Search

In this paper, a construction system of outdoor semantic maps by personal mobility robots that move in dynamic outdoor environments is proposed. The maps have topological forms based on understanding of road structures. That is, the nodes of maps are intersections, and arcs are roads between each pair of intersections. Topological framework significantly reduces computer resources, and enables consistent map building in environments which include loops. Trajectories of moving objects, landmarks, entrances of buildings, and traffic signs are added along each road. This framework enables personal mobility robots to recognize dangerous points or regions. The proposed system uses two laser range finders (LRFs) and one omni-directional camera. One LRF is swung by a tilt unit, and reconstruct 3D shapes of obstacles and the ground. The other LRF is fixed on the body of the robot, and is used for moving objects detection and tracking. The camera is used for localization and loop closings. We implemented the proposed system in a personal mobility robot, and demonstrated its effectiveness in outdoor environments.

In the research to realize high standard task-oriented assistant robots, a general and strategic way of development is essential. Otherwise high functionality and potential for evolution of those robots cannot be achieved. Robotic systems are socially expected to assist our daily life in many situations. As a result, projects related to those robots are becoming large, involving many researchers and engineers of universities and companies. This motivated us a new strategy to construct robotic systems based on mother environment and humanoid specialization to keep developing and refining functional elements of robots in an evolutionary way. The mother environment is an entity that creates brains of humanoid robots, where various robotics function elements, libraries, middle-wares and other research tools are integrated. Then the brain of each robot is developed utilizing the functional elements in the mother. We call this process specialization of a humanoid. To enhance this specialization process, we introduce a generator, which realizes conversion of functions in the mother environment for the real-time layer. After the research of these specific robots, enhanced robotics functions are incorporated into the mother again. We call this process feedback. In this chapter, we present these ideas using concrete implementation examples in IRT projects[1], where several robots to assist our daily life are developed.

Autonomous locomotion is one of the most important capabilities for humanoid robots operating within human environments. We present a walking control system that follows a given desired motion online using a layered control architecture, and implemented as a basic system of autonomous walking. A moving goal tracking function and reactive obstacle avoidance functions are implemented together with a stereo vision system, forming higher layer components of an autonomous locomotion system. Experiments using these layers are shown as basic examples of autonomous locomotion control.

This paper describes our research efforts aimed at developing several low-level autonomous capabilities required for remote-operation tasks involving humanoid-type robots. The low-level autonomy considered falls into three categories: 1) walking functions, such as online dynamic balance compensation and online walking trajectory generation, 2) manipulation functions such as arm motion planning and 3D vision based interactive planning, and 3) human interaction functions such as human identification and tracking, face recognition, and voice recognition/speech synthesis. We describe experimental results implemented on the humanoid robot research platforms H6 and H7.

Human can perform variety of limber whole-body motions using numerous muscles and huge number of various sensors. The human brain has all the connections to the sensors and muscles, and learn how to manage them for whole-body motions. In this research, we have aimed to build a complex body with physically massive parallel sensor-motor systems to enter the next stage for studying humanoid brain systems. It is designed to have a flexible spined torso and a whole-body with fully muscle-tendon driven systems. In this paper the design and implementation of the first model of the humanoid is described with some experiments.

Design and acquisition method of environmental model are important issues for robots which act in the real world such as a daily life environment. Robots have to follow up changes of environment and reconstruct the model because of the conditions in the real world environment would be changed constantly. Also the model for unobserved part would be needed and should be inferred when users instruct the robot using symbolic expressions. In this paper, we have focused on stochastic representation of environmental memory to realize smooth communication between humans and robots, and realtime memory management with ambiguities in the real world. We also show that the representation is effective to construct a cooperative task achievement system on intelligent robots.

This paper proposes wave-shape pattern control method for whole-body de-formable robots containing electroactive polymers. Mechanisms consisting of a typicalelectroactive polymer gel containing poly 2 -acrylamido -2- methylpropane sulfonic acid(PAMPS),named ’gel robots’, have been designed, developed, and controlled experimentally.We faced a common problem called, the degrees-of-freedom problem, namely controllingmany points on the gel surface with a small number of inputs. In order to solve the problem,we once reduced the number of inputs to one, and discovered that wave-shape pattern evolvesfor the beam-shaped gel even in a constant uniform electric field. This method makes use ofthe pattern formation. Wave-shaped gels with varying curvature are obtained by switchingthe polarity of a spatially uniform electric field. The method is verified through experimentswhich are carefully designed based on numerical simulations. 1 Introduction Electroactive polymers [1] change their shapes in the electric fields. The fact moti-vated us to design the whole-body deformable robots. The purpose of this study is toestablish methods for deriving a variety of shapes and motions of deformable robotswhose bodies are made of active materials. Shape control of such mechanisms isdifficult, which is commonly called the degrees-of-freedom problem [2], namely aproblem of controlling many points of continuum with a small number of inputs.In order to explore the high dimensional configuration space of elastic objects [3],probabilistic roadmaps was applied.Osada et al. developed a surfactant-driven ionic polymer gel which is made ofpoly 2-acrylamido-2-methylpropane sulfonic acid (PAMPS), and well known for itslarge deformation[4]. Although the gel reversibly bends and stretches by alternatingthe polarity of the electric fields, the spatiotemporal pattern formation has not beenstudied in depth. We have been developing deformable machines utilizing the gel,hereaftercalled”gelrobots”,andproposedmethodsforexploitingavarietyofshapesand motions of the gel[5–8]. The methods were applied and succeeded in generatingvariety of motions such as beam-shaped gels curling around an object and starfish-shaped gels turning over[9]. The pattern formation process of the gel was analyzedrefering to the living things that also have deformable bodies. They accumulate thetemporalsequenceofinputandbuildtheirbodiesinthedevelopmentalprocesscalledmorphogenesis. Uniform structures are converted to complex organs in a uniform

Humanoid robotics hardware and control techniques have advanced rapidly during the last five years. Presently, several companies have announced the commercial availability of various humanoid robot prototypes. In order to improve the autonomy and overall functionality of these robots, reliable sensors, safety mechanisms, and general integrated software tools and techniques are needed. We believe that the development of practical motion planning algorithms and obstacle avoidance software for humanoid robots represents an important enabling technology. This paper gives an overview of some of our recent efforts to develop motion planning methods for humanoid robots for application tasks involving navigation, object grasping and manipulation, footstep placement, and dynamically-stable full-body motions. We show experimental results obtained by implementations running within a simulation environment as well as on actual humanoid robot hardware.

The paper describes the humanoid robot “H6”, which was designed to serve as a platform for experimental research on the development of advanced humanoid-type robots. The key features of the design of H6 include: 1) complete, 35-DOF human-shaped body with joints having sufficient torque to support full-body motion, 2) high-performance PC/AT compatible on-board computer running RT-Linux, a real-time OS that facilitates simultaneous low-level and high-level control, 3) fully self-contained on-board power supply and wireless network conrection, that allows remote operation via radio ethernet, 4) software for dynamic walking trajectory generation, motion planning, and 3D stereo vision. We give an overview of both the hardware and software design components of H6, and discuss some experimental results involving remote operation.

This article addresses the development of a humanoid robot named Saika and skillful manipulations performed by Saika. The developed humanoid robot Saika has a two-DOF neck, dual five-DOF upper arms, a torso and a head which consists of two eyes and two ears. Saika has humansize dimension and weighs eight kilograms. This article also presents three kinds of manipulations performed by Saika: (1) hitting a bounding ball, (2) grasping unknown objects by groping and (3) catching a thrown ball. Those tasks are chosen to study behavior-based movement control and intelligence.