A paper is conditionally accpeted by IEEE T-RO

December 2nd, 2019
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).

Jiaming Liang is going to give an oral presentation for HIFICOMA 2019

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/ ).


Teach-Repeat-Replan

Introduction

A robust system that can enable small quadrotors to fly fully autonomously at high speeds in complex environments with only vision and imu. For non-professionals, it will be helpful that the drone is capable of executing the mission autonomously after being easily taught how to fly by human, while being able to avoid obstacles when flying. Our system contains all components including hardwares and softwares which has accurate and fast vision-imu based locallization, mapping, safe flight corridor generating, global/local motion planning and high performance flight controller to perform this task. the drone can fly at high speed reliably in a complex GPS-denied indoor environment, and relys on only onboard components on a 250mm frame while flying.


Zhejiang University Aerial Robotics Team

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:http://www.kivact.com/2018/08/31/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

ZMART Performance video


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: ACE

Research Prototype

Battlecruiser

“Battlecruiser operational.”

IARC 2016 and 2017 main competition platform.

Science Vessel

“Explorer reporting.”

Human In The Loop (HITL) research, keyboard operation (get out of RC controller), video and sensor data real-time transmission, manipulator installed.

Wraith

“Wraith awaiting launch orders.”

Flight control, servo, formation, basic HITL, aerial carrier.

Observer

“I sense a soul in search of answers.”

Indoor formation, swarm, aerial carrier,

Overlord

“Hmm…..”

Parallel arm, manipulator.

Research Area

Dynamics and Control: Design and Modelling, Disturbance Control, Trajectory Generation, Formation

Environment Sensing: Computer Vision, Machine Learning, Detection and Tracking, Visual Odometry, SLAM

Artificial Intelligence: Reinforcement Learning, Deep Learning, Human in the Loop, Situation Awareness


UAVs formation flight test

Indoor + Dual machine

Outdoor+ Multi-machine

Formation:

one-word sweep, triangle formation, lead follower, lock hover

Cluster

  • Relative independence of communication architecture
  • Single agent with unique functionally
  • Ability to compete tasks off the ground in clusters

Zhejiang University's 120th Anniversary Formation


6 DOF power system

Zero attitude trajectory tracking

8-shaped track + Heading keeping

Maneuver while hovering

S-shaped track + Spin swing


Observation and motion reconstruction of flapping flight

Introduction
This 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.
Paper
1.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.