GENERAL ENQUIRIES: Tel: + 27 12 841 2911 | Email: callcentre@csir.co.za

Mobile intelligent autonomous systems

 

News

CSIR Research Space is constantly being developed and populated. Please report any errors to Siphethile Muswelanto Constructive criticism and suggestions would be welcome.

Recent Submissions

  • Burke, Michael G (IEEE, 2017-09)
    This work introduces a generative Bezier curve model suitable for surf-zone curve tracking in coastal image sequences. The model combines an adaptive curve parametrised by control points governed by local random walks with ...
  • Masha, Ditebogo F; Burke, Michael G; Twala, B (IEEE, 2017-11)
    Recent work has shown that proprioceptive measurements such as terrain slip can be used for terrain classification. This paper investigates the suitability of four simple slip estimation methods for differentiating between ...
  • Xungu, Sipho A; Notununu, Lwando G; Mbizeni, Asanda; Dickens, John S (IEEE, 2017-11)
    Locomotives are at risk to collisions and derailment due to obstacles on the track. Trains do not have the ability to steer around obstacles, they are confined to the track and depend on stopping to avoid hazards. These ...
  • Ajoodha, R; Rosman, Benjamin S (IEEE, 2017-11)
    Current structure learning practices in Bayesian networks have been developed to learn the structure between observable variables and learning latent parameters independently. One exception establishes a variant of EM for ...
  • Perlow, J; Rosman, Benjamin S; Hayes, B; Ranchod, P (2017-11)
    An important step in the construction of novel objects is the ability to recognise combinations of raw materials which are likely to be useful. We aim to exploit the intuition that the visual characteristics of candidate ...
  • Burke, Michael (ACM Digital Library, 2017-10)
    Machine learning models trained using images can be used to generate image overlays by investigating which image areas contribute the most towards model outputs. A common approach used to accomplish this relies on blanking ...
  • Görür, OC; Rosman, Benjamin S; Hoffman, G; Albayrak, S (2017-03)
    We propose an architecture that integrates Theory of Mind into a robot’s decision-making to infer a human’s intention and adapt to it. The architecture implements humanrobot collaborative decision-making for a robot ...
  • Earle, AC; Saxe, AM; Rosman, Benjamin S (2017-08)
    Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition of a domain into subtasks remains a ...
  • Darlow, Luke Nicholas; Rosman, Benjamin S (2017-10)
    The high variability of fingerprint data (owing to, e.g., differences in quality, moisture conditions, and scanners) makes the task of minutiae extraction challenging, particularly when approached from a stance that relies ...
  • Van Niekerk, B; Damianou, A; Rosman, Benjamin S (Association for Uncertainty in Artificial Intelligence (AUAI), 2017-08)
    Applying reinforcement learning to robotic systems poses a number of challenging problems. A key requirement is the ability to handle continuous state and action spaces while remaining within a limited time and resource ...
  • Saxe, AM; Earle, AC; Rosman, Benjamin S (Proceedings of Machine Learning Research, 2017-08)
    Hierarchical architectures are critical to the scalability of reinforcement learning methods. Most current hierarchical frameworks execute actions serially, with macro-actions comprising sequences of primitive actions. We ...
  • James, S; Konidaris, G; Rosman, Benjamin S (Association for the Advancement of Artificial Intelligence, 2017-02)
    Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has gained widespread attention in recent years. Despite the vast amount of research into MCTS, the effect of modifications on the algorithm, ...
  • Swart, S; Zietsman, JJ; Coetsee, JC; Goslett, DG; Hoek, A; Needham, D; Monteiro, Pedro MS (Taylor & Francis, 2016-12)
    South Africa’s small pelagic fishery is an important component of the country’s commercial fisheries sector, second in value only to the demersal trawl fishery. Management of this sector relies on frequent hydro-acoustic ...
  • Claessens, R; De Waal, A; De Villiers, Pieter; Penders, A; Pavlin, G; Tuyls, K (SCITEPRESS, 2016-04)
    The range of applications that require processing of temporally and spatially distributed sensory data is expanding. Common challenges in domains with these characteristics are sound reasoning about uncertain phenomena and ...
  • Mwila, Martin K (Tshwane University of Technology, 2014-08)
    Wireless technologies have been rapidly spreading all around the world and have become embedded in most of our modern technologies. Mobility, portability, low cost, and the ease of network installation are the key features ...
  • Burke, Michael (IEEE, 2016-12)
    The ability to predict the importance of an image is highly desirable in computer vision. This work introduces an image ranking scheme suitable for use in video or image sequences. Pairwise image comparisons are used to ...
  • Blasch, E; Costa, PCG; De Villiers, J Pieter; Laskey, KB; Llinas, J; Jousselme, A-L (IEEE, 2016-07)
    Over the course of Dave Hall's career, he highlighted various concerns associated with the implementation of data fusion methods. Many of the issues included the role of uncertainty in data fusion, practical implementation ...
  • Pancham, Ardhisha; Withey, Dan; Bright, G (IEEE, 2016-10)
    The use of low-cost, camera sensors for Simultaneous Localization And Mapping and Moving Object Tracking (SLAMMOT) is a developing research area. Image features can be static or dynamic, sparse or dense, and can appear or ...
  • Hernandez-Leal, P; Taylor, ME; Rosman, Benjamin; Sucar, LE; Munoz de Cote, E (Association for the Advancement of Artificial Intelligence (AAAI), 2016-02)
    In many situations, agents are required to use a set of strategies (behaviors) and switch among them during the course of an interaction. This work focuses on the problem of recognizing the strategy used by an agent within ...
  • Rosman, Benjamin; Hawasly, M; Ramamoorthy, S (Springer Verlag, 2016-02)
    A long-lived autonomous agent should be able to respond online to novel instances of tasks from a familiar domain. Acting online requires `fast' responses, in terms of rapid convergence, especially when the task instance ...

View more