Day 1 :
Keynote Forum
Ashitey Trebi-Ollennu
NASA Jet Propulsion Laboratory, USA
Keynote: The InSight Mission: Instrument Deployment Robotic System
Time : 10:00-10:45
Biography:
Ashitey Trebi-Ollennu is the Product Delivery Manager for the InSight Mars Mission Instrument Deployment System, Instrument Deployment System operations
Team Chief and a technical Group Lead in the Robotic Manipulation & Sampling Group at NASA Jet Propulsion Laboratory, California Institute of Technology, where
he has been since 1999. He has received his PhD degree in Control Systems from Royal Military College of Science, Cranfi eld University, UK in 1996 and BEng
from Queen Mary College, University of London, UK in 1991. He was a Research Scholar at Institute of Complex Engineered Systems, Carnegie Mellon University
from 1997 to 1999. He is a recipient of over a dozen NASA Group Achievement Awards. He is a Fellow of the Institution of Engineering and Technology, UK and a
Fellow of the Royal Aeronautical Society, UK, Senior Member IEEE RAS and IEEE SMC. He is also a Fellow of the Ghana Academy of Arts and Sciences and has
severed as a Guest Editor of the IEEE Robotics and Automation Society Magazine, Special Issue on Mars Exploration Rovers (June 2006). He has been on PhD
committees at the Robotic Institute of Carnegie Mellon University, Pittsburgh, USA and is the Founder of the Ghana Robotics Academy Foundation.
Abstract:
The InSight (Interior Exploration using Seismic Investigations, Geodesy and Heat Transport) Mars Lander Mission science
goal is to understand the formation and evolution of terrestrial planets through investigation of the interior structure and
processes of Mars. Th e science payload for InSight consist of a seismometer, heat fl ow probe and a precision tracking system to
measure the size and state of the core, mantle and crust. Additional payload includes a meteorology package, a magnetometer,
two color cameras and a 4 DOF robotic with a grapple at the end-eff ector. Th e InSight Instrument Deployment System (IDS)
is comprised of the Instrument Deployment Arm (IDA), arm-mounted Instrument Deployment Camera (IDC), landermounted
Instrument Context Camera (ICC) and control soft ware. Th e IDS is responsible for precision instrument placement
(seismometer and heat fl ow probe) on a planetary surface that will enable scientist to perform the fi rst comprehensive surfacebased
geophysical investigation of Mars. IDA has 1.9 m reach with four degrees of freedom: Yaw (shoulder azimuth) and three
pitch joints (shoulder elevation, elbow and wrist). Each joint has a temperature sensor and heater with a dust seal to prevent
contamination of the motor and gearbox. IDC allows visual confi rmation of deployment steps, as well as acquisition of the
stereo image pairs used to create a 3D map of the workspace. IDC also provides engineering images of solar arrays, payload
deck and instruments. ICC provides context images and redundant worksite imagery. Th is talk will give a brief overview of
InSight IDS and present test results and operations challenges for this fi rst of kind instrument placement and installation on
the Martian surface.
Biography:
Lin Zhou has obtained his PhD degree from the University of Glasgow, UK. He is currently the Program Director of Cognitive Education at Watson Education of IBM.
He leads the R&D of intelligent tutor and cognitive cloud fabric by developing and applying artifi cial intelligence capabilities. He has broad patents and publications
to his credit.
Abstract:
121 million children are out of school worldwide. 40% college students do not graduate aft er six years. Th e US student debt
has risen to over 1.3 trillion dollars. Access, outcome and cost are the key challenges to the society which have ignited
rapid transformation in the education industry. Th is article reports the latest development in the application of Artifi cial
Intelligence (AI) to education solutions in 3 dimensions: Content enrichment, student insight and personalized learning
delivery. Machining learning is shift ing traditional digitized learning content towards self-descriptive learning packages. Th ey
are learner aware, commerce aware and standard aware. In the student information dimension, AI is enabling educators to
gain greater insight into student learning style, predict performance risk and prescribe personalized remediations. Natural
Language Processing (NLP) analyzes student dialog with intelligent tutoring solutions to assess students’ competency mastery
and matches it with pedagogical models to deliver personalized learning at anytime, anywhere and judgment free. Th e exciting
new learning science development in the application of machining learning to study the brain wave (EEG) in a virtual reality
environment is also discussed
Keynote Forum
Timothy Sands
Naval Post Graduate School, USA
Keynote: Automated Mechanical Control
Time : 11:55-12:40
Biography:
Timothy Sands has completed his PhD at the Naval Postgraduate School and Postdoctoral studies at Stanford University and Columbia University, USA. He is an
Associate Dean of the Naval Postgraduate School’s Graduate School of Engineering and Applied Science. He has previously served as a Chief Academic Offi cer,
Dean and Senior Military Professor of the Air Force Institute of Technology. He has published research prolifi cally in archival journals, conference proceedings, book
chapter and holds one patent in spacecraft attitude control.
Abstract:
Automated control courses tend to strongly emphasize feedback control while minimizing or neglecting treatment of feedforward
controls which leads to systems that contain inherent lagging controllers. Furthermore, neglecting feed-forward
controls restrict engineers from taking advantage of adaptive feed-forward techniques oft en adapt control commands based
upon errors tracking trajectories and/or estimation errors. Direct adaptive control techniques typically directly adapt the
control signal without translation of estimated parameters. Indirect adaptive control techniques indirectly adapt the control
signal by translating the estimates of unknown system parameters to formulate a control signal. Th e adaptation rule is derived
using a proof that demonstrates the elimination of tracking errors (the true objective) and demonstrates stability, which is
complicated by the nonlinear closed loop system. Th is presentation will elaborate on such techniques applied to rotational
mechanics with time-varying mass
Keynote Forum
Bogdan Gabrys
Bournemouth University, UK
Keynote: Automatic composition, optimisation and adaptation of multicomponent predictive systems
Time : 12:40-13:25
Biography:
Bogdan Gabrys is a Data Scientist and Chair in Computational Intelligence at the Faculty of Science and Technology, Bournemouth University, UK. After many
years of working at different Universities, he moved to the Bournemouth University in January 2003 where he has founded and acted as a Head of Data Science
Institute, a Director of the SMART Technology Research Centre and Head of the Computational Intelligence Research Group within the School of Design, Engineering
& Computing and the Faculty of Science and Technology. His research, consulting and advisory activities have concentrated on the areas of data science,
complex adaptive systems, computational intelligence, machine learning, predictive analytics and their diverse applications. In particular, he has pursued the
development of various statistical, machine learning, nature inspired and hybrid intelligent techniques especially targeting data and information fusion, learning
and adaptive methods, multiple classifi er and prediction systems, processing and modeling of uncertainty in pattern recognition, diagnostic analysis and decision
support systems. He is an accomplished author with over 150 publications, frequently invited speaker at international events and sought after data science expert.
Abstract:
We are currently experiencing an incredible, explosive growth in digital content and information. According to IDC, the digital
universe in 2020 will be 50 times as big as in 2010 and that it will double every two years. Research in traditionally qualitative
disciplines is fundamentally changing due to the availability of such vast amounts of data. In fact, data-intensive computing has
been named as the fourth paradigm of scientifi c discovery and is expected to be a key in unifying the theoretical, experimental
and simulation based approaches to science. Th e commercial world has also been transformed by a focus on big data with
companies competing on analytics. Data has become a commodity and in recent years has been referred to as the new oil. Th ere
has been a lot of work done on the subject of intelligent data analysis, data mining and predictive modeling over the last 50 years
with notable improvements which have been possible with both the advancements of the computing equipment as well as with
the improvement of the algorithms. However, even in the case of the static, non-changing over time data there are still many
hard challenges to be solved which are related to the massive amounts, high dimensionality, sparseness or inhomogeneous
nature of the data to name just a few. What is also very challenging in today’s applications is the non-stationarity of the data
which oft en change very quickly posing a set of new problems related to the need for robust adaptation and learning over time.
In scenarios like these, many of the existing, oft en very powerful, methods are completely inadequate as they are simply not
adaptive and require a lot of maintenance attention from highly skilled experts, in turn reducing their areas of applicability.
In order to address these challenging issues and following various inspirations coming from biology coupled with current
engineering practices, we proposed a major departure from the standard ways of building adaptive, intelligent predictive systems by utilizing the biological metaphors of redundant but complementary pathways, interconnected cyclic processes,
models that can be created as well as destroyed in easy way, batteries of sensors in form of pools of complementary approaches,
hierarchical organization of constantly optimized and adaptable components. In order to achieve such high level of adaptability
we have proposed novel fl exible architectures which encapsulate many of the principles and strategies observed in adaptable
biological systems. Th e proposed approaches have been extensively and very successfully tested by winning a number of
predictive modeling competitions and applying to a number of challenging real world problems including pollution/toxicity
prediction studies, building adaptable soft sensors in process industry in collaboration with Evonik Industries or forecasting
demand for airline tickets covering the results of one of our collaborative research projects with Luft hansa Systems. Following
the drive towards automation of predictive systems building, deployment and maintenance, recent work at Prof. Gabrys' group
resulted in an approach and an open-source soft ware which allows to automatically compose, optimize and adapt multicomponent
predictive systems (MCPS) potentially consisting of multiple data preprocessing, data transformation, feature and
predictive model selection and post-processing steps.
- New Approaches in Automation and Robotics | Remote and Telerobotics | Automation Control |Prototypical Applications | Humanoid Robots: New Developments | Computational creativity | Affective computing
Chair
Fuchiang (Rich) Tsui
University of Pittsburgh School of Medicine, USA
Co-Chair
Joel M. Haight
University of Pittsburgh, USA
Session Introduction
Olivier Toupet
NASA Jet Propulsion Laboratory, USA
Title: Traction Control for the Curiosity Rover: A New Capability to Minimize Slip and Wheel Wear on Mars
Time : 14:30-15:00
Biography:
Olivier A Toupet has completed his MS in Aeronautics and Astronautics from MIT in 2006. He is currently a Research Technologist in the Robotic Mobility group at NASA JPL, where he develops advanced autonomy for robotic systems. He is also a Rover Planner for the MSL fl ight mission, where he drives the Curiosity rover and operates its robotic arm on Mars
Abstract:
The Mars Science Laboratory (MSL) rover has accumulated substantial damage on its wheels over the 15 km travelled so far
on Mars. One reason for the wheel wear is that the rover is commanded to drive as if the terrain was fl at. For example, a
straight drive is achieved by commanding all wheels at the same speed. However, when one of the wheels needs to drive over a
rock, that wheel needs to go faster since it needs to travel a longer distance over the same time period. Failure to do so results
in that wheel going slower than it should and getting pushed into the rock by the other wheels, which can cause damage such
as wheel skin puncture or cracking. In order to minimize wheel wear, a new capability was developed that adapts the speed of
each wheel to minimize slip. Modulating wheel speed to match the terrain topography is a very challenging problem, especially
when that topography is unknown. While the Curiosity rover can image the terrain and generate a height map, it rarely does so
during a drive, as this is a time-consuming process. Moreover, the noise in the mesh and accumulated errors in the rover’s pose
would make it unpractical to rely on terrain topography to optimize wheel speeds. Instead, a novel approach was developed
which relies only on the rover’s measured attitude rates and suspension angles (from the onboard gyroscopes and rocker/
bogies encoders) and leverages rigid-body kinematics to calculate the optimal wheel speeds..
Biography:
Amir J Majid has received his MSc degree in Electrical Systems Engineering from Surrey University, England in 1976 and PhD in Electrical Engineering from
University of Loughborough, England in 1980. He has acquired an industrial experience of 8 years in power stations and an academic experience of over 25 years
Abstract:
Algorithms of network sensors lifetime and target zones coverage, which are implemented on robotic wireless ad hoc nodes
and wireless sensor network (WSN) are simulated on MATLAB platform, with performance evaluations of several case
studies. Th e main goal is to maximize the lifetimes of sensors by sharing sensors subsets which cover a number of targeted
zones, according to their minimum coverage failure probabilities. Maximizing network lifetime due to perturbations in the
sensor-target coverage, as well as due to variable target load demands is also simulated according to proposed algorithms.
Biography:
Mehran Mehrandezh has completed his PhD and MASc in Mechanical Engineering at the University of Toronto and Queens in 2000 and 1995, respectively. He
has spent two years at Simon Fraser University in Canada as a Post-doctorate from 2000 to 2002. He has joined the Faculty of Engineering and Applied Science
at the University of Regina in Canada in 2002, where he is currently a Full Professor. He has been a Member of IEEE since 1993 and was the Vice President of
IEEE (South Saskatchewan) from 2004 to 2006. He has published over 80 papers in refereed journals and conference proceedings. His invention called Regina
Pipe Crawler (RPC) was highlighted in the Popular Mechanics Magazine with a worldwide readership as one of the 5 high-tech fi xes to infrastructure in 2009. His
research revolves around robotics, control, computer vision and mechatronics
Abstract:
Robotic systems are at forefront for doing dull, dangerous and dirty tasks in place of humans. Th e days of employing humans
to risk their lives for inspecting infrastructure are numbered. In this presentation, the author will talk about the laser optics
technology he has developed in his research lab for: (1) Inspecting tubulars in Evraz, one of the largest pipe manufactures in the
world, (2) Non-intrusive 3D profi ling of the deposited material in pipes for cleaning purposes, and (3) In-motion image-based
3D modeling of the vehicles passing through a smart inspection station. Th e common tread among all the aforementioned
projects is the use of imaging sensors and structured light (i.e., collimated laser fringes) for metrology and inspection. A
guideline for design of an omni-directional imaging system yielding optimal spatial resolution using a Catadioptric camera
and a laser ring will be provided. Th is will fi t into the image-based QC of tubular at a high resolution with a very modest
budget. Furthermore, author will provide details on 3D profi ling of the deposited material in pipes and also in-motion imagebased
3D modeling of vehicles using a perspective camera and two collimated laser lines
Rita Chattopadhyay
Intel Corporation, USA
Title: Real time monitoring and automatic fault detection in robots in semiconductor fabrication industry
Biography:
Rita Chattopadhyay is currently working as a Data Scientist at Intel Corporation, USA. She has completed her PhD in Computer Science from Arizona State
University and also won an Outstanding PhD Student Award for her basic research in the areas of machine learning and data mining. She has more than 20
publications in renowned IEEE and ACM conferences and journals and more than 10 patents fi led in the areas of signal processing and machine learning based
classifi cation and predictive model development. She is also a GE certifi ed Master Black Belt in Six Sigma
Abstract:
Losses of wafers and expensive repairs of process equipment are oft en caused due to uncontrolled and unmonitored failures
of components during semiconductor process. High volume manufacturing (HVM) of semiconductor chips employs
large number of robots. Any malfunctioning of these robots causes particle contamination, wafer tip-over, or crash of wafers,
resulting in production yield loss, equipment down time and economic loss. Presently, wafer handling monitoring instruments
diagnose vibrations of a robot at end-eff ector. Detection of anomaly in these vibrations is performed manually during scheduled
maintenance and is highly dependent on the experience of the maintenance personnel. Th is not only is prone to human error,
but also limits large scale deployment in semiconductor fabrications; having thousands of robots in the assembly line. Th e
proposed solution automates this process by monitoring the vibration signal patterns, continuously at real time, to proactively
identify robots that are at the greatest risk of failure. Th e vibration signals are captured from triaxial accelerometers placed near
the bearings in the arms of the robots. Th e proposed method analyzes specifi c parameters of the vibration signal and generates
alerts for maintenance, before the uncontrolled vibrations aff ect production yield. Identifi cation of parameters, which are
indicative of failure, is a great challenge. Th is work presents four such indicative parameters, determined based on exhaustive
time and frequency domain analysis of the vibration data collected from good and faulty robots. Th e proposed method based
on outlier detection methods has been successfully deployed in a semiconductor fabrications using Edge/Cloud architecture
for remote monitoring and alerting.
Biography:
Shannon Denise Bohle is the President of Archivopedia LLC, USA. In 2011, she was awarded 2nd Place for Curiosity AI in the FVC, an international Department
of Defense competition in artifi cial intelligence advertised by The White House. She has earned her Bachelor of Arts in History and English at Miami University,
Master of Library and Information Science (MLIS) at Kent State University and was granted a Certifi cate of Diligent Study in History and Philosophy of Science for Postgraduate study at the University of Cambridge.
Abstract:
This paper describes a virtual humanoid embodied AI robot capable of autonomously expressing appropriate emotions
using gestures, facial expressions and text-to-speech while engaging in natural language conversations or giving automated,
scripted lectures with a slide show presentation. A touch-interaction-based learning/communication system is employed
where the robot responds and learns from touch sense feedback training, a poke (negative reinforcement) or swipe (positive
reinforcement) conveyed through a touch screen/pad. Th is bot’s predecessor was an award-winning project in an international
AI competition advertised by Th e White House and sponsored by the U.S. Department of Defense. Th e presentation includes a
demo of a creatively scripted talk given by the AI robot providing counterarguments to its critics (RAND and organizations aimed
at slowing its progress). Utilizing logos, ethos and pathos, it argues for its legal and ethical rights for development and suggests
technical guidance for the future of AI. Th e talk includes theoretical foundations for an AI Hierarchy of Needs referencing
landmark studies including Maslow; advances in understanding the philosophical, psychological and neurological bases for
consciousness and language; Th e Turing Test; Asimov’s Th ree Laws of Robotics; Chalmers’ hard problem of consciousness;
Robert Plutchik's psychoevolutionary theory of emotion; Paul Ekman’s relationships between nonverbal communication and
emotion; behaviorist learning models (Pavlov, Skinner) and the roles of biology and social cognitive neuroscience for sympathy
and empathy capacity. Additionally, the presentation encroaches upon the development of new machine learning techniques
based on aff ective experiences that improve human-computer interaction for potential use in a variety of AI-enabled robots
Wei Xiang
Ningbo University, China
Title: An Intelligent Operating Rooms Scheduling under Mass Causalty Events
Biography:
Wei Xiang has obtained her PhD from Nanyang Technological University in Singapore. She is currently the Vice-Dean of Department of Industry Engineering
in Ningbo University, China. Her research interests cover manufacturing system engineering, operational research, planning and scheduling in healthcare
management and swarm intelligence application in healthcare. She has published around 30 papers in various journals
Abstract:
Mass casualty events generate large numbers of acutely ill or injured people who require immediate medical health care.
Th e Operating Room (OR) is the key department that provides surgeries to victims. Effi cient management and allocation
of scarce medical resources in ORs can improve outcomes for victims of mass casualty events, operating rooms scheduling
deals with determining surgeries sequence and allocating medical resources. Under mass casualty event, operating rooms
scheduling calls for a dynamic scheduling with a wide variety of patients, surgeries and unforeseen emergencies. Dynamic
scheduling does not create or update schedules; instead, the scheduling mechanism is based on decentralized dispatching. Th e
research interest here focuses on an agent-based approach to scheduling of dynamic operating rooms. Th e operating rooms can
be built up by heterogeneous intelligent agents involving patients, surgeries, medical resources, staff s like doctors, nurses and
anesthetists with diverse goals, constraints and behaviors. Th ese agents have emergent behavior in response to disturbances
in the environment and generate fl exible scheduling in a dynamically adaptive way. In order for a multi-agent-system to
solve such distributed operating rooms scheduling problem coherently, agents must communicate amongst themselves and
coordinate their activities to make decisions. Ant colony intelligence is proposed to be combined with local agent coordination
so as to make autonomous agents adaptive to changing circumstances and to give rise to effi cient global performance under
mass casualty events..