Isura Ranatunga

Optimized Assistive Human–Robot Interaction Using Reinforcement Learning

An intelligent human-robot interaction (HRI) system with adjustable robot behavior is presented. The proposed HRI system assists the human operator to perform a given task with minimum workload demands and optimizes the overall human-robot system performance. Motivated by human factor studies, the presented control structure consists of two control loops. First, a robot-specific neuro-adaptive controller is designed in the inner loop to make the unknown nonlinear robot behave like a prescribed robot impedance model as perceived by a human operator. In contrast to existing neural network and adaptive impedance-based control methods, no information of the task performance or the prescribed robot impedance model parameters is required in the inner loop. Then, a task-specific outer-loop controller is designed to find the optimal parameters of the prescribed robot impedance model to adjust the robots dynamics to the operator skills and minimize the tracking error. The outer loop includes the human operator, the robot, and the task performance details. The problem of finding the optimal parameters of the prescribed robot impedance model is transformed into a linear quadratic regulator (LQR) problem which minimizes the human effort and optimizes the closed-loop behavior of the HRI system for a given task. To obviate the requirement of the knowledge of the human model, integral reinforcement learning is used to solve the given LQR problem. Simulation results on an x-y table and a robot arm, and experimental implementation results on a PR2 robot confirm the suitability of the proposed method.

Enhanced therapeutic interactivity using social robot Zeno

Social robotics has emerged as a new research area in recent years. One of the reasons behind this emergence is the rapid pace of improvements in sensor, actuator and processing capabilities in modern hardware enabling robots to interact with humans more effectively than ever before. The motivation for the work presented in this paper is to use advanced human-robot head-eye interaction algorithms in order to create a robotic framework that assists physical therapists treating sensor-motor impairments, such as Autism and Cerebral Palsy by using robotic systems. The robotic platform used in our work is the social robot Zeno, which has a fantastically friendly appearance and bridges the previously reported uncanny valley. In this paper we report on a new coordination algorithm based on reinforcement learning implemented on Zeno for achieving human like head-eye coordination to visually engage patients with cognitive impairments. The experimental results show that the various methods implemented enables social robot Zeno achieve natural head-eye coordination with significant improvement in accuracy without the need of extensive kinematic analysis of the system.

RoDiCA: a human-robot interaction system for treatment of childhood autism spectrum disorders

In this paper, we describe the implementation of interactive robotics in virtual environments accomplishing human-robot interaction for treatment of Autism Spectrum Disorders (ASDs). Interaction between our system and children suffering from ASDs is accomplished by teaching them body language such as hand and arm motion, facial expressions and speech to encourage them to engage in social interaction with other humans and for improving their motor skills. A Kinect sensor is used to allow direct control of the humanoid robot, Zeno, by the therapist or child to enable dynamic interaction. The motions of Zeno and the child are recorded simultaneously by a motion capture system to assess the interaction. Specifically, we compare arm and torso motions of the child which should closely follow those of the robot. This behavior can be used for clinical treatment and diagnosis during robot assisted therapy. Therapists can take advantage of this interactive behavior to achieve desired poses of the robot that may be beneficial to children with ASDs to enhance their motor skills as well as their social interaction skills. In order to compare the motion characteristics of robots and subjects, we use various metrics such as cross correlation and signal 2-norm. Results show that the childs motion follows the robots motion closely and the analysis techniques are reasonable indicators to compare the similarity of the human and robot motions.

Implementation of interactive arm playback behaviors of social robot Zeno for autism spectrum disorder therapy

In this paper, we describe control algorithms accomplishing human-robot interaction through mimicking behaviors between the humanoid robot Zeno and humans. Specifically, arm and torso motions of the robot follow closely those of the human, this mimicking behavior, can be used for clinical treatment and diagnosis during robot therapy of subjects suffering from Autism Spectrum Disorders (ASD). In this paper, we describe algorithms and results of implementing simple position control schemes on Zeno via visual feedback from Kinect data. The behavior can be used by therapists to achieve desired poses of the robot that may be beneficial to children with ASD by enhancing their motor skills as well as social interaction. Results show that in this case, simple actuators, sensors and control schemes can generate smooth and responsive robot trajectories.

Human-Robot Upper Body Gesture Imitation Analysis for Autism Spectrum Disorders

In this paper we combine robot control and data analysis techniques into a system aimed at early detection and treatment of autism. A humanoid robot - Zeno is used to perform interactive upper body gestures which the human subject can imitate or initiate. The result of interaction is recorded using a motion capture system, and the similarity of gestures performed by human and robot is measured using the Dynamic Time Warping algorithm. This measurement is proposed as a quantitative similarity measure to objectively analyze the quality of the imitation interaction between the human and the robot. In turn, the clinical hypothesis is that this will serve as a consistent quantitative measurement, and can be used to obtain information about the condition and possible improvement of children with autism spectrum disorders. Experimental results with a small set of child subjects are presented to illustrate our approach.

Intent aware adaptive admittance control for physical Human-Robot Interaction

Effective physical Human-Robot Interaction (pHRI) needs to account for variable human dynamics and also predict human intent. Recently, there has been a lot of progress in adaptive impedance and admittance control for human-robot interaction. Not as many contributions have been reported on online adaptation schemes that can accommodate users with varying physical strength and skill level during interaction with a robot. The goal of this paper is to present and evaluate a novel adaptive admittance controller that can incorporate human intent, nominal task models, as well as variations in the robot dynamics. An outer-loop controller is developed using an ARMA model which is tuned using an adaptive inverse control technique. An inner-loop neuroadaptive controller linearizes the robot dynamics. Working in conjunction and online, this two-loop technique offers an elegant way to decouple the pHRI problem. Experimental results are presented comparing the performance of different types of admittance controllers. The results show that efficient online adaptation of the robot admittance model for different human subjects can be achieved. Specifically, the adaptive admittance controller reduces jerk which results in a smooth human-robot interaction.

Neptune: assistive robotic system for children with motor impairments

This paper describes Neptune, a mobile manipulator designed as an assistive device for the rehabilitation of children with special needs, such as those suffering from Cerebral-Palsy. Neptune consists of a mobile robot base and a 6DOF robotic arm, and it is interfaced to users via Wii Remote, iPad, Neural Headset, a camera, and pressure sensors. These interfaces allow patients, therapists and operators to interact with the robot in multiple ways, as may be appropriate in assistive scenarios such as: direct physical interaction with the iPad, arm positioning exercises through WiiMote, remote navigation and object retrieval through the environment via the Neural Headset, etc. In this paper we present an overview of the system and discuss its future uses in rehabilitation of CP children.

Implementation of an adaptive, model free, learning controller on the Atlas robot

Recent events in natural and man-made disasters have highlighted the limitation in mans ability to confine and mitigate damage in such scenarios. Therefore, there is an urgent need for robotic technology that can function in all environments and serve as a substitute to humans in disaster scenarios. This paper presents research efforts to advance walking technology of humanoid robots with application to the Boston Dynamics Atlas robot. The Atlas was designed as part of the DARPA Robotics Challenge (DRC). The paper contribution is in a model free, walking trajectory tracking controller that is tested using GAZEBO robotics simulator. Artificial neural networks are used to learn the robots nonlinear dynamics on the fly using a neuroadaptive control algorithm. The learned nonlinear dynamics are utilized along with a filtered error signal to generate input torques to control the system. Results show that the ability to approximate the robot nonlinear dynamics allows for full-body control without the need of modeling such a complex system. This ability is what makes the control scheme utilized appealing for complex, real-life, robotic applications that occur in a non-laboratory setting.

Explicit force control vs impedance control for micromanipulation

This paper presents a study of different force control schemes for controlling contact during manipulation tasks at the microscale. Explicit force control and impedance control are compared in a contact transition scenario consisting of a compliant microforce sensor mounted on a microrobotic positioner, and a compliant microstructure fabricated using Silicon MEMS. A traditional double mass-spring-damper model of the overall robot is employed to develop the closed-loop force controllers. Specific differences between the two control schemes due to the microscale nature of contact are highlighted in this paper from the experimental results obtained. The limitations and tradeoffs of the two control laws at the microscale due to the presence of backlash are discussed. A simple method to deal with the pull-off force effects specific to the microscale is proposed. Future improvements of the impedance control schemes to include adaptation are discussed in order to handle objects with unknown stiffness.

Adaptive Admittance Control for Human-Robot Interaction Using Model Reference Design and Adaptive Inverse Filtering

Corobotics involves humans and robots working collaboratively as a team. This requires physical human-robot interaction (pHRI) systems that can adapt to the preferences of different humans and have good robustness and stability properties. In this brief, a new inner-loop/outer-loop robot controller formulation is developed that makes pHRI robust to changes in both corobot and human user. First, an inner-loop controller with guaranteed robustness and stability causes a robot to behave like a prescribed admittance model. Second, an outer-loop controller tunes the admittance model so that the robot system assists humans with varying levels of skill to achieve task-specific objectives. This design technique cleanly separates robot-specific control from task performance objectives and allows formal inclusion in an outer design of both an ideal task model and unknown human operator dynamics. Experimental results with the controllers running on a PR2 robot demonstrate the effectiveness of this approach.