Kai Olav Ellefsen

Kai Olav Ellefsen
University of Oslo · Department of Informatics

Doctor of Philosophy

About

42
Publications
8,280
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
398
Citations
Additional affiliations
October 2019 - present
University of Oslo
Position
  • Professor (Associate)
August 2016 - October 2019
University of Oslo
Position
  • PostDoc Position
January 2015 - July 2016
Brazilian Institute of Robotics
Position
  • PostDoc Position
Description
  • My research is into autonomous mission planning applied to robotic inspection of underwater installations.
Education
August 2005 - June 2010

Publications

Publications (42)
Preprint
Full-text available
End-to-end congestion control is the main method of congestion control in the Internet, and achieving consistent low queuing latency with end-to-end methods is a very active area of research. Even so, achieving consistent low queuing latency in the Internet still remains an unsolved problem. Therefore, we ask "What are the fundamental limits of end...
Preprint
Designing robots by hand can be costly and time consuming, especially if the robots have to be created with novel materials, or be robust to internal or external changes. In order to create robots automatically, without the need for human intervention, it is necessary to optimise both the behaviour and the body design of the robot. However, when co...
Chapter
Full-text available
Designing robots by hand can be costly and time consuming, especially if the robots have to be created with novel materials, or be robust to internal or external changes. In order to create robots automatically, without the need for human intervention, it is necessary to optimise both the behaviour and the body design of the robot. However, when co...
Article
Full-text available
In modular robotics modules can be reconfigured to change the morphology of the robot, making it able to adapt to specific tasks. However, optimizing both the body and control of such robots is a difficult challenge due to the intricate relationship between fine-tuning control and morphological changes that can invalidate such optimizations. These...
Chapter
Full-text available
Predicting the future using deep learning models is a research field of increasing interest. However, there is a lack of established evaluation methods for assessing their predictive abilities. Images and videos are targeted towards human observers, and since humans have individual perceptions of the world, evaluation of videos should take subjecti...
Preprint
Full-text available
In September 2020, the Broadband Forum published a new industry standard for measuring network quality. The standard centers on the notion of quality attenuation. Quality attenuation is a measure of the distribution of latency and packet loss between two points connected by a network path. A vital feature of the quality attenuation idea is that we...
Article
Neural networks have been widely used in agent learning architectures; however, learnings for one task might nullify learnings for another. Behavioural plasticity enables humans and animals alike to respond to environmental changes without degrading learned knowledge; this can be achieved by regulating behaviour with neuromodulation—a biological pr...
Preprint
Full-text available
In modular robotics, modules can be reconfigured to change the morphology of the robot, making it able to adapt for specific tasks. However, optimizing both the body and control is a difficult challenge due to the intricate relationship between fine-tuning control and morphological changes that can invalidate such optimizations. To solve this chall...
Preprint
Full-text available
In Evolutionary Robotics a population of solutions is evolved to optimize robots that solve a given task. However, in traditional Evolutionary Algorithms, the population of solutions tends to converge to local optima when the problem is complex or the search space is large, a problem known as premature convergence. Quality Diversity algorithms try...
Conference Paper
Full-text available
Neural networks have been widely used in agent learning architectures; however, learning multiple context-dependent tasks simultaneously or sequentially is problematic when using them. Behavioural plasticity enables humans and animals alike to respond to changes in context and environmental stimuli, without degrading learnt knowledge; this can be a...
Article
Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world: Artificial organisms evolving in computational environments have also elicited surprise and wonder from the researchers studying them. The process of ev...
Chapter
Full-text available
A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent’s plans and act...
Chapter
Full-text available
Creating robust robot platforms that function in the real world is a difficult task. Adding the requirement that the platform should be capable of learning, from nothing, ways to generate its own movement makes the task even harder. Evolutionary Robotics is a promising field that combines the creativity of evolutionary optimization with the real-wo...
Preprint
Full-text available
Overcoming robotics challenges in the real world requires resilient control systems capable of handling a multitude of environments and unforeseen events. Evolutionary optimization using simulations is a promising way to automatically design such control systems, however, if the disparity between simulation and the real world becomes too large, the...
Preprint
Full-text available
A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and act...
Article
Full-text available
The structure and performance of neural networks are intimately connected, and by use of evolutionary algorithms, neural network structures optimally adapted to a given task can be explored. Guiding such neuroevolution with additional objectives related to network structure has been shown to improve performance in some cases, especially when modula...
Preprint
Full-text available
The structure and performance of neural networks are intimately connected, and by use of evolutionary algorithms, neural network structures optimally adapted to a given task can be explored. Guiding such neuroevolution with additional objectives related to network structure has been shown to improve performance in some cases, especially when modula...
Preprint
Full-text available
Gaining a better understanding of how and what machine learning systems learn is important to increase confidence in their decisions and catalyze further research. In this paper, we analyze the predictions made by a specific type of recurrent neural network, mixture density RNNs (MD-RNNs). These networks learn to model predictions as a combination...
Preprint
Full-text available
Musical performance requires prediction to operate instruments, to perform in groups and to improvise. We argue, with reference to a number of digital music instruments (DMIs), including two of our own, that predictive machine learning models can help interactive systems to understand their temporal context and ensemble behaviour. We also discuss h...
Article
Full-text available
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic process that transcends the substrate in which it occurs, evolution's creativity is not limited to nature. Indeed, many researchers in the field of digital evolution have o...
Chapter
Full-text available
Four-legged mammals are capable of showing a great variety of movement patterns, ranging from a simple walk to more complex movement such as trots and gallops. Imbuing this diversity to quadruped robots is of interest in order to improve both mobility and reach. Within the field of Evolutionary Robotics, Quality Diversity techniques have shown a re...
Conference Paper
Full-text available
For many, the pursuit and enjoyment of musical performance goes hand-in-hand with collaborative creativity, whether in a choir, jazz combo, orchestra, or rock band. However, few musical interfaces use the affordances of computers to create or enhance ensemble musical experiences. One possibility for such a system would be to use an artificial neura...
Article
Full-text available
An important open problem in robotic planning is the autonomous generation of 3D inspection paths – that is, planning the best path to move a robot along in order to inspect a target structure. We recently suggested a new method for planning paths allowing the inspection of complex 3D structures, given a triangular mesh model of the structure. The...
Conference Paper
We propose a new method for planning paths allowing the inspection of complex 3D structures, given a triangular mesh model of the structure. The method differs from previous approaches in its emphasis on generating and considering also plans that result in imperfect coverage of the inspection target. In many practical tasks, one would accept imperf...
Article
Full-text available
A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forg...
Conference Paper
Full-text available
In this paper we study age-varying plasticities across different components in an artificial neural network performing a reinforcement learning task. An evolutionary algorithm is given the task of mapping the age of agents to the plasticity levels of different network components. The results show that patterns of plasticity resembling biological se...
Conference Paper
Full-text available
We study the costs and benefits of plasticity by evolving agents in environments with different rates of environmental change. Evolution allows both hard-coded strategies and learned strategies, with learning rates varying throughout life. We observe a range of change rates where the balance of costs and benefits are just right for evolving learnin...
Conference Paper
Full-text available
The learning of various skills and behaviors in animals and humans goes through phases known as critical periods, where plasticity is temporarily facilitated. The experiments presented here are designed to shed further light on this phenomenon, by investigating three mechanisms that have been suggested for controlling the timing of critical periods...
Conference Paper
Full-text available
This paper describes a genetic algorithm that was developed for optimizing plans in a robotic competition. The algorithm was used both as a static planner, making plans before matches, and as a dynamic replanner during matches, a task with much stricter demands of efficiency. The genetic algorithm was hybridized with a local search technique, which...
Article
Full-text available
The goal of this thesis is to implement a dynamic scheduling system for an autonomous robot that performs a foraging task in a complex, unstable environment. The work will improve the scheduling system implemented as the author's specialization project with the ability to reschedule intelligently when an opposing robot makes changes to the pla...

Network

Cited By

Projects

Projects (5)
Archived project
Project
Discover new AI models of musical processes and ways to use them in real-time music interaction.