TY - JOUR T1 - Outline of a sensory-motor perspective on intrinsically moral agents JF - Adaptive Behavior Y1 - 2016 A1 - Christian Balkenius A1 - Lola Cañamero A1 - Philip Pärnamets A1 - Birger Johansson A1 - Martin V Butz A1 - Andreas Olsson AB - We propose that moral behaviour of artificial agents could (and should) be intrinsically grounded in their own sensory-motor experiences. Such an ability depends critically on seven types of competencies. First, intrinsic morality should be grounded in the internal values of the robot arising from its physiology and embodiment. Second, the moral principles of robots should develop through their interactions with the environment and with other agents. Third, we claim that the dynamics of moral (or social) emotions closely follows that of other non-social emotions used in valuation and decision making. Fourth, we explain how moral emotions can be learned from the observation of others. Fifth, we argue that to assess social interaction, a robot should be able to learn about and understand responsibility and causation. Sixth, we explain how mechanisms that can learn the consequences of actions are necessary for a robot to make moral decisions. Seventh, we describe how the moral evaluation mechanisms outlined can be extended to situations where a robot should understand the goals of others. Finally, we argue that these competencies lay the foundation for robots that can feel guilt, shame and pride, that have compassion and that know how to assign responsibility and blame. PB - SAGE VL - 24 UR - https://journals.sagepub.com/doi/10.1177/1059712316667203 IS - 5 N1 - Download ER - TY - CONF T1 - Optimal Noise in Spiking Neural Networks for the Detection of Chemicals by Simulated Agents T2 - Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems Y1 - 2008 A1 - Oros, Nicolas A1 - Volker Steuber A1 - Davey, Neil A1 - Lola Cañamero A1 - Roderick G Adams ED - Seth Bullock ED - Jason Noble ED - Richard A. Watson ED - Mark A Bedau AB - We created a spiking neural controller for an agent that could use two different types of information encoding strategies depending on the level of chemical concentration present in the environment. The first goal of this research was to create a simulated agent that could react and stay within a region where there were two different overlapping chemicals having uniform concentrations. The agent was controlled by a spiking neural network that encoded sensory information using temporal coincidence of incoming spikes when the level of chemical concentration was low, and as firing rates at high level of concentration. With this architecture, we could study synchronization of firing in a simple manner and see its effect on the agent’s behaviour. The next experiment we did was to use a more realistic model by having an environment composed of concentration gradients and by adding input current noise to all neurons. We used a realistic model of diffusive noise and showed that it could improve the agent’s behaviour if used within a certain range. Therefore, an agent with neuronal noise was better able to stay within the chemical concentration than an agent without. JF - Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems PB - MIT Press CY - Winchester, UK SN - 978-0-262-75017-2 UR - https://mitpress-request.mit.edu/sites/default/files/titles/alife/0262287196chap58.pdf ER - TY - CONF T1 - Optimal Receptor Response Functions for the Detection of Pheromones by Agents Driven by Spiking Neural Networks T2 - Proc. 9th European Meeting on Cybernetics and Systems Research, Vol. II Y1 - 2008 A1 - Oros, Nicolas A1 - Volker Steuber A1 - Davey, Neil A1 - Lola Cañamero A1 - Roderick G Adams ED - Trappl, R AB - The goal of the work presented here is to find a model of a spiking sensory neuron that could cope with small variations in the concentration of simulated chemicals and also the whole range of concentrations. By using a biologically plausible sigmoid function in our model to map chemical concentration to current, we could produce agents able to detect the whole range of concentration of chemicals (pheromones) present in the environment as well as small variations of them. The sensory neurons used in our model are able to encode the stimulus intensity into appropriate firing rates. JF - Proc. 9th European Meeting on Cybernetics and Systems Research, Vol. II PB - Austrian Society for Cybernetic Studies CY - Vienna, Austria SN - 978-3-85206-175-7 UR - http://www.cogsci.uci.edu/~noros/mypapers/OROS_2008_EMCSR.pdf ER - TY - CONF T1 - Optimization Criteria Underlying "Winner-Take-All" and "Voting-Based" Action Selection Policies T2 - Towards Intelligent Mobile Robots, TIMR'03: 4th British Conference on Mobile Robotics Y1 - 2003 A1 - Avila-García, Orlando A1 - Lola Cañamero A1 - René te Boekhorst A1 - Davey, Neil ED - U Nehmzow ED - C Melhuish JF - Towards Intelligent Mobile Robots, TIMR'03: 4th British Conference on Mobile Robotics CY - University of the West of England, Bristol ER -