Adaptive Task-Space Force Control for Humanoid-to-Human Assistance

We envision a humanoid robot to serve as a source of additional motion-support forces in assistance for frail persons. In this context, we present a control strategy for a humanoid to adaptively regulate its assistive force contribution. First, we identify a human model torque control for optimal execution of a priori known motion task from sample recordings of this task performed by a healthy individual. We utilize the identified model in the proposed position discrepancy based observer of the human torque contribution, the unknown and unmeasurable variable. We propose an experience-based human contribution model learning strategy that allows to improve the human contribution estimate from trial-to-trial. The target assistive torque contribution is then calculated as the difference between the optimal torque required for the motion task and the estimated human contribution. The target assistive torque is integrated into a multi-robot quadratic programming task-space controller to compute the desired interaction force required for the robot to supply the necessary assistive torque for the human model. We use the non-optimal recordings of the human motion task to emulate human frailty and apply our adaptive force control strategy to demonstrate the results of a humanoid successfully assisting the simulated human model to restore the optimal motion task performance.

Adaptive sensorimotor peripersonal space representation and motor learning for a humanoid robot

Micha Hersch

This thesis presents possible computational mechanisms by which a humanoid robot can develop a coherent representation of the space within its reach (its peripersonal space), and use it to control its movements. Those mechanisms are inspired by current theories of peripersonal space representation and motor control in humans, targeting a cross-fertilization between robotics on one side, and cognitive science on the other side. This research addresses the issue of adaptivity the sensorimotor level, at the control level and at the level of simple task learning. First, this work considers the concept of body schema and suggests a computational translation of this concept, appropriate for controlling a humanoid robot. This model of the body schema is adaptive and evolves as a result of the robot sensory experience. It suggests new avenues for understanding various psychophysical and neuropsychological phenomenons of human peripersonal space representation such as adaptation to distorted vision and tool use, fake limbs experiments, body-part centered receptive fields, and multimodal neurons. Second, it is shown how the motor modality can be added to the body schema. The suggested controller is inspired by the dynamical system theory of motor control and allows the robot to simultaneously and robustly control its limbs in joint angles space and in end-effector location space. This amounts to controlling the robot in both proprioceptive and visual modalities. This multimodal control can benefit from the advantages offered by each modality and is better than traditional robotic controllers in several respects. It offers a simple and elegant solution to the singularity and joint limit avoidance problems and can be seen as a generalization of the Damped Least Square approach to robot control. The controller exhibits several properties of human reaching movements, such as quasi-straight hand paths and bell-shaped velocity profiles and non-equifinality. In a third step, the motor modalities is endowed with a statistical learning mechanism, based on Gaussian Mixture Models, that enables the humanoid to learn motor primitives from demonstrations. The robot is thus able to learn simple manipulation tasks and generalize them to various context, in a way that is robust to perturbations occurring during task execution. In addition to simulation results, the whole model has been implemented and validated on two humanoid robots, the Hoap3 and the iCub, enabling them to learn their arm and head geometries, perform reaching movements, adapt to unknown tools, and visual distortions, and learn simple manipulation tasks in a smooth, robust and adaptive way. Finally, this work hints at possible computational interpretations of the concepts of body schema, motor perception and motor primitives.

EPFL2009

Teaching Physical Collaborative Tasks: Object-Lifting Case Study with a Humanoid

Aude Billard, Sylvain Calinon, Elena Gribovskaya

This paper presents the application of a statistical framework that allows to endow a humanoid robot with the ability to perform a collaborative manipulation task with a human operator. We investigate to what extent the dynamics of the motion and the haptic communication process that takes place during physical collaborative tasks can be encapsulated by the probabilistic model. This framework encodes the dataset in a Gaussian Mixture Model, which components represent the local correlations across the variables that characterize the task. A set of demonstrations is performed using a bilateral coupling teleoperation setup; then the statistical model is trained in a pure follower/leader role distribution mode between the human and robot alternatively. The task is reproduced using Gaussian Mixture Regression. We present the probabilistic model and the experimental results obtained on the humanoid platform HRP- 2; preliminary results assess our theory on switching behavior modes in dyad collaborative tasks: when reproduced with users which were not instructed to behave in either a follower or a leader mode, the robot switched automatically between the learned leader and follower behaviors.

IEEE2009

Robotic assistants in therapy and education of children with autism: Can a small humanoid robot help encourage social interaction skills?

Aude Billard

This article presents a longitudinal study with four children with autism, who were exposed to a humanoid robot over a period of several months. The longitudinal approach allowed the children time to explore the space of robot– human, as well as human–human interaction. Based on the video material documenting the interactions, a quantitative and qualitative analysis was conducted. The quantitative analysis showed an increase in duration of pre-defined behaviours towards the later trials. A qualitative analysis of the video data, observing the children’s activities in their interactional context, revealed further aspects of social interaction skills (imitation, turn-taking and role- switch) and communicative competence that the children showed. The results clearly demonstrate the need for, and benefits of, long-term studies in order to reveal the full potential of robots in the therapy and education of children with autism.

2005

Adaptive sensorimotor peripersonal space representation and motor learning for a humanoid robot

Micha Hersch

EPFL2009