In this paper, we consider the important problem of safe exploration in reinforcement learning. While reinforcement learning is well-suited to domains with complex transition dynamics and high-dimensional state-action spaces, an additional challenge is posed by the need for safe and efficient exploration. Traditional exploration techniques are not particularly useful for solving dangerous tasks, where the trial and error process may lead to the selection of actions whose execution in some states may result in damage to the learning system (or any other system). Consequently, when an agent begins an interaction with a dangerous and high-dimensional state-action space, an important question arises; namely, that of how to avoid (or at least minimize) damage caused by the exploration of the state-action space. We introduce the PI-SRL algorithm which safely improves suboptimal albeit robust behaviors for continuous state and action control tasks and which efficiently learns from the experience gained from the environment. We evaluate the proposed method in four complex tasks: automatic car parking, pole-balancing, helicopter hovering, and business management

No abstract

Socially assistive robots appear as a powerful tool in the upcoming silver society. They are among the technologies for Assisted Living, offering a natural interface with smart environments, while helping people through social interaction. The CLARC project aims to develop a socially assistive robot to help clinicians perform Comprehensive Geriatric Assessment (CGA) procedures. This robot autonomously drives some tests and processes, saving time for the clinician to perform more added-value activities, like designing care plans. The project has recently finished its first two phases, and now it faces its final one. This paper details the current prototype of the CLARC system and the main results collected so far during its evaluation. Then, it describes the updates and modifications planned for the next year, in which long term extensive evaluations will be conducted to validate its acceptability and utility.

One of the aims of cognitive robotics is to endow robots with the ability to plan solutions for complex goals and then to enact those plans. Additionally, robots should react properly upon encountering unexpected changes in their environment that are not part of their planned course of actions. This requires a close coupling between deliberative and reactive control flows. From the perspective of robotics, this coupling generally entails a tightly integrated perceptuomotor system, which is then loosely connected to some specific form of deliberative system such as a planner. From the high-level perspective of automated planning, the emphasis is on a highly functional system that, taken to its extreme, calls perceptual and motor modules as services when required. This paper proposes to join the perceptual and acting perspectives via a unique representation where the responses of all software modules in the architecture are generalized using the same set of tokens. The proposed representation integrates symbolic and metric information. The proposed approach has been successfully tested in CLARC, a robot that performs Comprehensive Geriatric Assessments of elderly patients. The robot was favourably appraised in a survey conducted to assess its behaviour. For instance,

No abstract