Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 11 of 11 for “"Neural controllers"”.

  1. Recurrence and Plasticity in Evolved Neural Controllers

    … more important applications of evolutionary neurocontrollers is the development of systems that are able to dynamically adapt to a changing environment. While traditional approaches to control system design demand that the developer attempt to foresee all possible situations within which the …

    ecu Repository record for Recurrence and Plasticity in Evolved Neural Controllers (opens in a new tab)

  2. Evolution of Grasping Behaviour in Anthropomorphic Robotic Arms with Embodied Neural Controllers

    … reported in this thesis focus upon synthesising neural controllers for anthropomorphic robots that are able to manipulate objects through an automatic design process based on artificial evolution. The use of Evolutionary Robotics makes it possible to reduce the characteristics and parameters …

    plymouth Repository record for Evolution of Grasping Behaviour in Anthropomorphic Robotic Arms with Embodied Neural Controllers (opens in a new tab)

  3. On the Evolutionary Co-Adaptation of Morphology and Distributed Neural Controllers in Adaptive Agents

    … development and evolution of mor- phology and neural controller in artificial agents provided with a distributed neural network. In order to understand if this kind of network is appropriate for the evolution of non trivial behaviours in artificial agents, two experiments (description and results …

    plymouth Repository record for On the Evolutionary Co-Adaptation of Morphology and Distributed Neural Controllers in Adaptive Agents (opens in a new tab)

  4. Stability analysis of recurrent neural networks with applications

    Recurrent neural networks are an important tool in the analysis of data with temporal structure. The ability of recurrent networks to model temporal data and act as dynamic mappings makes them ideal for application to complex control problems. Because such networks are dynamic, however, application …

    colostate Repository record for Stability analysis of recurrent neural networks with applications (opens in a new tab)

  5. Internal vs. External Memory in Neuroevolution: Insights From Hybrid Architectures

    … of Augmenting Topologies (NEAT) to develop neural controllers for agents in a 2-D foraging task. We compare three distinct controller architectures that support different forms of memory: (1) purely recurrent networks; (2) feedforward networks equipped with a pheromone-dropping and detecting …

    tamu Repository record for Internal vs. External Memory in Neuroevolution: Insights From Hybrid Architectures (opens in a new tab) Embargoed until 2028-05-01

  6. NEURAL FEEDBACK CONTRIBUTION TO HUMAN LOCOMOTION CONTROL

    … can be used to test the validity of different neural controllers. In this thesis, we devised three studies to further our understanding of the role different muscle modulations play in human walking and hypothesize the neural mechanisms involved in producing them. In study one, we investigated …

    maryland Repository record for NEURAL FEEDBACK CONTRIBUTION TO HUMAN LOCOMOTION CONTROL (opens in a new tab)

  7. Hybrid control architecture for navigation of autonomous mobile robots

    … behaviours are modelled using fuzzy logic, neural networks and hybrid behavioural encoding incorporating stateflow-fuzzy logic and stateflow-neural networks. The deliberative system is comprised of finite state machines. The processing is achieved in a centralised and/or decentralised manner …

    southwales Repository record for Hybrid control architecture for navigation of autonomous mobile robots (opens in a new tab) Download PDF for Hybrid control architecture for navigation of autonomous mobile robots (opens in a new tab)

  8. Biologically inspired computational structures and processes for autonomous agents and robots

    … it explores behaviors generated by artificial neural structures appropriately shaped by the processes of evolution and spatial learning;The first part of this dissertation deals with the evolution of artificial neural controllers for a box-pushing robot task. We show that evolution discovers …

    iastate Repository record for Biologically inspired computational structures and processes for autonomous agents and robots (opens in a new tab)