19 research outputs found
The Tortoise and the Hare
No full textHere is a large-format pamphlet that reproduces the fable part of a Dutch version, De Schildpad en de Haas, for which I have guessed a publication year of 1960. As I mention there, it features delightful children's art, especially for the early views of an angry and exhausted turtle. I cannot say whether the English version is the same as the long Dutch prose story, but at least having this English text helps now to make sense of the pictures and to answer the questions I had then about what seemed an unusual presentation of the story. In this English version, there are two tortoises. The disrobed victor turtle who enjoys relaxing on top of his shell is not really yet a victor. It is, as this version makes clear, another tortoise who looked exactly like Tubby. He appears along the route. Thus a part of an element from another fable, usually told between a hare and a porcupine, shows up here; there many porcupines are used to confuse the hare, while one substitute appears here. In this version, Horace the hare thought If slow old Tubby has time to rest then I will, too! And so he went to sleep. Several illustrations from the fuller Dutch version are skipped here. As I suggest, they may complicate the story further
The AgriRover : a reinvented mechatronic platform from space robotics for precision farming
No full textThis paper presents an investigation of a novel development of a multi-functional mobile platform for agriculture applications. This is achieved through a reinven-tion process of a mechatronic design by spinning off space robotic technologies in terrestrial applications in the AgriRover project. The AgriRover prototype is the first of its kind in exploiting and applying space robotic technologies in precision farming. To optimize energy consumption of the mobile platform, a new dynamic total cost of transport algorithm is proposed and validated. An autonomous navi-gation system has been developed to enable the AgriRover to operate safely in unstructured farming environments. An object recognition algorithm specific to agriculture- has been investigated and implemented. A novel soil sample collect-ing mechanism has been designed and prototyped for on-board and in-situ soil quality measurement. The design of the whole system has benefited from the use of a mechatronic design process known as the Tiv model through which a plane-tary exploration rover is reinvented into the AgriRover for agricultural applica-tions. The AgriRover system has gone through three sets of field trials in the UK and some of these results are reported
Cooperative Visual Object Learning
No full textA lot of attention has recently been focused on possible benefits of the cooperation between machines and humans. Taking the best from machines and humans and joining them together can produce results which exceed each collaborating partner performing separately. A common belief is that thekey for good cooperation is an excellent communication. Some important aspects of communication are self-evaluation processes. When applied to humans these processes improve the communication quality between humans. Therefore, we believe that employing self-evaluation processes at machinesadvances the human-machine communication, and cooperation quality. Accordingly, this thesis is exploring communication strategies between machines and humans. More precisely, it examines possibilities for the communication improvement through an exploration of self-evaluation processes of classifiers.Firstly, we introduce a baseline framework, an interactive visual category learning architecture, called Tubby at Honda Research Institute in Germany. For simplicity we consider in a first step the classification of objects rather than the more difficult task of learning multiple categories per object. We then introduce theoretical foundations used in the thesis. The background on classification, neural networks, outlier detection and assessment of classifiers is explained in depth. We outline the critical importance of self-evaluation in classification. Therefore, we propose two self-evaluation measures which are incorporated within a testing and a training strategy. The first measure captures a confidencein predictions during classification and it is used within the proposed testing strategy. The second measure denotes the quality of each training sample with respect to the generalization performance of classification and it is used within the proposed training strategy. The quality of the training sample essentially represents how different the current training sample is from all of the previously acquired training samples of the object. The confidence and the quality measure are communicated through a graph to the user of the system. Depending on whether the system is in the testing or training phase the value of the corresponding measure is provided to the user. Two ways of deriving eachof the two measures are presented. Essentially, we offer two testing and two training strategies. Furthermore, we consider each proposed strategy separately and a combination of those. We then evaluate all of the considered cases against a baseline strategy. The evaluations are performed in different dimensionalities of the feature space for different numbers of training and testing objects. We present an offline simulation of the interaction between Tubby and the user. Results of the simulation provide additional insights into the working mechanisms of the proposed strategies and measures.The proposed strategies improve the baseline performance. The absolute improvement of the average classification accuracy varies between 1% and 25%, depending on the dimensionality of the feature space and number of training and testing objects. The best results are achieved when a combination of the proposed training and testing strategy is used. The biggest improvement is observed when a lot of objects are in the learning process (≈ 100), and the dimensionality of the feature space is high (≥ 10D). In the actual application setting this is the most realistic case - a large number of objects and a high dimensionality of the feature space
Distillation Of Sound: Dub In Jamaica And The Creation Of Culture
No full textIn the early 1970s, the culture of Jamaica shifted politically and culturally with the introduction of the mixing board in music. This writing centers on the ways in which technology created a culture of dub reggae that has gone on to affect the world. The major albums and engineers that influenced this change are the focus here. By doing so, we can view how large changes in technology affected the society of Jamaica and how this led to significant cultural development. With Raymond Williams’ definition of culture and Thomas Vendrys’ structure of Dub music, the culture is defined, furthered, and discussed. Engineers like Lee “Scratch” Perry, King Tubby, and others used the technology to break into the music landscape and to establish what is known today as dub music.
The differences between the preceding music of ska and reggae and dub are looked at as well. What created these differences and what led to the shift are the focus of this presentation. Examples of dub music, and how they differ from reggae will be heard and discussed. The split between the social classes in Jamaican society is also a part of this conversation. Dub music situates within the working-class of Jamaica at this time and stands outside of the music industry in interesting ways. The mixing desk and other forms of technology were used to create a specific shift in the culture of Jamaican society. This shift is still being felt today and the developments of these early engineers and producers are still being used to construct dub music. By focusing on the early developments of the music and how these developments created a cultural shift, we can see how technology changed the way that Jamaican popular music impacted the world
Benthic sediment surveys of inner Darwin Harbour (GA0358) and shallow water areas in and around Bynoe Harbour (GA0359) in 2017: Chlorin measurements on seabed sediments.
No full textMaintenance and Update Frequency: asNeededStatement: Bottom sediments were collected using either a Shipek grab or a Box corer. Bulk sub-samples (6.5 ml) of surface sediment (0-2 cm) were extruded into vials which were wrapped in Al foil and immediately frozen. Porosity was determined by calculation of the wet volume as a percentage of the total volume, after freeze drying and correction for seawater salts. The accuracy of the wet/dry measurements were >1%. The precision of the volume measurements were >2%. The residual sediments were then ground in the dark, and each successive sample was quickly returned to the freezer. Chlorins were then extracted from freeze-dried sediment using the method of Schubert et al. (2005). Relative standard deviations of the precisions on duplicate samples are presented with the datasets.Benthic sediment sampling of Inner Darwin Harbour (GA0358) and shallow water areas in and around Bynoe Harbour (GA0359) was undertaken between May 29 and June 19, 2017. Partners involved in the surveys included Geoscience Australia (GA), the Australian Institute of Marine Science (AIMS) and the Department of Environment and Natural Resources within the Northern Territory Government (NT DENR) (formerly the Department of Land and Resource Management (DLRM)). These surveys form part of a four year (2014-2018) science program aimed at improving knowledge about the marine environments in the regions around Darwin and Bynoe Harbour’s through the collection and collation of baseline data that will enable the creation of thematic habitat maps to underpin marine resource management decisions. This project is being led by the Northern Territory Government and is supported by the INPEX-led Ichthys LNG Project, in collaboration with - and co-investment from GA and AIMS. This dataset comprises total chlorin and chlorin index measurements made on seabed sediments
The AgriRover : a mechatronic platform from space robotics for precision farming
No full textThis paper reports an investigation of a novel development by spinning off space robotic technologies into agriculture and dissemination of the findings of AgriRover project, which is the first of its kind in exploiting and applying space robotic technologies in precision farming. To measure energy performance of mobile platform, a new dynamic total cost of transport is proposed and validated. An autonomous navigation system based on a rover control architecture has been developed to enable the AgriRover to traverse safely in unstructured farming environments. A novel and agriculture- specific object recognition algorithm has been investigated and implemented to enable higher degree of intelligence based on more smart data processing capability. A novel soil sample collecting mechanism has been designed and prototyped for onboard and in-situ soil quality measurement. The design of the whole system has benefited from the use of a mechatronic design process known as the Tiv model through which a planetary rover is reinvented into the AgriRover for agricultural applications. The AgriRover system has gone through three field trials in the UK and China and some of these results are reported
RobotCycle: Assessing Cycling Safety in Urban Environments
No full textThis paper introduces RobotCycle, a novel ongoing project that leverages
Autonomous Vehicle (AV) research to investigate how road infrastructure
influences cyclist behaviour and safety during real-world journeys. The
project's requirements were defined in collaboration with key stakeholders,
including city planners, cyclists, and policymakers, informing the design of
risk and safety metrics and the data collection criteria. We propose a
data-driven approach relying on a novel, rich dataset of diverse traffic scenes
and scenarios captured using a custom-designed wearable sensing unit. By
analysing road-user trajectories, we identify normal path deviations indicating
potential risks or hazardous interactions related to infrastructure elements in
the environment. Our analysis correlates driving profiles and trajectory
patterns with local road segments, driving conditions, and road-user
interactions to predict traffic behaviours and identify critical scenarios.
Moreover, by leveraging advancements in AV research, the project generates
detailed 3D High-Definition Maps (HD Maps), traffic flow patterns, and
trajectory models to provide a comprehensive assessment and analysis of the
behaviour of all traffic agents. These data can then inform the design of
cyclist-friendly road infrastructure, ultimately enhancing road safety and
cyclability. The project provides valuable insights for enhancing cyclist
protection and advancing sustainable urban mobility.Comment: IEEE Intelligent Vehicles Symposium (IV 2024
RobotCycle: assessing cycling safety in urban environments
No full textThis paper introduces RobotCycle, a novel ongoing project that leverages Autonomous Vehicle (AV) research to investigate how road infrastructure influences cyclist behaviour and safety during real-world journeys. The project’s requirements were defined in collaboration with key stakeholders, including city planners, cyclists, and policymakers, informing the design of risk and safety metrics and the data collection criteria. We propose a data-driven approach relying on a novel, rich dataset of diverse traffic scenes and scenarios captured using a custom-designed wearable sensing unit. By analysing road-user trajectories, we identify normal path deviations indicating potential risks or hazardous interactions related to infrastructure elements in the environment. Our analysis correlates driving profiles and trajectory patterns with local road segments, driving conditions, and road-user interactions to predict traffic behaviours and identify critical scenarios. Moreover, by leveraging advancements in AV research, the project generates detailed 3D High-Definition Maps (HD Maps), traffic flow patterns, and trajectory models to provide a comprehensive assessment and analysis of the behaviour of all traffic agents. These data can then inform the design of cyclist-friendly road infrastructure, ultimately enhancing road safety and cyclability. The project provides valuable insights for enhancing cyclist protection and advancing sustainable urban mobility
Watching Grass Grow: Long-term Visual Navigation and Mission Planning for Autonomous Biodiversity Monitoring
No full textWe describe a challenging robotics deployment in a complex ecosystem to
monitor a rich plant community. The study site is dominated by dynamic
grassland vegetation and is thus visually ambiguous and liable to drastic
appearance change over the course of a day and especially through the growing
season. This dynamism and complexity in appearance seriously impact the
stability of the robotics platform, as localisation is a foundational part of
that control loop, and so routes must be carefully taught and retaught until
autonomy is robust and repeatable. Our system is demonstrated over a 6-week
period monitoring the response of grass species to experimental climate change
manipulations. We also discuss the applicability of our pipeline to monitor
biodiversity in other complex natural settings.Comment: to be presented at the Workshop on Field Robotics - ICRA 202
Watching grass grow: long-term visual navigation and mission planning for autonomous biodiversity monitoring
No full textWe describe a challenging robotics deployment in a complex ecosystem to monitor a rich plant community. The study site is dominated by dynamic grassland vegetation and is thus visually ambiguous and liable to drastic appearance change over the course of a day and especially through the growing season. This dynamism and complexity in appearance seriously impact the stability of the robotics platform, as localisation is a foundational part of that control loop, and so routes must be carefully taught and retaught until autonomy is robust and repeatable. Our system is demonstrated over a 6-week period monitoring the response of grass species to experimental climate-change manipulations. We also discuss the applicability of our pipeline to monitor biodiversity in other complex natural settings
