Implementing SODA in Embodied Robots
نویسندگان
چکیده
Giving robots the ability to learn without the guidance of a researcher is a practical method of developing more adaptable and intelligent systems. Self-Organizing Distinctive-State Abstraction (SODA) is an algorithm that allows a robot to learn routines from from raw sensorimotor inputs through training. The goal of our experiment was to implement SODA on a simulated version of the Khepera II robot in a T-shaped Maze environment. The task we aimed to complete was training our robot to complete a navigation task that consisted of finding a path from the upper left or upper right corner to a light placed at the bottom of the T-maze. We managed to successfully implement the phases dealing with exploration of the environment and training of HC and TF options, but were unsuccessful at training our robot to properly complete the the light-finding task.
منابع مشابه
Embodying and Improving SODA
We implemented variations on the Self-Organizing Distinctive State Abstraction model for robot state-discretization and task-learning in a Khepera robot. We conclude that hill-climbing as implementd in [5] is detrimental in embodied robots. Because the ultimate goal of developmental systems is intelligent, embodied robots, we believe that implementation in physical robots is an important test o...
متن کاملThe Curious Robot as a Case-Study for Comparing Dialog Systems
Modeling interaction with robots raises new and different challenges for dialog modeling than traditional dialog modeling with less embodied machines. We present four case studies of implementing a typical humanrobot interaction scenario with different state-of-the-art dialog frameworks in order to identify challenges and pitfalls specific to HRI and potential solutions. The results are discuss...
متن کاملEvolution of Communication and Language in Embodied Agents
evolution of communication and language in embodied agents evolution of communication and language in embodied agents evolution of communication and language in embodied agents chapter 7 evolving communication in embodied agents evolution of communication and language link.springer evolution of communication and language in embodied agents evolution of communication and language in embodied age...
متن کاملLook but Don't Stare: Mutual Gaze Interaction in Social Robots
Mutual gaze is a powerful cue for communicating social attention and intention. A plethora of studies have demonstrated the fundamental roles of mutual gaze in establishing communicative links between humans, and enabling non-verbal communication of social attention and intention. The amount of mutual gaze between two partners regulates human-human interaction and is a sign of social engagement...
متن کامل