARC)委员会评定,浙江大学代表队ZMART以综合评分第一、比赛成绩第一,获得IARC第七代任务世界冠军,赢得2万美元比赛奖金。浙江大学成为继斯坦福大学(1995),卡耐基梅隆大学(1997),柏林工大(2000),佐治亚理工(2008),麻省理工(2009),清华大学(2013)之后IARC第七个世界冠军得主。自此第七代任务结束,IARC比赛进入第八代任务。更多信息,请见页面:ZMART made a record in the IARC history Team Structure for 2017 总体组:王宏达、翁一桢、邱炜、万旭东、郭磊、叶鸿凯 感知组:朱疆成、崔粲、茹祥宇、朱均、汪哲培、王琦 ZMART featured in media 2016, ZMART Featured in Media ZMART Performance video 2016 IARC Official Results 2016 IARC Performance Collection – ZMART ZMART 2017 Trailer – We need you Award 2015 – the Best System Design Award 最佳系统设计 2016 – the First Prize (the Asia-Pacific Venue) 亚太赛区冠军 2017 – the First Prize (the Asia-Pacific Venue) 亚太赛区冠军 Competition 2016 the First Prize in the Asia-Pacific Venue 指导老师:许超、张宇 队员:王宏达、翁一桢、叶波、茹祥宇、朱均、万旭东、朱疆成、崔粲、邱炜、郭磊 Technical Progress: Visual Odometry, Boundary Detection (SVM), Dynamic Approaching (DP), Reinforcement Learning Platform: DJI M100 Task Computer: Intel NUC i5 Navigation: DJI Guidance / Hokuyo UTM-30LX Vision: Bluefox 2015 Best System Design Award in the Asia-Pacific Venue 指导老师:许超、王伟、张宇 队员:崔粲、叶长春、王宏达、翁一桢、叶波、邱炜、朱疆成、茹祥宇、黄永斌 Technical Progress: Visual Tracking to Moving Target Platform: X650 Carbon Flight Controller: Pixhawk Propulsion: T-Motor Power: ACE Navigation: Hokuyo URG-04LX / PX4-Flow Vision: Bluefox 2014 指导老师:许超 队员:秦通、翁一桢、娄常绪、黄夏楠、刘昊俣、王钟雷、陈乙宽、叶长春、朱疆成、韩滔 Technical Progress: 3D printing, ROS Platform: X650 Carbon Flight Controller: DJI Wookong Task Computer: Intel NUC i5 Propulsion: HLY / HobbyWing Power: ACE Navigation: Hokuyo UTM-30LX / Ultrosonic Sensor Vision: USB camera 2012 指导老师:许超 队员:崔粲、朱疆成、邱炜、俞中杰、王文龙、韩滔、张泉泉 Technical Progress: Flight Control, SLAM, Auto-exploration, Visual Tracking Platform: X650 Task Computer: ARM cortex A9 Flight Computer: Yutu Propulsion: 新西达(XXD) / (好盈)HobbyWing Navigation: Hokuyo UTM-30LX / Ultrosonic Sensor Power: […]
Approach one: Variational optical flowIntroductionIn this project, we propose a novel optical flow formulation for estimating two-dimensional velocity fields from an image sequence depicting the evolution of a passive scalar transported by a fluid flow. This motion estimator relies on a stochastic representation of the flow allowing to incorporate naturally a notion of uncertainty in the flow measurement. The Eulerian fluid flow velocity field is decomposed into two components: a large-scale motion field and a small-scale uncertainty component. We define the small-scale component as a random field. Subsequently, the data term of the optical flow formulation is based on a stochastic transport equation, derived from the formalism under location uncertainty proposed in Mémin (2014) and Resseguier et al. (2017a). In addition, a specific regularization term built from the assumption of constant kinetic energy involves the very same diffusion tensor as the one appearing in the data transport term. Opposite to the classical motion estimators, this enables us to devise an optical flow method dedicated to fluid flows in which the regularization parameter has now a clear physical interpretation and can be easily estimated. Experimental evaluations are presented on both synthetic and real-world image sequences. Results and comparisons indicate a very good performance of the proposed formulation for turbulent flow motion estimation.
IntroductionThis project mainly studies on the observation and motion parameters reconstruction of flapping flight, the stability analysis of insects hovering, and the flapping mechanisms design for the PIV experiments, aiming to improve the existing hull reconstruction and pose estimation algorithms, propose the analysis method of insect hovering under the active control under varying flapping frequency, and design flapping mechanisms with multiple freedoms for PIV experiments to implement more fined motion. As for hull reconstruction and pose estimation, the project reconstruct the hull of insect under the assumption that the insect body is rigid and its section is elliptical with the data of body radius, centerline and the wing outline. As for the experimental flapping motion system design, this project analyzes the design principles and keeps the Reynolds number and Strouhal number same in the real and experimental environment respectively, and describes how to the design bee-like and dragonfly-like flapping mechanisms and how the mechanisms are driven.Paper1.Y. Huang, J. Liang and C. Xu. Sability of the flapping-wing vehicle near hovering under active control by varying flapping frequency [C]. The Chinese Congress of Automation 2017, Jinan, Shandong, China, October 21-22, 2017.