Robotics is becoming more integrated into society and small user-friendly robots are becoming more common in office spaces and homes. This increases the importance of trust in human-robot interaction, which is essential to understand in order to design systems that foster appropriate levels of trust. Too much or not enough trust in a robotic system can lead to inefficiencies, risks, and other damages. The robot in this experiment was used as a navigational system to guide a participant through an arrow maze. This experiment examined human trust in robots, the decision between doing a task or relying on a robot, and inconsistencies between human awareness and robot guidance.

The current paper discusses the concept of human-robot interaction through the lens of a model depicting the key elements of robot-to-human and robot-of-human transparency. Robot-to-human factors represent information that the system (which includes the robot but is broader than just the robot) needs to present to users before, during, or after interactions. Robot-of-human variables are factors relating the human (or the interactions with the human; i.e., teamwork) that the system needs to communicate an awareness of to the users. The paper closes with some potentials design implications for the various transparency domains to include: training and the human-robot interface (including social design, feedback, and display design).

We developed a system dynamics model to simulate the impact of operator trust on performance in multiple robot control. Analysis of a simulated urban search and rescue experiment showed that operators decided to manually control the robots when they lost trust in the autonomous planner that was directing the robots. Operators who rarely used manual control performed the worst. However, the operators who most frequently used manual control reported higher workload and did not perform any better than operators with moderate manual control usage. Based on these findings, we implemented a model where trust and performance form a feedback loop, in which operators perceive the performance of the system, calibrate their trust, and adjust their control of the robots. A second feedback loop incorporates the impact of trust on cognitive workload and system performance. The model was able to replicate the quantitative performance of three groups of operators within 2.3%. This model could help us gain a greater understanding of how operators build and lose trust in automation and the impact of those changes in trust on performance and workload, which is crucial to the development of future systems involving humanautomation collaboration.

This paper describes work underway at the Krasnow Institute for Advanced Study on the topic of modeling social trust. We have built and are testing an ACT-R model intended to replicate human participants building and maintaining social trust using an economic investment game. We already have behavioral and fMRI imaging data for subjects which we expect to generate comparable data by having an ACT-R model read the same inputs the humans did and decide whether to trust or not their partner.

Care homes for persons with dementia are being designed so that caregivers can easily observe and therefore respond to the needs of people with dementia. However, the layout of care homes can then become overly restrictive for its residents, for example, by not supporting intermediate spaces where people can come across one another and start a conversation. We report a case study where a video monitoring system was deployed into a purpose-built care home to help caregivers to observe activities in the blind spots pertaining to the layout. We had carried out a study prior to and subsequent to the deployment of video monitoring in order to understand its impact. We found that both the caregivers and the residents benefitted from video monitoring, provided it is deployed sensitively. Furthermore, the deployment of video monitoring enables the design of more beneficial physical layouts. The deployment of video monitoring goes along with the physical layout of care homes.

Game-based learning has been proven an effective method to engage students in the class. However, it is very challenging to balance playability and learnability when only developing digital games. Some "playable" games may not carry sufficient knowledge; some "learnable" games may reduce the students' interest and curiosity. In this ongoing research, we proposed an innovative learning method, "game-initiated learning." This method consists of three main steps: game, discussion and self-directedlearning. In this model, students can experience real-world problems from the game, discuss problems they found in the game, and finally, the instructors can deliver related knowledge that is useful to solving the problems previously discussed. To validate the proposed method, we selected a topic of disaster education in Taiwan and experimentally developed a set of course materials including a digital game, animation videos and an e-book. We conducted a review meeting, inviting experts from hydraulic engineering, game development, and disaster mediation as well as schoolteachers and students. The reviewers were asked to play the games and review all course materials. From the feedbacks of the reviewers, we found game-initiated learning an educational method with great potential in providing tacit and explicit knowledge about disaster management.

We demonstrate a supplemental episodic memory system that can help arbitrary Soar agents use reinforcement learning in environments with hidden state. Our system watches for learning bottlenecks and then specializes the agent's existing rules by conditioning on recent history. Because we avoid a full episodic retrieval, performance scales well regardless of the agent's lifespan. Our approach is inspired by well established methods for dealing with hidden state.

Agents engaged in lifelong learning can benefit from the ability to acquire new concepts from continuous interaction with objects in their environments which is a ubiquitous ability in humans. This paper advocates the use of sensorimotor concepts that combine perceptual and actuation patterns.Related representations to sensorimotor concepts are Predictive State Representation in dynamical systems, Affordance Based Concepts in language and Skills in reinforcement learning. The paper proposes a system for learning generalized sensorimotor concepts from unsegmented interactions between the agent and the objects in its environment that works in continuous action and observation spaces and in the same time require no reinforcement signals. A proof-of-concept experiment with the proposed system on a simulated e-puck robot is reported to support the applicability of the proposed approach.

Nowadays developing autonomous systems, which can act in various environments and interactively perform their assigned tasks, are intensively desirable. These systems would be ready to be applied in different fields such as medicine, controller robots and social life. Reinforcement learning is an attractive area of machine learning which addresses these concerns. In large scales, learning performance of an agent can be improved by using hierarchical Reinforcement Learning techniques and temporary extended actions. The higher level of abstraction helps the learning agent approach lifelong learning goals. In this paper a new method is presented for discovering subgoal states and constructing useful skills. The method utilizes Ant System optimization algorithm to identify bottleneck edges, which act like bridges between different connected areas of the problem space. Using discovered subgoals, the agent creates temporal abstractions, which enable it to explore more effectively. Experimental Results show that the proposed method can significantly improve the learning performance of the agent.

One way to improve the robustness and flexibility of robot performance is to let the robot learn from its experiences. In this paper, we describe the architecture and knowledge-representation framework for a service robot being developed in the EU project RACE, and present examples illustrating how learning from experiences will be achieved. As a unique innovative feature, the framework combines memory records of low-level robot activities with ontology-based high-level semantic descriptions.