Whole-Body Balance Control of a Humanoid Robot in Real Time Based on ZMP Stability Regions Approach

Abstract

One of the most important and complex tasks for a humanoid robot is to avoid overturning during a bipedal gait. This work aims at setting the base for designing a general balance controller to be used with any humanoid robot. In addition, it is based on a strong simplification of humanoid model which attempts to be used in real-time applications. In particular, several “stability zones” are defined as function of the criticalness of balance. The results are presented in simulation and experimentally, using the humanoid platforms HOAP-3 and TEO.     

Guaranteed interval analysis localization for mobile robots

This paper presents a set membership method (named Interval Analysis Localization (IAL)) to deal with the global localization problem of mobile robots. By using a LIDAR (LIght Detection And Ranging) range sensor, the odometry and a discrete map of an indoor environment, a robot has to determine its pose (position and orientation) in the map without any knowledge of its initial pose. In a bounded error context, the IAL algorithm searches a set of boxes (interval vector), with a cardinality as small as possible that includes the robot’s pose. The localization process is based on constraint propagation and interval analysis tools, such as bisection and relaxed intersection. The proposed method is validated using real data recorded during the CAROTTE challenge, organized by the French ANR (National Research Agency) and the French DGA (General Delegation of Armament). IAL is then compared with the well-known Monte Carlo Localization showing weaknesses and strengths of both algorithms. As it is shown in this paper with the IAL algorithm, interval analysis can be an efficient tool to solve the global localization problem.     

Near-future perception system: Previewed Reality

ABSTRACT

The present paper introduces a near-future perception system called Previewed Reality. In a co-existence environment of a human and a robot, unexpected collisions between the human and the robot must be avoided to the extent possible. In many cases, the robot is controlled carefully so as not to collide with a human. However, it is almost impossible to perfectly predict human behavior in advance. On the other hand, if a user can determine the motion of a robot in advance, he/she can avoid a hazardous situation and exist safely with the robot. In order to ensure that a user perceives future events naturally, we developed a near-future perception system named Previewed Reality. Previewed Reality consists of an informationally structured environment, a VR display or an AR display, and a dynamics simulator. A number of sensors are embedded in an informationally structured environment, and information such as the position of furniture, objects, humans, and robots, is sensed and stored structurally in a database. Therefore, we can forecast possible subsequent events using a robot motion planner and a dynamics simulator and can synthesize virtual images from the viewpoint of the user, which will actually occur in the near future. The viewpoint of the user, which is the position and orientation of a VR display or an AR display, is also tracked by an optical tracking system in the informationally structured environment, or the SLAM technique on an AR display. The synthesized images are presented to the user by overlaying these images on a real scene using the VR display or the AR display. This system provides human-friendly communication between a human and a robotic system, and a human and a robot can coexist safely by intuitively showing the human possible hazardous situations in advance.     

MOTION PLANNING OF AN INTELLIGENT ROBOT USING GA MOTIVATED TEMPORAL ASSOCIATIVE MEMORY

ABSTRACT

The paper discusses the concept of re-planning for a mobile robot in the presence of semidynamic obstacles. The navigational planning is done by employing genetic algorithm until it reaches the goal point. The path segments traversed by the mobile robot are stored by a simple matrix, employing temporal associative memory. During subsequent traversal, the robot utilizes the previously stored matrix to avoid an obstacle path. In case of deadlock, the robot back tracks using TAM and finds alternative paths to reach the goal. This algorithm has been realized on a Pioneer 2DX mobile robot of ActiveMedia Robotic LLC, USA, through client server architecture. The result shows that the robot reaches the goal within a vicinity of a 20 mm radius.     

Action-based sensor space segmentation for soccer robot learning

Robot learning, such as reinforcement learning, generally needs a well-defined state space in order to converge. However, building such a state space is one of the main issues of robot learning because of the interdependence between state and action spaces, which resembles the well-known "chicken and egg" problem. This article proposes a method of action-based state space construction for vision-based mobile robots. Basic ideas to cope with the interdependence are that we define a state as a cluster of input vectors from which the robot can reach the goal state or the state already obtained by a sequence of one kind of action primitive regardless of its length, and that this sequence is defined as one action. To realize these ideas, we need many data (experiences) of the robot and we must cluster the input vectors as hyper ellipsoids so that the whole state space is segmented into a state transition map in terms of action from which the optimal action sequence is obtained. To show the validity of the method, we apply it to a soccer robot that tries to shoot a ball into a goal. The simulation and real experiments are shown.     

Online Object Categorization Using Multimodal Information Autonomously Acquired by a Mobile Robot

Abstract

In this paper, we propose a robot that acquires multimodal information, i.e. visual, auditory, and haptic information, fully autonomously using its embodiment. We also propose batch and online algorithms for multimodal categorization based on the acquired multimodal information and partial words given by human users. To obtain multimodal information, the robot detects an object on a flat surface. Then, the robot grasps and shakes it to obtain haptic and auditory information. For obtaining visual information, the robot uses a small hand-held observation table with an XBee wireless controller to control the viewpoints for observing the object. In this paper, for multimodal concept formation, multimodal latent Dirichlet allocation using Gibbs sampling is extended to an online version. This framework makes it possible for the robot to learn object concepts naturally in everyday operation in conjunction with a small amount of linguistic information from human users. The proposed algorithms are implemented on a real robot and tested using real everyday objects to show the validity of the proposed system.     

Development of a separable search-and-rescue robot composed of a mobile robot and a snake robot

Abstract

In this study, we propose a new robot system consisting of a mobile robot and a snake robot. The system works not only as a mobile manipulator but also as a multi-agent system by using the snake robot's ability to separate from the mobile robot. Initially, the snake robot is mounted on the mobile robot in the carrying mode. When an operator uses the snake robot as a manipulator, the robot changes to the manipulator mode. The operator can detach the snake robot from the mobile robot and command the snake robot to conduct lateral rolling motions. In this paper, we present the details of our robot and its performance in the World Robot Summit.     

Transition Motion from Ladder Climbing to Brachiation with Optimal Load-Allocation Control

Abstract

This paper describes the transition motion from ladder climbing to brachiation for a multi-locomotion robot (MLR). The MLR has versatile modes of locomotion, such as biped walking, quadruped walking, brachiation and ladder climbing. The transition is a challenging motion, because the environmental boundaries change and the robot has to switch the form of its locomotion depending on its surroundings, situations and purposes. The robot supports itself with three end-effectors that maintain its stability, while one hand transfers from a rung on the vertical ladder to a new rung behind the robot for brachiation. A closed kinematic chain is formed by the robot links and the ladder. In this case, if the number of position-controlled active joints is greater than the number of the chain’s degrees of freedom, an internal stress appears because of unavoidable position errors. The huge internal stress may lead some motors to become overloaded. Since the safety of each motor is very important for a serial-link robot, a load-allocation algorithm is proposed to balance the loads of the joint motors. The algorithm is verified through experiments.     

Qualitative navigation for mobile robots in indoor environments

This article describes a novel qualitative navigation method for mobile robots in indoor environments. The approach is based on qualitative representations of variations in sensor behavior between adjacent regions in space. These representations are used to localize and guide planning and reaction. Off-line, the system accepts as input a line-based diagram of the environment and generates a map based on a simple qualitative model of sensor behavior. During execution, the robot controller integrates this map into a reaction module. This architecture has been tested both in simulation and on a real mobile robot. Results from both trials are provided.     

Virtual Chassis for Snake Robots: Definition and Applications

Abstract

Intuitively representing the motion of a snake robot is difficult. This is in part because the internal shape changes that the robot uses to locomote involve the entire body and no single point on the robot intuitively represents the robot’s pose at all times. To address this issue, we present a method of defining body coordinate frames that departs from the typical convention of rigidly fixing a frame to a link on the robot, and instead define a body frame that is based on the averaged position of all of the robot’s links. This averaged frame serves as a virtual chassis that effectively isolates the internal motion of the robot’s shape changes from the external motion, due to the robot’s interaction with its surroundings. This separation of motion allows much simpler models—such as those derived for wheeled vehicles—to accurately approximate the motion of the robot as it moves through the world. We demonstrate the practical advantages of using the virtual chassis body frame by estimating the pitch and roll of a snake robot undergoing dynamic motion by fusing readings from its internal encoders, gyros, and accelerometers with an extended Kalman filter.     

Navigation behavior based on self-organized spatial representation in hierarchical recurrent neural network

ABSTRACT

A cognitive map is an internal model of the external world and contains the spatial representation of the surrounding environment. The existence of the cognitive map was first identified in rats; rats can navigate to their desired destination using cognitive maps while dealing with environmental uncertainty. We performed a mobile robot navigation experiment where obstacles were randomly placed using hierarchical recurrent neural network (HRNN) with multiple timescales. The HRNN was trained to navigate the mobile robot to the destination indicated by a snapshot image. After the training, the HRNN was able to successfully avoid the obstacles and navigate to the destination from any location in the environment. Analysis of the internal states of the HRNN showed that the module with fast timescale handles obstacle avoidance and the one with slow timescale has spatial representation corresponding to the spatial position of the destination. Moreover, in the experiment wherein the novel path appeared, the trained HRNN performed shortcut behavior. The shortcut behavior shows that the HRNN performed navigation using the self-organized spatial representation in the slow recurrent neural network. This indicates that training of goal-oriented navigation, i.e. the navigation motivated by a snapshot image of the destination results in the self-organization of cognitive map-like representation.     

Network Auditing Products

Abstract

The movie Terminator features a classic plot: man against machine. The concept of a powerful robot machine that can become more powerful than man is a frightening one that has lit up the screens of Hollywood for several decades. Today that fear has become a real threat in the eyes of some system administrators who have had to deal with something known as a bot.     

Natural language understanding based on mental image description language <Emphasis Type="Italic">L</Emphasis><Subscript><Emphasis Type="Italic">md</Emphasis></Subscript> and its application to language-centered robot manipulation

The authors have been working on natural language understanding based on the knowledge representation language L _md and its application to robot manipulation by verbal suggestion. The most remarkable feature of L _md is its capability of formalizing spatiotemporal events in good correspondence with human/robotic sensations and actions, which can lead to integrated computation of sensory, motory and conceptual information. This paper describes briefly the process from text to robot action via semantic representation in L _md and the experimental results of robot manipulation driven by verbal suggestion. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Direction-changing fall control of humanoid robots: theory and experiments

Humanoid robots are expected to share human environments in the future and it is important to ensure the safety of their operation. A serious threat to safety is the fall of such robots, which can seriously damage the robot itself as well as objects in its surrounding. Although fall is a rare event in the life of a humanoid robot, the robot must be equipped with a robust fall strategy since the consequences of fall can be catastrophic. In this paper we present a strategy to change the default fall direction of a robot, during the fall. By changing the fall direction the robot may avoid falling on a delicate object or on a person. Our approach is based on the key observation that the toppling motion of a robot necessarily occurs at an edge of its support area. To modify the fall direction the robot needs to change the position and orientation of this edge vis-a-vis the prohibited directions. We achieve this through intelligent stepping as soon as the fall is predicted. We compute the optimal stepping location which results in the safest fall. Additional improvement to the fall controller is achieved through inertia shaping, which is a principled approach aimed at manipulating the robot’s centroidal inertia, thereby indirectly controlling its fall direction. We describe the theory behind this approach and demonstrate our results through simulation and experiments of the Aldebaran NAO H25 robot. To our knowledge, this is the first implementation of a controller that attempts to change the fall direction of a humanoid robot.     

Sliding mode control for trajectory tracking of mobile robot in the RFID sensor space

This paper presents a sliding mode control method for wheeled mobile robots. Because of the nonlinear and nonholonomic properties, it is difficult to establish an appropriate model of the mobile robot system for trajectory tracking. A robust control law which is called sliding mode control is proposed for asymptotically stabilizing the mobile robot to a desired trajectory. The posture of the mobile robot (including the position and heading direction) is presented and the kinematics equations are established in the two-dimensional coordinates. According to the kinematics equations, the controller is designed to find an acceptable control law so that the tracking error will approximate 0 as the time approaches infinity with an initial error. The RFID sensor space is used to estimate the real posture of the mobile robot. Simulation and experiment demonstrate the efficacy of the proposed system for robust tracking of mobile robots. Recommended by Sooyong Lee under the direction of Editor Jae-Bok Song. This work was supported by the Korea Science and Engineering (KOSEF) grant funded by the Korea government (MOST) (No. R01-2007-000-10171-0). Jun Ho Lee received the M.S degree in Mechanical Engineering from Pusan National University. His research interests include factory automation and sliding mode control. Cong Lin received the B.S. degree in Electrical Engineering from Jilin University and the M.S degree in Electrical Engineering from Pusan National University. His research interests include neural network and sliding mode control. Hoon Lim is currently a M.S student in Electrical Engineering of Pusan National University. His research interests include mobile manipulator and sliding mode control. Jang Myung Lee received the B.S. and M.S degrees in Electronics Engineering from Seoul National University, Korea. He received the Ph.D. degree in Computer from the University of Southern California, Los Angeles. Now, he is a Professor in Pusan National University. His research interests include integrated manufacturing systems and intelligent control.     

An autonomous educational mobile robot mediator

So far, most of the applications of robotic technology to education have mainly focused on supporting the teaching of subjects that are closely related to the Robotics field, such as robot programming, robot construction, or mechatronics. Moreover, most of the applications have used the robot as an end or a passive tool of the learning activity, where the robot has been constructed or programmed. In this paper, we present a novel application of robotic technologies to education, where we use the real world situatedness of a robot to teach non-robotic related subjects, such as math and physics. Furthermore, we also provide the robot with a suitable degree of autonomy to actively guide and mediate in the development of the educational activity. We present our approach as an educational framework based on a collaborative and constructivist learning environment, where the robot is able to act as an interaction mediator capable of managing the interactions occurring among the working students. We illustrate the use of this framework by a 4-step methodology that is used to implement two educational activities. These activities were tested at local schools with encouraging results. Accordingly, the main contributions of this work are: i) A novel use of a mobile robot to illustrate and teach relevant concepts and properties of the real world; ii) A novel use of robots as mediators that autonomously guide an educational activity using a collaborative and constructivist learning approach; iii) The implementation and testing of these ideas in a real scenario, working with students at local schools.

LEARNING BEHAVIORS BY AN AUTONOMOUS SOCIAL ROBOT WITH MOTIVATIONS

In this study, an autonomous social robot is living in a laboratory where it can interact with several items (people included). Its goal is to learn by itself the proper behaviors in order to maintain its well-being at as high a quality as possible. Several experiments have been conducted to test the performance of the system.

The Object Q-Learning algorithm has been implemented in the robot as the learning algorithm. This algorithm is a variation of the traditional Q-Learning because it considers a reduced state space and collateral effects. The comparison of the performance of both algorithms is shown in the first part of the experiments. Moreover, two mechanisms intended to reduce the learning session durations have been included: Well-Balanced Exploration and Amplified Reward. Their advantages are justified in the results obtained in the second part of the experiments.

Finally, the behaviors learned by our robot are analyzed. The resulting behaviors have not been preprogrammed. In fact, they have been learned by real interaction in the real world and are related to the motivations of the robot. These are natural behaviors in the sense that they can be easily understood by humans observing the robot.     

Control of flexible manipulators via singular perturbations and distributed vibration damping

A composite control strategy for a two-link flexible manipulator is analyzed which combines hub actuation with distributed vibration control. The hub actuation is based upon an integral manifold approach in which the system dynamics are approximately linearized to any order of a small parameter E representing stiffness of the robot arms. A polymer film is proposed as a distributed actuator to dampen vibrations due to elasticity in the links. Simulation results are provided which show that the addition of the distributed actuator significantly reduces the displacement and velocity of the first flexible mode in each link compared to hub actuation alone. Editor: T. Vincent     

Exploratory Navigation Based on Dynamical Boundary Value Problems

The paper presents a general framework for concurrent navigation and exploration of unknown environments based on discrete potential fields that guide the robot motion. These potentials are obtained from a class of partial differential equation (PDE) problems called boundary value problems (BVP). The boundaries are generated from sensor readings and therefore they change as the robot moves. This framework corresponds to an extension of our previous work (Prestes, E., Idiart, M. A. P., Engel, P. and Trevisan, M.: Exploration technique using potential fields calculated from relaxation methods, in: IEEE/RSJ International Conference on Intelligent Robots and Systems, 2001, p. 2012; Prestes, E., Engel, P. M., Trevisan, M. and Idiart, M. A.: Exploration method using harmonic functions, Robot. Auton. Syst. 40(1) (2002), 25–42). Here, we propose that a careful choice of the PDE and the boundary conditions can produce efficient exploratory behaviors in sparse and dense environments. Furthermore, we show how to extend the exploratory behavior to produce new ones by changing dynamically the boundary function (the value of the potential at the boundaries) as the exploration takes course. Our framework is validated through a series of experiments with a real robot in office environments.     

Single-actuator AUV performing 3-DOF motion

In this study, we aim to design, simulate and build an autonomous underwater robot with constrained number of control input. A one degree-of-freedom (DOF) input robot whose control output come in three-DOF underwater position is created and tested through simulation and experiment.

The robot has a tube-like shape with a vertical pathway inside for pushing water through using a motorized propeller as its only actuator, making ‘1-DOF input’. Despite constraining to one actuator, three different patterns of input by the difference of motor actuation are used to get various output underwater. When the motor rotates forward, the water is pushed upward and the robot moves downward. With backward rotation, the robot rotates around the vertical axis to change orientation. Lastly, when the motor stops, the robot floats with strong buoyancy. In addition, some weights are placed on its body for asymmetrical trajectory.

Following a formation of design and mechanism, a model is derived. A simulation is carried out to verify the ability of the proposed model. Then, a test robot is built and tested in a real water tank. Both the simulation and experiment results support the proposal, showing that the robot can travel in 3-DOF with the limited inputs.