This article describes RHP Friends, a social humanoid robot developed to enable assistive robotic deployments in human-coexisting environments. As a use case application, we present its potential use in nursing by extending its capabilities to operate devices and tools according to the task and by enabling remote assistance operations. To meet a wide variety of tasks and situations in environments designed by and for humans, we develop a system that seamlessly integrates the slim and lightweight robot and several technologies: locomanipulation, multicontact motion, teleoperation, and object detection and tracking. We demonstrate the system’s usage in a nursing application. The robot efficiently performs the daily task of patient transfer and a nonroutine task, represented by a request to operate a circuit breaker. This demonstration, held at the 2023 International Robot Exhibition (IREX), was conducted three times a day over three days.
Trying to infer the strategy of the opponent is very important in games. Especially in Real-Time Strategy Games (RTS), where you have uncertainty and thus cannot see most of the opponent’s actions, but you do not want to be unprepared for its strategy. Good human players can do it almost naturally, but it is a different story for AI players. Plan recognition is a challenging problem, especially with uncertainty and the number of possible actions and states of the world in RTS games. We address the problem of plan recognition in RTS games. We show that an approach based on plan recognition as planning and heuristic search can yield good results and be robust to noise. Furthermore, we found that such an approach has its accuracy decreasing slightly with noisy data, does not need any training beforehand, and could be easily adapted to different RTS games.Our approach allows us to infer in real-time the plan that a player might be pursuing in an RTS game, here we focus on the RTS game called StarCraft, but it could be adapted to many other RTS games.
Goal recognition is a sub-field of plan recognition that focuses on the goals of an agent. Current approaches in goal recognition have not yet tried to apply concept learning to a propositional logic formalism. In this paper, we extend our method for inferring an agent’s possible goal by observing this agent in a series of successful attempts to reach its goal and using concept learning on these observations. We propose an algorithm, LFST (Learning From Successful Traces), to produce concise hypotheses about the agent’s goal. We show that if such a goal exists, our algorithm always provides a possible goal for the agent, and we evaluate the performance of our algorithm in different settings. We compare it to another concept-learning algorithm that uses a formalism close to ours, and we obtain better results at producing the hypotheses with our algorithm. We introduce a way to use assumptions about the agent’s behavior and the dynamics of the environment, thus improving the agent’s goal deduction by optimizing the potential goals’ search space.