4^th World Congress on Robotics and Artificial Intelligence October 23-24, 2017 Osaka, Japan

Biography:

Mathew Holloway has completed his education in Engineering and Design at Bath University (MEng), The Royal College of Art and Imperial College London (Joint Masters, MA and MSc). He has also been the founder of three high tech start-ups where he has taken his ideas into the market place, securing accreditation, sales and the trade sale of his last venture.

Abstract:

This paper focuses on the application of robotic technologies for the retrofit of thermal insulation under suspended timber floors. Across Northern Europe, there is a large proportion of older, hard to treat homes which remain cold and uncomfortable in winter due to the lack of adequate thermal insulation. In the UK alone, there are as many as 10 million homes with an uninsulated floor that can contribute as much as 40% of the draughts and 25% of the heat loss for a typical dwelling. Traditional methods require the floor to be lifted and insulation panels to be cut and fit by hand. This provides an excellent opportunity for a robotic device to remotely apply insulation in situ, without the hassle and expense of traditional methods. However, the application is particularly demanding as the physical attributes of underfloor voids are highly variable and access has to be achieved through small openings formed in the wall or floor. Once access has been achieved, the void space needs to mapped, navigated and the thermal insulation material applied in an appropriate manner. A review of mobile robotic platforms for this application was conducted before an innovative reconfigurable robotic solution was developed. The design of the resulting solution used a new approach for robotics that combines stage gate and agile product development methodologies, in order to increase the speed of development. The resulting robot is capable of spraying a typical underfloor void in approximately four hours, with reliable operation. To date over one hundred commercial installations have been completed indicating the robustness of the solution developed. The impact on the resident, building and energy usage has been assessed with data logging and calculation of heat transfer using ISO-13370 for selected sites to quantify the benefit for using robotics in this application. 

Biography:

Anjali Vishwas Kulkarni is working as Principal Research Engineer at the Centre for Mechatronics, IIT Kanpur. She has completed her PhD in Electrical Engineering. She has written two book chapters and has published several papers. She has reviewed several papers for various international journals. She holds Membership of IETE, ISAMPE and RSI.

Abstract:

Technology is all pervading in today’s world. Hence, learning and development of technological skills is very important. This can be achieved with a paradigm shift of using Technology based science education. Most gadgets and equipment today are mechatronic devices. Mobile technology is one such example which has made tremendous impact on our life style. Mechatronics is a design practice in applying mechanical engineering, control theory, computer science, electronics and electrical engineering, sensor and actuator technologies to improve products or processes. This technology has produced many new products and provided powerful ways of improving the efficiency of the products. The lecture will discuss about the present scenario, the research experience and the future trends in this area. The applications of Mechatronics in the fields such as medical, material handling, military, rescue operations and industry automation will be discussed. Some of the facilities at IIT Kanpur useful in realizing these research trends will be touched upon. On-line courses on robotics and mechatronics for teachers of IIT’s, NIT’s and Government Engineering colleges have been under consideration for making Mechatronics more popular and penetrating. This will in turn foster the government mandate of Digital India. Another aspect of mechatronics being explored is in providing the hands-on technical education for students through numerous workshops. This is proving to be fruitful in generating the technological awareness and interest. Mechatronics being the applied subject is very challenging with many entrepreneur potentials. Graduate students, women and men alike, can come forward to initiate small-scale business in one of the many aspects of the mechatronic product, these are: over-all design process, mechanical design, manufacturing, programming, electronics and electrical control, sensors design and fabrication, to name a few. Government is also promoting the establishment of startups and facilitating the overall process. In my opinion, national development in every sense is through the use and development of technologies and the gateway to this progress leads through the Mechatronics.

Biography:

Ben M Chen is currently a Professor and Provost's Chair in the Department of Electrical and Computer Engineering, National University of Singapore. He is also serving as the Director of NUS ECE Control, Intelligent Systems and Robotics Area and Head of Control Science Group, NUS Temasek Laboratories. His current research interests are in unmanned systems, robust control, control applications and financial market modeling. He is an IEEE Fellow and has published more than 400 journal and conference articles and a dozen research monographs He has served on the Editorial Boards of several international journals including IEEE Transactions on Automatic Control, Systems & Control Letters and Automatica. He currently serves as an Editor-in-Chief of Unmanned Systems. He has received a number of research awards nationally and internationally.

Abstract:

In this talk, we aim to report some advanced unmanned aerial systems (UAS) developed in the Department of Electrical and Computer Engineering, National University of Singapore. Attention is particularly paid to UAS, which is capable of navigating through in cluttered indoor and outdoor GPS-denied environments, such as hostile buildings, sewer tunnels, radiation contaminated areas and inside forests. Topics under studied include dynamic modeling of an unmanned helicopter, advanced flight control system design, multi-sensory data fusion, real-time simultaneous localization and mapping, and dynamic path planning in unknown environments. We will also take this opportunity to highlight some techniques that we have recently developed for the 2017 International Micro Air Vehicles (IMAV) competition, which was held in Toulouse, France, September 18–21, 2017. The IMAV competition is a yearly event that aims at fostering key technologies for the development of micro-air vehicles. It provides an arena for research groups around the world to showcase their research achievements and to test their results in real environments. Besides the unmanned aerial systems capable of navigating fully autonomously in GPS-denied environments, we have also managed to achieve sophisticated cooperative control and task management of multiple unmanned aerial vehicles for heavy duty missions. Other topics on the development of unconventional hybrid aircraft, which has the capability of taking off and landing vertically and transiting to a fixed-wing mode for fast cruise flight will also be showcased in the talk.

Biography:

Ronald R Riso has his research activities centered on developing implantable neural interface technology for controlling powered artificial limbs and techniques to provide tactile and position sensibilities from prostheses. Previously, he was Senior Research Scientist with Inner Sea Technology Inc., a research company for developing neuro-prostheses.

Abstract:

The full potential of advanced anthropomorphic powered prostheses depends on the effectiveness of the user control system. With a peripheral nerve based controller, the user commands the actuators of the prosthesis in the same manner that motor nerves in an intact limb elicit muscle activity. Ideally, each actuator is controlled by the specific motor nerve that performs the same joint movement in an intact limb. The simultaneous movements of multiple joints to complete complex limb motions is then able to be coordinated by the user’s brain, as aptly demonstrated by amputees treated with targeted muscle re-innervation (TMR). Despite the increases in prosthesis performance with TMR, several drawbacks exist such as the need for pattern recognition to correct for signal crosstalk when a host muscle becomes re-innervated by a mix of motor nerves that originally sub-served different joint motions. Moreover, researchers still struggle with how to provide tactile and proprioceptive sensibilities from artificial limbs. Microchannel nerve interfaces are being developed in diverse laboratories, to mitigate these issues and to expand the clinical applicability of naturally controlled prostheses. Microchannel rational and development: Microchannel nerve interfaces are based on the ability of severed peripheral nerves to regenerate and sort themselves into individually addressable channels that contain electrodes for recording and/or stimulation. Thus, efferent motor nerve activity can be recorded for prosthesis commands and sensory nerve fibers can be electrically stimulated to input tactile sensations and information regarding joint motion and position. Developmental studies of micro-channel nerve interface technology substantially concern discovering ways to control the sorting of different nerve fiber modalities into specific channels of the array. This presentation describes strategies used to fabricate microchannel devices, clinical applications and the present status of their deployment in animal studies. Key design factors are discussed such as channel cross sectional area and length, physical topography of channel walls, presence of appropriate extracellular matrix proteins, inclusion of nerve outgrowth scaffold materials, inclusion of specific neuro-trophic molecules and the importance of providing target tissues.

Biography:

Hao Wang is Associate professor at Nanjing University of Aeronautics & Astronautics, China. Hao Wang has his expertise in animal flight, bio-inspired robotics and robo-animals.

Abstract:

Robo-animal is a new branch in specialized robot, which treats a living animal itself as the mobile robot platform and controls its movement by neuro-modulation. Robo-pigeon has been investigated in recent years because of its ideal mobility and bearing capacity, but so far it has only been studied under laboratory conditions. Investigation under natural condition outdoors is still lacking. To develop a controllable robo-pigeon flying outdoors, here we have proposed an onboard preprogram approach to design a carriable control module and proposed a hierarchy stimulation algorithm to ensure the effectiveness of control signals of deep brain stimulation (DBS). The control module, in dimension of 34 mm×24 mm×20 mm and in mass of 16.8 g, could generate control signals automatically according to the local position and timing of the integrated global position system (GPS). The stimulation algorithm was hierarchized into three levels, single-, periodic- and multi periodic-stimuli. Two robo-pigeons were tested outdoors in the range of 30 km around the pigeon loft. On the level of multi periodic-stimuli, both robo-pigeons were controlled well. Orbiting flight was properly elicited at the preprogrammed GPS region. The first controllable flight in outdoor robo-pigeons will open the door to exciting new applications of specialized robot such as forestry survey.

Biography:

Anuradha Ranasinghe is currently working as an Assistant Professor (Lecturer) at Liverpool Hope University, UK. She has been awarded her PhD in Robotics from King’s College London. Her research focuses on haptics, human-robot interaction and computational motor control and somatosensory feedback of the humans. She has published high impact factor journals and peer reviewed conferences.

Abstract:

Robot leading has been taken in several physical human robot interactions (HRI) scenarios such as search and rescue, disaster response and human navigation. There are some situations humans have to work with limited perceptions from the environment. In that scenario, it would be interesting to have an intelligent agent like a robot to guide humans when the environment perceptions are limited. When humans interact with robots, it is important to understand how humans perceive their arm perturbations. In this study, we are trying to understand how humans will perceive arm perturbations in haptic based robotic guiding. Then we can design more human aware robotic guidance algorithm to guide humans. To perturb the arm, we implemented a 3^rd order predictive guiding control policy extracted from our previous human demonstration experiments on a planar 1-DoF robotic arm. In our previous studies, we found that human use a 3^rd order predictive and a 2^nd order reactive AR (auto-regressive) models for guiding and following, respectively. In this study, we found that reactive following nature of the humans has been changed to predictive after training. To test the possible causes of the model changes, we presented some behavioral matrices such as rise time (RT), the model order (N) and steady state variability (SSV) in moving leftward and rightward in arm flexion and extension, respectively. The higher RT, consistency of the model order N and low SSV mimic that humans have an intrinsic tendency to be in the predictive nature whenever possible. Our results give as an insight as to how to design human aware haptic-based robotic guiding algorithms for future applications.

Biography:

Lei Cai has completed his BS and MS degrees in the College Life Sciences, Shandong Normal University, Jinan and a PhD degree in Mechanical Design and Theory from Nanjing University of Aeronautics and Astronautics, Nanjing. He is the author of more than 20 articles and 6 China invention patents. His research interests include bio-robot, biosensors technology and animal locomotion control. He is a Member of the International Society of Bionic Engineering.

Abstract:

Pigeons can be an ideal animal for the study of flying bio-robot, not only because it has sustained flying ability, load-bearing and good orienting abilities, but also because it has superiority in motion concealment, obstacle avoidance and a complete autonomous intelligent in against environment interference. In order to develop bio-robot pigeon, we studied the movement regulation function of the midbrain nuclei and other adjacent structures in pigeon. Electrical stimulation was applied in investigating the movement regulation mechanisms in pigeons under light anesthesia and freely moving conditions respectively. In the acute experiment (under light anesthesia), the pigeon was fixed to a special head adapter, after the pain reflex disappeared, then removed the scalp above the surgical field, followed by removal of the cranium with a dental drill and removal of the dura and arachnoid under stereomicroscopy. Electrical micro-stimulation (intensity=30 μA; pulse duration=1.0 ms; frequency=80 Hz) was applied to locate and verify the turning related brain regions. The most eligible location was marked using an anodal DC current (40 μA for 20 s) to deposit iron ions. After the histological localization, the brain regions related to turning behavior mainly focused in the formation reticularis medialis, tractus vestibulomesencephalicus and the nucleus vestibularis lateralis. In the chronic experiment (in freely moving conditions), microelectrodes were implanted into the brain regions determined in the acute experiment and then a brain computer interface was fixed on the pigeon’s skull. After the pigeon recovery, via a wireless remote-control stimulator, we successfully induced turning behavior in freely moving pigeons. Our study suggested that pigeon’s midbrain played an important role in modulating the pigeon’s turning behavior. This work will provide new knowledge in flying bio-robot research and birds’ locomotion induction.

Biography:

Lei Cai has completed his BS and MS degrees in the College Life Sciences, Shandong Normal University, Jinan and a PhD degree in Mechanical Design and Theory from Nanjing University of Aeronautics and Astronautics, Nanjing. He is the author of more than 20 articles and 6 China invention patents. His research interests include bio-robot, biosensors technology and animal locomotion control. He is a Member of the International Society of Bionic Engineering.

Abstract:

Pigeons can be an ideal animal for the study of flying bio-robot, not only because it has sustained flying ability, load-bearing and good orienting abilities, but also because it has superiority in motion concealment, obstacle avoidance and a complete autonomous intelligent in against environment interference. In order to develop bio-robot pigeon, we studied the movement regulation function of the midbrain nuclei and other adjacent structures in pigeon. Electrical stimulation was applied in investigating the movement regulation mechanisms in pigeons under light anesthesia and freely moving conditions respectively. In the acute experiment (under light anesthesia), the pigeon was fixed to a special head adapter, after the pain reflex disappeared, then removed the scalp above the surgical field, followed by removal of the cranium with a dental drill and removal of the dura and arachnoid under stereomicroscopy. Electrical micro-stimulation (intensity=30 μA; pulse duration=1.0 ms; frequency=80 Hz) was applied to locate and verify the turning related brain regions. The most eligible location was marked using an anodal DC current (40 μA for 20 s) to deposit iron ions. After the histological localization, the brain regions related to turning behavior mainly focused in the formation reticularis medialis, tractus vestibulomesencephalicus and the nucleus vestibularis lateralis. In the chronic experiment (in freely moving conditions), microelectrodes were implanted into the brain regions determined in the acute experiment and then a brain computer interface was fixed on the pigeon’s skull. After the pigeon recovery, via a wireless remote-control stimulator, we successfully induced turning behavior in freely moving pigeons. Our study suggested that pigeon’s midbrain played an important role in modulating the pigeon’s turning behavior. This work will provide new knowledge in flying bio-robot research and birds’ locomotion induction.

Biography:

Ziad Zamzami is currently a PhD candidate at the Sorbonne Universités-University of Pierre and Marie Curie (UPMC) in Paris, France and a Member of the Institute of Intelligent Systems and Robotics (ISIR). He holds a Master’s degree in Advanced Systems and Robotics (SAR) from the UPMC. He holds a BSc and MSc in Material Science and Mechanical Engineering from the University of Mulhouse, France in the framework of the joint double degree program with the French University of Egypt. He has participated in several projects including; Fast Autonomous Rover SysTem (FAST) project funded by the French National Research Agency (ANR) and more recently on the FRAUDO Project in partnership with the French Atomic Energy Commission (CEA) and the French Defense Research Projects Agency (DGA). His research interest includes motion planning, trajectory optimization, underactuated robotics and multibody dynamics.

Abstract:

Humans and animals are capable of overcoming complex terrain challenges with graceful and agile movements. One of the key ingredients for such complex behaviors is motion coordination to exploit their natural dynamics. Sports performers coordinate their action in many different ways to achieve their goals. Coordination is a key feature in highly dynamic maneuvers ranging from the graceful, precise action of an ice dancer to the explosive, physical power of a triple jumper. Lizard coordinates its tail swing to stabilize its dynamic motion over rough terrain. Cheetah can rapidly accelerate and maneuver during the pursuit of its prey by the coordinating of the motion of its tail. Understanding and emulating these motions is one of the long-standing grand challenges in robotics and biomechanics with possible applications in rehabilitation, sport, search-and-rescue, environmental monitoring and security. Despite the existence of powerful tools such as nonlinear trajectory optimization, they are usually treated as black boxes that provide local optimal trajectories. We introduce the Dynamical Coupling Map (DCM), a novel graphical technique, to help gain insight into the output trajectory of the optimization and analyze the capability of underactuated robots. As examples of dynamic maneuvers, the DCM analysis is demonstrated on the swing-up motion of a simplified model of a gymnast on high bar as well as a vertical jump for a high-dimensional humanoid robot with arms swing. The DCM shows graphically and intuitively the pivotal role of exploiting the natural dynamics in order to exceed their physical capacity which is dictated by the input torques limits. We also extend the current posteriori analysis to exploiting the natural dynamics as a priori for guiding motion generation of highly dynamic maneuvers.

Biography:

Wenbo Wang is Associate Professor at Nanjing University of Aeronautics and Astronautics, China. Wenbo Wang has his expertise in the bio-mimetics on gecko locomotion, i.e., modulation on gecko's locomotion.

Abstract:

For neural stimulation and recording in neuro-ethology, different acustomized electrode micro drives are required for different unrestrained species. We specially designed and fabricated a novel electrode micro drive for studying the locomotion control of a freely moving Gekko gecko lizard. Opening the skull of the lizard was required for the implantation of the electrodes in the midbrain. The micro drive system consists mainly of a titanium case to protect the skull opening and shield the external signal and a screw-and-nut mechanism to drive the electrode plate. The miniature system has a volume of 9.6 mm × 9.8 mm × 11.8 mm and a mass of 2.05 g, which is suitable for the head morphology and loading capability of the lizard. The system was successfully applied to study the locomotion control of unrestrained Gekko gecko lizards, which exhibited diverse behaviors corresponding to various implantation depths of the electrodes and could be efficiently guided to a lateral orientation.

Biography:

Zhouyi Wang has completed his Degree of Doctor of Philosophy from Nanjing University of Aeronautics and Astronautics. His research areas include tribology, bionics, animal kinematics and dynamics.

Abstract:

Locomotion is essential character of animals and excellent moving ability results from the delicate sensing of the substrate reaction forces (SRF) acting on body and modulating the behavior to adapt the motion requirement. The inclined substrates present in habitats pose a number of functional challenges to locomotion. In order to effectively overcome these challenges, climbing geckos execute complex and accurate movements that involve both front and hind limbs. Few studies have examined gecko’s SRF on steeper inclines of greater than 90°. To reveal how the SRFs acting on the front and hind limbs respond to angle incline changes, we obtained detailed measurements of the three-dimensional SRFs acting on the individual limbs of the Tokay gecko while it climbed on an inclined angle of 0°-180°. The fore-aft forces acting on the front and hind limbs show opposite trends on inverted inclines of greater than 120°, indicating propulsion mechanism changes in response to inclines. When the incline angles change, the forces exerted in the normal and fore-aft directions by the gecko’s front and hind limbs are reassigned to take full advantage of the limbs’ different roles in overcoming resistance and in propelling locomotion. This also ensures that weight acts in the angle range between the forces generated by the front and hind limbs. The change in the distribution of SRF with a change in incline angle is directly linked to the favorable trade-off between locomotive maneuverability and stability.

Biography:

Abstract:

Biography:

Rea Nkhumise is a Robotics Engineer for the SKA-SA Science Data Processing Department. He holds an MSc in Mechatronics Engineering from Tennessee Tech University (USA) with specialty and experience in computational intelligent, control algorithms and embedded system design. His background is mechanical engineering. He has designed and built multiple automated products using open source hardware and software, especially Arduino supported, which are currently commercial.

Abstract:

The SKA-SA is building a radio telescope that will output a total raw data of 62 EB annually. Most of the data will be inactive and rarely accessed however needs to be safely stored for 10-15 years. The data is not sensitive and there is no urgency when it has to be retrieved. The challenge is finding a cost-effective data storage architecture that has the capacity, longevity and reliability fit for purpose. Amongst available architectures in the market, the tape library is the most affordable one. Yet, its purchase costs (including installation and licensing) from leading manufacturers are enormous. There is also a perpetual development of open source robotics technology (like CNC machines, 3D printers, etc.) which in principle is similar to that of the tape library. The same technology can be harnessed and repurposed into the tape library industry to tremendously drive down costs. This disruption could potentially improve the tape library technology and be of benefit to small businesses and scientific organizations. In the project approach, the development of the tape library was sectioned into 4 main modules: (1) Storage assembly made from extruded beams and 3D printed cartridge cells; (2) Robotic manipulator moving in 2 axes using Arduino and Grbl for controlling actuators; (3) End-effector that picks and grabs tapes during operation which is controlled by an Arduino shield; and (4) Support accessories for monitoring, reading tapes and coordinating the operational process using Raspberry Pi. This approach cuts cost by 75% and the storage capacity is nearly of that acquired from leading manufacturers. It uses LTO industry standards as well and assumes competitive performance specifications like scalability, compatibility and ease-of-assembly. This is a work in progress project where reliability and robustness of the tape library using open source technology are to be evaluated.

Biography:

Youssouf Ismail Cherifi is currently pursuing his PhD at IGEE (ex-Inelec). He has completed his Master’s degree in Computer Engineering and previously worked on the implementation and control of a biped robot using static walk and Arduino.

Abstract:

Speaker recognition is the task of identifying or verifying the speaker based on speaker specific features such as MFCC, IMFCC, LPC, LPCC and so on. The problem is that each feature contains a certain level of information that no other set of features can provide. However, all this information can be split into two categories-features that model the speech production system and features that are used to model the human way of hearing. The objective of this paper is to use two set of features and deep learning in order to enhance the accuracy of speaker recognition task. The two set of features are selected such that they represent both the speech production and hearing systems. This system can also be used to extract deep features that can be used to replace the classical speaker specific features.

Biography:

Antonius Mamphiswana has his expertise in Mathematics, Statistics and passion in improving computer vision. His approach for terrain classification combines machine learning and an approach which is introduces by Sebastian Thrun, et al., which can improve terrain classification for unmanned ground vehicle.

Abstract:

Identifying the travesability of a terrain for unmanned ground vehicle (UGV) is of great importance. This is because UGV are intended to operate in a dynamic environment where there are many obstacles (dynamic and static obstacle). For the UGV to be able to identify the travesability of the scene, the UGV needs to be continuously sensing and predicting the travesability of the terrain around it. To do the sensing, we used 5 color cameras and a velodyne lidar. To predict if the terrain is traversable or not we have used a deep convolutional neural network (DCNN) and height difference was calculated from point cloud data. The DCNN will classify RGB images and height difference approach will classify point cloud data from the velodyne lidar. The height difference approach was used by Stanley the car that won the DARPA grand challenge 2005. The results from both the classifier (DCNN) and the height difference have time stamp which will help in fusing the results. Both the approaches produce good results in identifying the travesability of the terrain.

Biography:

Shannon D Bohle is the President of Archivopedia LLC, USA. In 2011, she was awarded 2^nd Place for Curiosity AI in the FVC, an International Department of Defense competition in artificial intelligence advertised by The White House. She has earned her Bachelor of Arts in History and English at Miami University, a Master of Library and Information Science (MLIS) at Kent State University and was granted a Certificate of Diligent Study in History and Philosophy of Science for postgraduate study at the University of Cambridge.

Abstract:

This paper is based on talks that included a demo of my new virtual humanoid embodied AI bot capable of autonomously expressing appropriate emotions using gestures, facial expressions and text-to- voice. It does this while engaging in natural language conversations or giving automated scripted lectures with a slide show presentation.The system employs a touch-interaction-based learning and communication system where the virtual bot responds and learns from touch sense feedback training-a poke (negative reinforcement) or swipe (positive reinforcement)-conveyed through a touch screen. The bot’s predecessor was part of an award-winning project in an international Artificial Intelligence competition advertised by The White House and sponsored by the U.S. Department of Defense. The talk and demo combination consists of a creatively scripted talk given by the AI bot that provides a counterargument to its critics (RAND and a variety of organizations aimed at slowing its progress). Using logos, ethos, and pathos, it argues for its legal and ethical rights for development and suggests specific technical guidance developing AI for their accompanying responsibilities. Embedded in the talk are theoretical foundations for an AI Hierarchy of Needs using landmark studies. These include the work of Maslow; advances in understanding the philosophical, psychological and neurological bases for consciousness and language; The Turing Test; Asimov’s Three Laws of Robotics; Chalmers’ hard problem of consciousness; Robert Plutchik's psychoevolutionary theory of emotion; Paul Ekman’s relationships between nonverbal communication (such as facial expressions) and emotions; classical and operant conditioning for learning (especially Pavlov and 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 affective experiences (learned through touch and conversation) for the improvement of human-computer interaction for potential use in a variety of AI- enabled robots.