Alle Publikationen

Erweiterte Suche öffnen

Treffer: 2

2014
Chiang, Y.; Chu, T.; Lim, C. D.; Wu, T.; Tseng, S.; Fu, L. (2014) : Personalizing robot behavior for interruption in social human-robot interaction: 2014 IEEE International Workshop on Advanced Robotics and its Social Impacts: Evanston, IL: IEEE, S. 44-49

DOI: https://doi.org/10.1109/ARSO.2014.7020978

Abstract: People engaging in an activity usually has individual tolerance to be interrupted [1], [2]. Humans subconsciously adapt their behaviors to draw other one’s attention and to get into a conversation based on their historical experiences, but robots often fail to be aware of humans’ feeling and thus interrupt their users repeatedly. To endow service robots with such socially acceptable ability, we propose an online human-aware interactive learning framework in this paper, under which the robot personalizes its behaviors according to both observed user’s attention and its conjecture about user’s awareness of itself. To this purpose, the correlation between the robot’s theory of awareness, user’s attention and robot behavior are explored through reinforcement learning techniques. The conducted experiment shows that the robot can personalize its interruption strategy, and the optimal policies converged for at least 26 episodes.

Keywords: Face, Hidden Markov models, human-robot interaction, ieee xplore, Interrupters, interruption strategy, Künstliche Intelligenz, learning (artificial intelligence), Markov processes, online human-aware interactive learning framework, reinforcement learning techniques, robot behavior personalization, Robot sensing systems, robot theory of awareness, service robot, social human-robot interaction, social sciences, user attention, user awareness
Zaraki, A.; Giuliani, M.; Dehkordi, M. B.; Mazzei, D.; D’ursi, A.; De Rossi, D. (2014) : An RGB-D based social behavior interpretation system for a humanoid social robot: 2014 Second RSI/ISM International Conference on Robotics and Mechatronics (ICRoM): Tehran, Iran: IEEE, S. 185-190

DOI: https://doi.org/10.1109/ICRoM.2014.6990898

Abstract: Humanoid social robots that interact with people need to be capable of interpreting the social behavior of their interaction partners in order to respond in a socially appropriate way. In this paper, we present a social behavior interpretation system that enables a humanoid robot to recognize human social behavior by analyzing communicative signals. The system receives the constructed RGB-D scene from a Kinect sensor, extracts information about body gesture and head pose from the scene using Microsoft Kinect SDK, and recognizes eight human social behaviors using a Hidden Markov Model (HMM). We trained the eight-state HMM with a corpus of 35 recorded human-human interaction scenes. The evaluation of the system shows a weighted average recognition rate of 81% for all states.

Keywords: Accuracy, Angemessen(heit) (von Technik), body gesture, eight-state HMM, Feature extraction, Gesture recognition, head pose, Hidden Markov model, Hidden Markov models, human social behavior, human-human interaction scenes, humanlike robot, humanoid social robot, human-robot interaction, ieee xplore, image colour analysis, image sensors, Joints, Kinect sensor, Microsoft Kinect SDK, pose estimation, RGB-D based social behavior interpretation system, RGB-D scene, Robot sensing systems, robot vision, social behavior interpretation system, social behavior recognition, Vectors, weighted average recognition rate

2014

poliTE