Mirko Raković

ON SOME ASPECTS OF HUMANOID ROBOTS GAIT SYNTHESIS AND CONTROL AT SMALL DISTURBANCES

This work considers some aspects of the problem of generating and preserving of two-legged gait bearing in mind the requirements for a higher degree of similarity with human gait (anthropomorphism) and robustness to the constantly present small disturbances during the walk. Reference motion was synthesized by semi-inverse method, varying the mode of ZMP traveling along a path selected in advance on the foot–ground surface. It was found that different ways of ZMP motion along the path has a decisive role in the trunk deflection in the sagittal plane. Also, the problem of classification of disturbances and their compensation during the gait is discussed in detail. The significance of the multi-link trunk in the gait synthesis and its role in the compensation of disturbances is also considered.

Comparison of PID and Fuzzy Logic Controllers in Humanoid Robot Control of Small Disturbances

Presence of permanent perturbations during walk requires simultaneous control of dynamic balance preservation and correction of internal synergy to bring it as close as possible to reference one. It is not answered yet in full extent how control for each of these tasks have to be synthesized. In this paper is discussed use of PID and fuzzy control for these purposes. In simulation experiment we applied for dynamic balance preservation only PID controller, but for internal synergy compensation two different controllers (PID and fuzzy) were applied. Obtained results were compared and discussed.

Realization of Biped Walking in Unstructured Environment Using Motion Primitives

Effective and efficient motion of humanoid robots in unstructured dynamic environments is a prerequisite for their activity in the living and working environment of humans. Motion in such environments has to be adjusted all the time to suit the current conditions. This paper presents a method for the synthesis and realization of the biped robot motion (walking) composed of simple movements-primitives, because any complex motion can be composed of tied primitives. The primitives are parametrized with the relationship established between the overall motion characteristics and their own parameters. This way, it is possible to achieve online modification at any moment. The proposed solution was tested by the simulation involving a dynamic robot model. The results demonstrate that it is possible to generate a dynamically balanced walk that can be modified online at any moment of its realization.

Human-like Robot MARKO in the Rehabilitation of Children with Cerebral Palsy

Actual research in the field of robot-supported therapy is dominantly oriented on systems for clinical neurorehabilitation of motor disorders and therapy of difficulties related to autism. However, very little attention is dedicated to the functional development of the therapeutic robot, which would be capable of participating, actively and intelligently, in a verbal dialogue of natural language with a patient and therapist. In this paper an approach is presented for incorporating the human-like robot MARKO in the physical therapy for children with cerebral palsy (CP). The mechanical design of the robot MARKO is briefly described and its context aware cognitive system which connects modules for sensorimotor system, speech recognition, speech synthesis and robot vision is presented. The robot is conceived as a child’s playmate, able to manage three-party natural language conversation with a child and a therapist involved. Traditional CP physical therapies are usually repetitive, lengthy and tedious which results in a patient’s lack of interest and disengagement with the therapy. On the other hand, treatment progress and the improvement of the neural functionality are directly proportional to the amount of time spent exercising. The idea is to use the robot to assist doctors in habilitation/rehabilitation of children, with a basic therapeutical role to motivate the children to practice therapy harder and longer. To achieve this, the robot must fulfill several requirements: it must have hardware design which provides sufficient capabilities for demonstration of gross and fine motor skills exercises, it must have appropriate character design to be able to establish affective attachment of the child, and it must be able to communicate with children verbally (speech recognition and synthesis), and non-verbally (facial expressions, gestures).

Walking on Slippery Surfaces: Generalized Task-Prioritization Framework Approach

Like humans, bipedal robots can easily fall on slippery and low-friction surfaces. In order to avoid costly breakdowns, fall avoidance is of major importance. Recently reported generalized task-prioritization framework enables us to impose dynamical inequality constraints on the robot motion, which we used to create quasi-static walk using task prioritization. Created walking is tested on high- and low-friction surfaces and resulting walking patterns are observed.

Biped Walking on Irregular Terrain Using Motion Primitives

Effective and efficient motion of humanoid robots is a prerequisite for their activity in the unstructured environment. It is of great importance to enable the walk on uneven ground surface. This work presents a method for the synthesis and realization of the online modifiable robot walk that is adjustable to the partially unknown configuration of ground surface. Walk is composed of tied simple movements—primitives which are parameterized with established relationship with overall motion parameters. Proposed approach was tested by simulation and it was demonstrated that it is possible to generate a online modifiable dynamically balanced walk. For such walk is tested the ability to adapt to uneven configuration to uneven terrain.

Online Generation of Biped Robot Motion in an Unstructured Environment

In this work is demonstrated the possibility of using primitives to generate complex movements that ensure motion of bipedal humanoid robots in unstructured environments. It is pointed out that for the robot’s motion in an unstructured environment an on-line generation of motion is required. Generation of motion by using primitives represents superposition of simple movements that are easily performed. Simple movements are either reflex or learned synchronous movements of several joints, and each of these movements represents one primitive. Each primitive has its parameters and constraints that are determined on the basis of the movements capable of performing by a human. A set of all primitives represents the data base from which primitives are selected and combined for the purpose of performing a complex movement.

Humanoid Robot Reaching Task Using Support Vector Machine

A novel approach for the realization of the humanoid robot’s reaching task using Support Vector Machine (SVM) is proposed. The main difficulty is how to ensure an appropriate SVM training data set. Control law is firstly devised, and SVM is trained to calculate driving torques according to control law. For purpose of training SVM, sufficiently dense training data set was generated using designed controller. However, dynamic parameters of the system change when grasping is performed, so SVM coefficients were altered in order to adapt to changes that have occurred. In the stage of verification, the target point to be reached by the robot’s hand is assigned. The trained SVM determines the necessary torques in a very efficient way, which has been demonstrated by several simulation examples.

Generating Complex Movements of Humanoid Robots by Using Primitives

The objective of this work is to demonstrate the possibility of using primitives to generate complex movements that ensure motion of bipedal humanoid robots. Primitives represent simple movements that are either reflex or learned. Each primitive has its parameters and constraints that are determined on the basis of the movements capable of performing by a human. The set of all primitives represents the base from which primitives are selected and combined for the purpose of performing the corresponding complex movement. The proof that a correct selection of primitives is made and that the movement is the appropriate one is obtained on the basis of the maintainance of dynamic balance, which is realized by monitoring the ZMP position, as well as based on the pattern of the very movement.

Parameters adaptation of motion primitives for achieving more efficient humanoid walk

This paper deals with the problem of non synchronicity during the on-line realization of humanoid walk synthesized by combining and tying motion primitives. Motion primitives are simple and parameterized movements. For realization of the on-line modifiable walk, relationship is established between the gait characteristics and the pa-rameters of the primitives. The parameters of the primitives for basic walk were determined empirically, so the problem appeared of non synchronization of the primitives that are executed in parallel. In order to reduce the non synchronicity effects, the algorithm for adaptation of the primitive parameters is introduced. The improved parameters of the primitives allowed the realization of a more efficient walk.