Adaptive Fuzzy and Predictive Controllers for Expressive Robot Arm Movement during Human and Environment Interaction

Abstract

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,

Multi-Platform Intelligent System for Multimodal Human-Computer Interaction

“…Ardila et al implemented an adaptive controller for a robot arm [2], which can adapt motion trajectories to the environment and an overall robot interaction profile. This adaptive controller uses the PAD emotional model (Pleasure, Arousal and Dominance), where PAD values are used to change the strategy of robot movements.…”

“…Ardila [2] Coronado [20] Röning [24] Liu [25,26] Target environ-ment All systems enable making adjustments in the scenario depending on changes in the environment, for example user emotions. Our system, as well as the systems described by Alonso-Martin, Röning and Liu use discrete emotion representation, while the Ardila system uses a continuous pleasure arousal model.…”

Improvement of Trajectory Tracking by Robot Manipulator Based on a New Co-Operative Optimization Algorithm

“…However, the applied PID controller in these works was tuned based on the trial-and-error method. In [5], adaptive fuzzy logic (FL) was utilized to adjust the robot-controller parameters and motion trajectories. A type-2 fuzzy logic with neural networks was optimized by particle-swarm optimization (PSO) for agricultural robots in [6].…”