Search

We present an application of a socially assistive robotics (SAR) system in a therapeutic setting. We examine the amount of interaction elicited by the robot in a therapeutic setting with individuals post-stroke. We examine the role of various communication modalities, and their affects on the participants' responses. Seven participants of mild to moderate functional impairment due to stroke interacted with our SAR system during three sessions of motor task practice. The robot guided the users as they performed a wire puzzle task, while providing them with feedback about their performance. We evaluated the amount of verbalization and eye contact made with the robot. Our results indicate that users make eye contact more often than they verbalize when interacting with the robot. Further, user interactions are most frequent at the beginning of a practice session, and occur less frequently as the session progresses. When a user observes that the robot is not responding to a certain type of communication, the user limits the use of that communication modality. These insights should be useful in the design of future robot-based therapeutic interventions., (© 2011 IEEE)

This paper discusses the emergence of sensorimotor coordination for ESCHeR, a 4DOF redundant foveated robot-head, by interaction with its environment. A feedback-error-learning(FEL)-based distributed control provides the system with explorative abilities with reflexes constraining the learning space. A Kohonen network, trained at run-time, categorizes the sensorimotor patterns obtained over ESCHeR's interaction with its environment, enables the reinforcement of frequently executed actions, thus stabilizing the learning activity over time. We explain how the development of ESCHeR's visual abilities (namely gaze fixation and saccadic motion), from a context-free reflex-based control process to a context-dependent, pattern-based sensorimotor coordination can be related to the Piagetian 'stage theory'.

Focuses on learning human arm movements by imitation through a model consists of a hierarchy of artificial neural networks. Validation of the model in a biomechanical simulation of a 37 degree of freedom humanoid; Utilization of data from human arm movements recorded as input to the model; Record of the data from human arm movement using video and marker-based tracking systems.

Studies a robotic domain in which human acts both as a teacher and a collaborator to a mobile robot. Development of an approach that allows a robot to learn task representations from its own experiences of interacting with a human; Mechanism that constructs high-level task representations based on the robot's underlying capabilities; Generalization of the framework to allow a robot to interact with humans.

Details a study which explored the idea that interactions between a robot and its environment can be efficiently captured through observation of behavior use over time. Experimental setup; Mobile robots used in the experiments; Explanation of the learning algorithm; Results and discussion; Conclusion.

Discusses the challenges of learning social behavior in the multi-robot domain. Key motivations for social rules; Concept of prototypical states of social interactions; Forms of social reinforcement; Description of the experimental environment and the robot testbed; Implementation of social reinforcement.

Abstract . This paper attempts to bridge the fields of machine learning, robotics, and distributed AI. It discusses the use of communication in reducing the undesirable effects of locality in fully distributed multi-agent systems with multiple agents robots learning in parallel while interacting with each other. Two key problems, hidden state and credit assignment, are addressed by applying local undirected broadcast communication in a dual role: as sensing and as reinforcement. The methodology is demonstrated on two multi-robot learning experiments. The first describes learning a tightly-coupled coordination task with two robots, the second a loosely-coupled task with four robots learning social rules. Communication is used to (1) share sensory data to overcome hidden state and (2) share reinforcement to overcome the credit assignment problem between the agents and bridge the gap between local individual and global group pay-off. [ABSTRACT FROM AUTHOR]