From vision to actions: Towards adaptive and autonomous humanoid robots

Although robotics research has seen advances over the last decades robots are still not in widespread use outside industrial applications. Yet a range of proposed scenarios have robots working together, helping and coexisting with humans in daily life. In all these a clear need to deal with a more unstructured, changing environment arises. I herein present a system that aims to overcome the limitations of highly complex robotic systems, in terms of autonomy and adaptation. The main focus of research is to investigate the use of visual feedback for improving reaching and grasping capabilities of complex robots. To facilitate this a combined integration of computer vision and machine learning techniques is employed. From a robot vision point of view the combination of domain knowledge from both imaging processing and machine learning techniques, can expand the capabilities of robots. I present a novel framework called Cartesian Genetic Programming for Image Processing (CGP-IP). CGP-IP can be trained to detect objects in the incoming camera streams and successfully demonstrated on many different problem domains. The approach requires only a few training images (it was tested with 5 to 10 images per experiment) is fast, scalable and robust yet requires very small training sets. Additionally, it can generate human readable programs that can be further customized and tuned. While CGP-IP is a supervised-learning technique, I show an integration on the iCub, that allows for the autonomous learning of object detection and identification. Finally this dissertation includes two proof-of-concepts that integrate the motion and action sides. First, reactive reaching and grasping is shown. It allows the robot to avoid obstacles detected in the visual stream, while reaching for the intended target object. Furthermore the integration enables us to use the robot in non-static environments, i.e. the reaching is adapted on-the- fly from the visual feedback received, e.g. when an obstacle is moved into the trajectory. The second integration highlights the capabilities of these frameworks, by improving the visual detection by performing object manipulation actions.

A Bayesian Framework for the Assessment of Vision-based Weed and Fruit Detection and Classification Algorithms

This paper proposes new metrics and a performance-assessment framework for vision-based weed and fruit detection and classification algorithms. In order to compare algorithms, and make a decision on which one to use fora particular application, it is necessary to take into account that the performance obtained in a series of tests is subject to uncertainty. Such characterisation of uncertainty seems not to be captured by the performance metrics currently reported in the literature. Therefore, we pose the problem as a general problem of scientific inference, which arises out of incomplete information, and propose as a metric of performance the(posterior) predictive probabilities that the algorithms will provide a correct outcome for target and background detection. We detail the framework through which these predicted probabilities can be obtained, which is Bayesian in nature. As an illustration example, we apply the framework to the assessment of performance of four algorithms that could potentially be used in the detection of capsicums (peppers).

Initial prototype testing of Ray's Night Out: A new mobile app targeting risky drinking in young people

Background Risky single occasion drinking (RSOD; 4 or more drinks in <6 h) more than doubles the risk of injury in young people (15 - 25 years). The potential role of smartphone apps in reducing RSOD in young people is yet to be explored. Objective: To describe the initial prototype testing of ‘Ray's Night Out’, a new iPhone app targeting RSOD in young people. Method Quantitative and qualitative methods were used to evaluate the quality, perceived utility, and acceptability of the app among nine young people (19e23 years). Results Participants reported Ray's Night Out had good to excellent levels of functionality and visual appeal, acceptable to good levels of entertainment, interest and information, and acceptable levels of customization and interactivity. Young people thought the app had high levels of youth appeal, would prompt users to think about their alcohol use limits, but was unlikely to motivate a change in alcohol use in its current form. Qualitative data provided several suggestions for improving the app. Conclusion Following revision, Ray's Night Out could provide an effective intervention for RSOD in non help-seeking young people. A randomized controlled trial is currently underway to test the final prototype of the app.

Engaging at-risk vocational education students with mobile devices

The potential of using mobile devices to increase learner engagement within a small group of at-risk vocational education students was studied through a qualitative case study. It was found that the use of mobile devices could be a strategy educators may use to reduce the barriers these students often encounter within traditional classrooms. Notions of interactivity, ease of use, existing familiarity and fluency were found to be fundamental variables that were central to the group's use of mobile devices. The study provides direction for educators looking for innovative ways to engage students who struggle in a classroom situation.

Method for comparing the capture efficiency of benthic sampling devices

Traditional comparisons between the capture efficiency of sampling devices have generally looked at the absolute differences between devices. We recommend that the signal-to-noise ratio be used when comparing the capture efficiency of benthic sampling devices. Using the signal-to-noise ratio rather than the absolute difference has the advantages that the variance is taken into account when determining how important the difference is, the hypothesis and minimum detectable difference can be made identical for all taxa, it is independent of the units used for measurement, and the sample-size calculation is independent of the variance. This new technique is illustrated by comparing the capture efficiency of a 0.05 m(2) van Veen grab and an airlift suction device, using samples taken from Heron and One Tree lagoons, Australia.

Use of electronic portal imaging devices for electron treatment verification

This study aims to help broaden the use of electronic portal imaging devices (EPIDs) for pre-treatment patient positioning verification, from photon-beam radiotherapy to photon- and electron-beam radiotherapy, by proposing and testing a method for acquiring clinicallyuseful EPID images of patient anatomy using electron beams, with a view to enabling and encouraging further research in this area. EPID images used in this study were acquired using all available beams from a linac configured to deliver electron beams with nominal energies of 6, 9, 12, 16 and 20 MeV, as well as photon beams with nominal energies of 6 and 10 MV. A widely-available heterogeneous, approximately-humanoid, thorax phantom was used, to provide an indication of the contrast and noise produced when imaging different types of tissue with comparatively realistic thicknesses. The acquired images were automatically calibrated, corrected for the effects of variations in the sensitivity of individual photodiodes, using a flood field image. For electron beam imaging, flood field EPID calibration images were acquired with and without the placement of blocks of water-equivalent plastic (with thicknesses approximately equal to the practical range of electrons in the plastic) placed upstream of the EPID, to filter out the primary electron beam, leaving only the bremsstrahlung photon signal. While the electron beam images acquired using a standard (unfiltered) flood field calibration were observed to be noisy and difficult to interpret, the electron beam images acquired using the filtered flood field calibration showed tissues and bony anatomy with levels of contrast and noise that were similar to the contrast and noise levels seen in the clinically acceptable photon beam EPID images. The best electron beam imaging results (highest contrast, signal-to-noise and contrast-to-noise ratios) were achieved when the images were acquired using the higher energy electron beams (16 and 20 MeV) when the EPID was calibrated using an intermediate (12 MeV) electron beam energy. These results demonstrate the feasibility of acquiring clinically-useful EPID images of patient anatomy using electron beams and suggest important avenues for future investigation, thus enabling and encouraging further research in this area. There is manifest potential for the EPID imaging method proposed in this work to lead to the clinical use of electron beam imaging for geometric verification of electron treatments in the future.

A Survey of autonomous vision-based See and Avoid for Unmanned Aircraft Systems

This paper provides a comprehensive review of the vision-based See and Avoid problem for unmanned aircraft. The unique problem environment and associated constraints are detailed, followed by an in-depth analysis of visual sensing limitations. In light of such detection and estimation constraints, relevant human, aircraft and robot collision avoidance concepts are then compared from a decision and control perspective. Remarks on system evaluation and certification are also included to provide a holistic review approach. The intention of this work is to clarify common misconceptions, realistically bound feasible design expectations and offer new research directions. It is hoped that this paper will help us to unify design efforts across the aerospace and robotics communities.

Repeatable Condition-Invariant Visual Odometry for Sequence-Based Place Recognition

This paper describes a vision-only system for place recognition in environments that are tra- versed at different times of day, when chang- ing conditions drastically affect visual appear- ance, and at different speeds, where places aren’t visited at a consistent linear rate. The ma- jor contribution is the removal of wheel-based odometry from the previously presented algo- rithm (SMART), allowing the technique to op- erate on any camera-based device; in our case a mobile phone. While we show that the di- rect application of visual odometry to our night- time datasets does not achieve a level of perfor- mance typically needed, the VO requirements of SMART are orthogonal to typical usage: firstly only the magnitude of the velocity is required, and secondly the calculated velocity signal only needs to be repeatable in any one part of the environment over day and night cycles, but not necessarily globally consistent. Our results show that the smoothing effect of motion constraints is highly beneficial for achieving a locally consis- tent, lighting-independent velocity estimate. We also show that the advantage of our patch-based technique used previously for frame recogni- tion, surprisingly, does not transfer to VO, where SIFT demonstrates equally good performance. Nevertheless, we present the SMART system us- ing only vision, which performs sequence-base place recognition in extreme low-light condi- tions where standard 6-DOF VO fails and that improves place recognition performance over odometry-less benchmarks, approaching that of wheel odometry.

Affective sensing + wearable imaging: Vision impairment and implications for spatial enquiry

Recent interest in affect and the body have mobilized a contemporary review of aesthetics and phenomenology within architecture to unpack how environments affect spatial experience. Emerging spatial studies within the neuro-sciences, and their implications for architectural research as raised by architectural theorists Juhani Pallasmaa (2014) and Harry Mallgrave (2013) has been well supported by a raft of scientists and institutions including the prestigious Salk Institute. Although there has been some headway in spatial studies of the vision impaired (Cattaneo et al, 2011) to understand the role of their non-visual systems in assisting navigation and location, little is discussed in terms of their other abilities in sensing particular qualities of space which impinge upon emotion. This paper reviews a collection of studies exploring face vision and echo-location, amongst others, which provide insight into what might be termed affective perception of the vision impaired, and how further interplay between this research and the architectural field can contribute new knowledge regarding space and affect. By engaging with themes from the Aesthetics, Phenomenology and indeed Neuro-science fields, the paper provides background of current and potential cross disciplinary research, and highlights the role wearable technologies can play in enhancing knowledge of affective spatial experience.

Distributed Robotic Vision as a service

The vision sense of standalone robots is limited by line of sight and onboard camera capabilities, but processing video from remote cameras puts a high computational burden on robots. This paper describes the Distributed Robotic Vision Service, DRVS, which implements an on-demand distributed visual object detection service. Robots specify visual information requirements in terms of regions of interest and object detection algorithms. DRVS dynamically distributes the object detection computation to remote vision systems with processing capabilities, and the robots receive high-level object detection information. DRVS relieves robots of managing sensor discovery and reduces data transmission compared to image sharing models of distributed vision. Navigating a sensorless robot from remote vision systems is demonstrated in simulation as a proof of concept.

PMU measurement based dynamic load modeling using SVC devices in online environment

Online dynamic load modeling has become possible with the availability of Static Voltage Compensator (SVC) and Phasor Measurement Unit (PMU) devices. The power of the load response to the small random bounded voltage fluctuations caused from SVC can be measured by PMU for modelling purposes. The aim of this paper is to illustrate the capability of identifying an aggregated load model from high voltage substation level in the online environment. The induction motor is used as the main test subject since it contributes the majority of the dynamic loads. A test system representing simple electromechanical generator model serving dynamic loads through the transmission network is used to verify the proposed method. Also, dynamic load with multiple induction motors are modeled to achieve a better realistic load representation.

Retinal photography screening programs to prevent vision loss from diabetic retinopathy in rural and urban Australia: A review

Purpose This review assessed the effectiveness of diabetic retinopathy (DR) screening programs, using retinal photography in Australian urban and rural settings, and considered implications for public health strategy and policy. Methods An electronic search of MEDLINE, PubMed, and Embase for studies published between 1 January 1996 and the 30 June 2013 was undertaken. Key search terms were “diabetic retinopathy,” “screening,” “retinal photography” and “Australia.” Results Twelve peer-reviewed publications were identified. The 14 DR screening programs identified from the 12 publications were successfully undertaken in urban, rural and remote communities across Australia. Locations included a pathology collection center, and Indigenous primary health care and Aboriginal community controlled organizations. Each intervention using retinal photography was highly effective at increasing the number of people who underwent screening for DR. The review identified that prior to commencement of the screening programs a median of 48% (range 16–85%) of those screened had not undergone a retinal examination within the recommended time frame (every year for Indigenous people and every 2 years for non-Indigenous people in Australia). A median of 16% (range 0–45%) of study participants had evidence of DR. Conclusions This review has shown there have been many pilot and demonstration projects in rural and urban Australia that confirm the effectiveness of retinal photography-based screening for DR

Regenerative sustainability for the built environment – from vision to reality: An introductory chapter

Regenerative sustainability is emerging as an alternative discourse around the transition from a ‘mechanistic’ to an ‘ecological’ or living systems worldview. This view helps us to re-conceptualize relationships among humans’ technological, ecological, economic, social and political systems. Through exploration of ‘net positive’ or ‘regenerative’ development lenses and the traditional sustainability literature, the conceptualization and approaches to achieve sustainable development and ecological modernization are expanded to articulate and to explore the evolving sustainability discourse, ‘regenerative sustainability’. This Special Volume of Journal of Cleaner Production (SV) is focused upon various dimensions of regenerative sustainability (e.g. regenerative design, regenerative development, and positive development) applied to the urban built environment at scales, which range from individual buildings, neighborhoods, and urban developments to integrated regional sustainable development. The main focus is on how these approaches and developments are evolving, how they can help us to prevent or adapt to climate change and how these approaches are likely to evolve in the next two to three decades. These approaches are addressed in four themes: (1) reviewing the theoretical development of the discourse of regenerative sustainability, its emerging principles and practices, (2) explaining how it can be measured and monitored, (3) providing encouraging practical pathways and examples of its implementation in multiple cultural and climatic contexts, and (4) mapping obstacles and enablers that must be addressed to help to ensure that more rapid progress is made in implementing the transitions towards an urban built environment that supports genuinely sustainable societies.

New encapsulating materials for implantable devices

Synthetic, natural, or composite, biomaterials occupy a key position in the management of disease and support continuous advancement of health care. Clinical utility of many permanent and biodegradable implants can be significantly improved via surface modification. Here, we discuss a novel polymer material developed from essential oil-based monoterpene alcohol using plasma polymerisation. The developed coatings are cytocompatible and limit adhesion and proliferation of a variety of pathogens. The coating can also be used to control degradation behaviour of resorbable materials, such as magnesium.

Implantable devices: issues and challenges

Ageing population and a multitude of neurological and cardiovascular illnesses that cannot be mitigated by medication alone have resulted in a significant growth in the number of patients that require implantable electronic devices. These range from sensors, gastric and cardiac pacemakers, cardioverter defibrillators, to deep brain, nerve, and bone stimulators. Long-term implants present specific engineering challenges, including low energy consumption and stable performance. Resorbable electronics may offer excellent short-term performance without the need for surgical removal. However, most electronic materials have poor bio- and cytocompatibility, resulting in immune reactions and infections. This paper reviews the current situation and highlights challenges for future advancements.