No abstract

No abstract

No abstract

We present and validate a method to detect surface cracks with visual and tactile sensing. The proposed algorithm localises cracks in remote environments through videos/photos taken by an on-board robot camera. The identified areas of interest are then explored by a robot with a tactile sensor. Faster R-CNN object detection is used for identifying the location of potential cracks. Random forest classifier is used for tactile identification of the cracks to confirm their presences. Offline and online experiments to compare vision only and combined vision and tactile based crack detection are demonstrated. Two experiments are developed to test the efficiency of the multi-modal approach: online accuracy detection and time required to explore a surface and localise a crack. Exploring a cracked surface using combined visual and tactile modalities required four times less time than using the tactile modality only. The accuracy of detection was also improved with the combination of the two modalities. This approach may be implemented also in extreme environments since gamma radiation does not interfere with the sensing mechanism of fibre optic-based sensors.

To create robots able to generate expressive motions and improve human robot interaction (HRI). An innovative adaptive control system architecture for a robot arm is developed which can adapt the control parameters and motion trajectories according to the perception generated by the human, the environment, and the overall robot interaction. An adaptive fuzzy controller that maps environmental and HRI factors to the PAD emotional model (Pleasure, Arousal, and Dominance) is proposed. These PAD values are used to change the robot strategy to generate trajectories and control parameters, which are designed to express different emotional states. The robot motions are commanded by the Robust Generalized Predictive Controllers (RGPC), using optimization by Youla parameters, that involves robot regulation with adaptive motion. The optimization control uses an adaptive receding horizon designed according to the response of the human and environment interaction. This proposal allows to generate motions with more personalized characteristics for human robot interaction in a non-humanoid robots.  Index Terms-robot arm, adaptive fuzzy control, adaptive robust predictive control, affective robotics I. INTRODUCTION Robots with the ability to cooperate with people and interact in social contexts are now being used in diverse scenarios. To enable long-term interactions, these robots must be able to convey a sense of believability, diversity and adaptation to environmental conditions [1]. It is often said that a key factor in creating intelligent social agents is the ability to express different affective states [2]. However, even when a large portion of human-human affective communication is expressed with gestures and postures [3], most studies related to emotional expression in robotics focused in artificially reproduced human-like facial expressions. Two notable examples are [4] and [5]. Moreover, many robots available on the market cannot perform facial expression due to the mechanical or technological limitations. Examples of these types of robots are mobile robots, manipulator robots, and quadropters, among others. Literature in affective computing reports very few works addressing the challenges that imply the use of non-zoomorphic robots,

No abstract

No abstract

No abstract