Submodular Trajectory Optimization for Aerial 3D Scanning


  1. He also had a short but nice journey at University of Zurich & ETH
    Zurich where he was doing research on vision-based control for UAVs as a
    Postdoc researcher prior to joining the Hong Kong Polytechnic University
    (PolyU) in 2018.Dr. Lu was the Best Student Paper Award Finalist at the
    largest aerospace conference AIAA in 2014 and 2015. He was invited to be
    a session co-chair in AIAA GNC and IROS conferences. He was invited to
    give talks at several research institutes and served as reviewer for
    many journals such as Automatica, IEEE transactions on Control Systems
    Technology, and many conferences such as ICRA, AIAA and IFAC.附件:无

Gesture-based piloting of an aerial robot using monocular vision


Aerial robots are becoming popular among general public, and with the
development of artificial intelligence (AI), there is a trend to equip
aerial robots with a natural user interface (NUI). Hand/arm gestures are
an intuitive way to communicate for humans, and various research works
have focused on controlling an aerial robot with natural gestures.
However, the techniques in this area are still far from mature. Many
issues in this area have been poorly addressed, such as the principles
of choosing gestures from the design point of view, hardware
requirements from an economic point of view, considerations of data
availability, and algorithm complexity from a practical perspective. Our
work focuses on building an economical monocular system particularly
designed for gesture-based piloting of an aerial robot. Natural arm
gestures are mapped to rich target directions and convenient fine
adjustment is achieved. Practical piloting scenarios, hardware cost and
algorithm applicability are jointly considered in our system design. The
entire system is successfully implemented in an aerial robot and various
properties of the system are tested.

Published in: Robotics and Automation (ICRA), 2017 IEEE International


图片 1



control techniques for autonomous UAVs and robotics报 告 人:鲁鹏
control of aircraft has become more challenging due to the fact that the
aircraft structure is becoming increasingly complex and flexible
materials are being used. The need of developing more advanced motion
planning and control techniques is increasing. State-of-the-art motion
planning and control techniques are challenged by model uncertainties as
well as disturbances. How to design a robust motion planning and control
techniques is important.In ground robotics, research on control of the
whole-body dynamics has aroused a lot of attention but also met with
significant challenges. Take hydraulic robots for example, the dynamics
of these robots are fast and the control of these robots is affected by
the friction in the hydraulic actuators. Therefore, more advanced
control techniques should be designed to improve their performance and
also make them more autonomous.报告人简介:Dr. Peng Lu is an assistant
professor in Hong Kong Polytechnic University (PolyU) and interested in
research on control for various robotic platforms including Unmanned
Aerial Vehicles. He obtained his BSc degree in automatic control from
Northwestern Polytechnical University (NPU) in 二零零六 where he received
Excellent Undergraduate Student Award. Then he was mainly working on
optimization and control for aircraft in NPU and obtained his MSc degree
in 二〇一二 when he won Excellent Master Thesis Award. In 二〇一二, he continued
his journey on flight control and moved to 德尔夫t University of
Technology (TU 德尔夫t) where he received his PhD degree in 二〇一五. After
that, he shifted a bit from flight control and started to explore
control for ground robotics at ETH Zurich as a Postdoc researcher in

图片 2


Drones equipped with cameras are emerging as a powerful tool for
large-scale aerial 3D scanning, but existing automatic flight planners
do not exploit all available information about the scene, and can
therefore produce inaccurate and incomplete 3D models. We present an
automatic method to generate drone trajectories, such that the imagery
acquired during the flight will later produce a high- fidelity 3D model.
Our method uses a coarse estimate of the scene geometry to plan camera
trajectories that: (1) cover the scene as thoroughly as possible; (2)
encourage observations of scene geometry from a diverse set of viewing
angles; (3) avoid obstacles; and (4) respect a user-specified flight
time budget. Our method relies on a mathematical model of scene coverage
that exhibits an intuitive diminishing returns property known as
submodularity. We leverage this property extensively to design a
trajectory planning algorithm that reasons globally about the
non-additive coverage reward obtained across a trajectory, jointly with
the cost of traveling between views. We evaluate our method by using it
to scan three large outdoor scenes, and we perform a quantitative
evaluation using a photorealistic video game simulator.






Autonomous multi-floor indoor navigation with a computationally constrained MAV


In this paper, we consider the problem of autonomous navigation with a
micro aerial vehicle (MAV) in indoor environments. In particular, we are
interested in autonomous navigation in buildings with multiple floors.
To ensure that the robot is fully autonomous, we require all computation
to occur on the robot without need for external infrastructure,
communication, or human interaction beyond high-level commands.
Therefore, we pursue a system design and methodology that enables
autonomous navigation with real time performance on a mobile processor
using only onboard sensors. Specifically, we address multi-floor mapping
with loop closure, localization, planning, and autonomous control,
including adaptation to aerodynamic effects during traversal through
spaces with low vertical clearance or strong external disturbances. We
present experimental results with ground truth comparisons and
performance analysis.

Published in: Robotics and Automation (ICRA), 2011 IEEE International



Waypoint navigation of quad-rotor MAV


Quad-rotor Micro Aerial Vehicle (MAV) is a multi-rotor MAV with 4
propellers which propel the MAV up to the air and move around. It has
high maneuverability to move around, such as roll, pitch and yaw
movements. However, line of sight and radio control effective range are
the major limitation for the MAVs which significantly shorten the travel
distance. Therefore, we proposed a waypoint navigation quad-rotor MAV
based on PID controller in this paper. User can set mission with
multiple waypoint and the PID controller to control MAV autonomously
moving along the waypoint to the desired position without remotely
controlled by radio control and guidance of pilot. The results show PID
controller is capable to control MAV to move to the desired position
with high accuracy. As the conclusion, the result of real flight
experiment shows that the %OS of designed PID controller for x is 13%
while y is 11.89% and z is 2.34%. Meanwhile, steady-state error for all
axis are 0%. This shows that the performance of PID controller is
satisfied. Hence, the quadrotor MAV could move to the desired location
via waypoint navigation without guidance of pilot.

Published in: System Engineering and Technology (ICSET), 2017 7th IEEE
International Conference


图片 3


Modeling and control of an interactive tilt-rotor MAV


来源:2017 4th International Conference on
Information Science and Control Engineering




Real-Time Onboard Mapping and Localization of an Indoor MAV Using Laser Range Finder


In this paper, we focus on the problem of micro aerial vehicle’s (MAV’s)
localization in unknown, GPS-denied indoor condition. For this problem,
we present a system to obtain the pose estimation and the occupancy grid
map of the environment by using laser range finder. In addition, to
improve the accuracy and robustness of tracking algorithm, we design a
method by fusing the pose estimation from SLAM with IMU data.
Furthermore, because of the length of the corridor may exceed the
measurement range of the laser range finder, we specifically put forward
an approach by fusing optical flow and IMU to compensate the error for
this. Plenty of real flights and static precision experiments have
proved the validity and accuracy of the proposed method.


 Information Science and Control Engineering (ICISCE), 2017 4th
International Conference


weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming


Selective weed treatment is a critical step in autonomous crop
management as related to crop health and yield. However, a key challenge
is reliable and accurate weed detection to minimize damage to
surrounding plants. In this letter, we present an approach for dense
semantic weed classification with multispectral images collected by a
micro aerial vehicle (MAV). We use the recently developed
encoder–decoder cascaded convolutional neural network, SegNet, that
infers dense semantic classes while allowing any number of input image
channels and class balancing with our sugar beet and weed datasets. To
obtain training datasets, we established an experimental field with
varying herbicide levels resulting in field plots containing only either
crop or weed, enabling us to use the normalized difference vegetation
index as a distinguishable feature for automatic ground truth
generation. We train six models with different numbers of input channels
and condition (fine tune) it to achieve ∼0.8 F1-score and 0.78 area under the
curve classification metrics. For the model deployment, an embedded
Graphics Processing Unit (GPU) system (Jetson TX2) is tested for MAV
integration. Dataset used in this letter is released to support the
community and future work.

Published in: IEEE
Robotics and Automation
 ( Volume: 3, Issue:
, Jan.
2018 )


图片 4