Humanoid Robots Human-like Machines Part 14 pps

Bilinear Time Delay Neural Network System for Humanoid Robot Software 511 … … !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ … … !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ … … !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ x y z 1 θ 2 θ 3 θ ……… Figure 14. Kinematics neural network ,,,, 22 lkj i kj i j i i ddd xd dd xd d dx x θθθθθθ (23) Fig. 15 show the growing neural network in this process. 1 θ 2 θ 3 θ x y z (a) 1 st order terms of the Polynomial (b) A part of 2 nd order terms of the Polynomial x 1 θ 2 θ … … x 1 θ 2 θ (c) A part of 3 rd order terms of the Polynomial … … … … … Figure 15. Kinematics neural network by learning process Humanoid Robots, Human-like Machines 512 5.2 Inverse Kinematics In this sub-section, I discuss the inverse kinematics problem. In this problem, the solution has an inverse trigonometric function. 5.2.1 Analytical Method The inverse kinematics of the arm (Fig.13) has 4 type solutions. In this sub-section, I only discuss following solution. The other solutions can be considered in the similar way. ()() [] αθ θ θ += ¿ ¾ ½ ¯ ®  +−++= = − − − r z llzyx ll y x 1 2 2 2 2 1 222 21 1 3 1 1 cos 2 1 cos tan (24) In the similar fashion as the forward kinematics, there is a convergence radius problem of the Taylor expansion of the term, )/(cos),/(tan,/1 11 rzyxy −− . It can be avoidable using the concept of analytical continuation. For example, because the function, )/(tan 1 yx − has the singular points at i± , the expansion near 0/ =yx breaks down near 1± . Fig.16 show the example of region splitting for )/(tan 1 yx − . Such techniques keep a high accuracy for wide range. Fig. 17 shows a part of the neural network using such techniques. It includes the digital switch neuron. -1.5 -1 -0.5 0 0.5 1 1.5 -2 0 2 4 6 8 10 12 14 16 0 3 1 3 6 yx / θ Figure 16. Approximate solution of y x 1 tan − = θ Bilinear Time Delay Neural Network System for Humanoid Robot Software 513 5.2.2 Numerical Method If we do not have the information of arm, the above technique can be applied numerically. In this case, the neural network has the some polynomials with digital switch (Fig.17). … … !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ x y z 1 θ 2 θ 3 θ … y 1 y x 1 tan − !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ !3 1 − 1 !5 1 !7 1 − 1 1 1 1 1 θ … Figure 17. A part of inverse kinematics neural network 5.3 Motion Generation and Control There are many references about the motion generation and control using this system. See references(Nagashima, 2003). Fig. 18 show the example of growing neural network for motion. ε ε ε Output Neuron Output Neuron (a) Cyclic motion (b) Non-cyclic motion Figure 18. Typical perturbation process for motion neural network Humanoid Robots, Human-like Machines 514 ε 0 0 0 ε 0 0 0 0 0 0 0 0 0 … … Joint neurons ε ε ε ε Smoothing neurons ε ε … Figure 19. An example of motion neural network 1 ε 2 ε Gyro sensor signal 01 C 02 C 21 C 12 C 11 C 22 C 13 C 23 C 0 ε + Feedback signal Figure 20. An example of feedback neural network  Figure 21. Experiments using HOAP Bilinear Time Delay Neural Network System for Humanoid Robot Software 515 Fig. 19 shows the neural network example for real motion. Fig. 20 shows the feedback neural network for stabilize the upper body of humanoid robot. Fig. 21 shows the HOAP, humanoid robot for experiment of walk. 5.4 Sound Analysis It is popular that the Fourier transformation (FT) is applied to the pre-processing of a sound analysis. Usually neural network for sound analysis uses the result of this FT. But it's unnatural and wrong in a sense of neural network as a total system basis. In this section, I discuss the problem of the transformation of signal. Proposed model can compose the differential equation for triangle functions as shown in previous section. I call this network CPG. Putting the signal to the neuron and wire of this CPG, this becomes the resonator governed by the following equation, ε ε signal ε ε sound signal ( raw data) (a) (b) + 0 C 0 C− 1 C 2 C 1 y 2 y 3 y b−1 s Figure 22. Central Pattern Recognizer (CPR) () sys dt dy dt yd fm δδωβ =+++ 1 2 1 2 1 2 1 (25) dt dy y 1 2 ω −= (26) 2 2 2 13 yyy += (27) where s is input signal, fm δ δ ω β ,,, are constants determined by connection weights, 21 , yy are neuron value. Fig. 22 shows the neural network for this. It vibrates sympathetically with the input signal and this can recognize a specific frequency signal. I Humanoid Robots, Human-like Machines 516 call this network Central Patten Recognizer (CPR). Using a number of this network, it is possible to create the network which function is very similar to FT. Fig.23 shows the elements of cognitive network, CPR. Fig.24 shows the output of this network and it is a two- dimensional pattern. The sound analysis problem becomes the pattern recognition of this output. The pattern recognition problem is solved by the fitting function problem similar to kinematics problem. … 0 A 1 A 2 A n A … … Figure 23. Sound analyzing neural network Figure 24. Example of sound analyzing results using CPR n A  1 A Bilinear Time Delay Neural Network System for Humanoid Robot Software 517 5.5 Logical Calculation Logical calculation is a basic problem for neural network in old days. Especially, exclusive- OR problem offer the proof that perceptron cannot solve the non-linear problem. In this section, I show examples which can solve the nonlinear logic problem using proposed system. Fig.5 shows the basic logical calculations, (or, and, not, xor). Fig.25 shows the simple application network. It shows the half adder which is the lowest bit adder circuit in an accumulator. y x c s 1− 1− εε εε Figure 25. Half adder 5.6 Sensor Integration The goal of this method is an integration of software system. The fusion of sensor problem is a well-suited application of this model. The concept of an associative memory is known as the introduction to a higher cerebral function. Especially, autocorrelation associative memory is important (Nakano, 1972). This concept can restore the noisy and muddy information to original one. Proposed model can work out this concept through the multiple sensing information. This fact is very important. Proposed model can treat the all sensing data evenly. In a similar fashion, the sensing result information at any levels can be treated evenly. 6. Conclusion In this chapter, I describe the neural network suitable for building the total humanoid robot software system and show some applications. This method is characterized by • uniform implementation for wide variety of applications • simplicity for dynamically structure modification The software system becomes flexible by these characteristics. Now, I’m working on the general learning technique for this neural network. There is a possibility free from NFL problem (Wolper, 1997). This chapter is originally written for the RSJ paper in Japanese (Nagashima, 2006). Humanoid Robots, Human-like Machines 518 7. References Barron, A,(1993). Universal Approximation Bounds for Superpositions of a Sigmoidal Function, IEEE Trans. on Information Theory, IT-39, pp.930-944. Bellman, R,(2003). Perturbation Techniques in Mathematics, Engineering and Physics, Dover Publications, Reprint Edition, June 27. Fujitsu Automation. http://jp.fujitsu.com/group/automation/en/. Grillner, S, Neurobiological Bases of Rhythmic Motor Acts in Vertebrate, Science 228, 143-149 Grune, D and Ceriel J.H.Jacobs, Parsing Techniques,(1991). A Practical Guide, Ellis Horwood Ltd. Hawking, J and Blakeslee, S, (2004). On Intelligence, Times Books McCulloch, W. and Pitts, W. ,(1943). A Logical Calculus of the Ideas Immanent in Nervous Activity, Bulletin of Mathematical Biophysics, 5, pp. 115-133 Hinch, E.J., etc., (1991). Perturbation Methods, Cambridge University Press, October 25. Kimura, H, Fukuoka, Y. and Cohen A.H.,(2003). Biologically Inspired Adaptive Dynamic Walking of a Quadruped Eobot, in 8th International Conference on the Simulation of Adaptive Behavior, 2003, pp. 201-210 Lorenz, E.N., (1963). Deterministic nonperiodic flow, J. Atmos. Sci., 20, 130 Minsky, M. (1990). Logical vs. Analogical or Symbolic vs. Connectionist or Neat vs. Scruffy, Artificial Intelligence at MIT, Vol.1, Expanding Frontiers, MIT Press Nagashima, F, (2003). A Motion Learning Method using CGP/NP, Proceedings of the 2nd International Symposium on Adaptive Motion of Animals and Machines, Kyoto, March, 4-8 Nagashima, F, (2004). - NueROMA -, Homanoid Robot Motion Generation System, Journal of the Robtics Society of Japan, Vol.22, No.2, pp.34-37 (in Japanese) Nagashima, F ,(2006). A Bilinear Time Delay Neural Network Model for a Robot Software System, Journal of the Robotics Society of Japan, Vol.24, No.6,pp.53-64 (in Japanese) Nakamura, Y. et al. (2001). Humanoid Robot Simulator fot the METI HRP Project, Robotics and Autonomous Systems, Vol.37, pp.101-114 Nakano, K., (1972). Associatron – A Model of Associative Memory, IEEE Trans. on Systems Man and Cybernetics, SMC 2, pp. 381-388 Poincare,(1908). Science et Methode Bellman, R, (2003). Perturbation Techniques in Mathematics, Engineering and Physics, Dover Publications; Reprint Edition, June 27 Rumelhart, D. E. , Hinton, G. E. and McCelland, J. L. (1986). A General Framework for Parallel Distributed Processing, In D.E.Rumelhart and J.L.McClelland(Eds.),: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Cambridge, Ma, MIT Press, 1, pp. 45 - 76 Shan, J, Nagashima, F. (2002). Neural Locomotion Controller Design and Implementation for Humanoid Robot HOAP-1, RSJ conference , 1C34 Wolper, D.H. and Macready, W.G. (1997). No Free Lunch Theorems for Optimazation, IEEE Transaction on Evolusionary Computation, 1, 1, pp. 67-82 27 Robot Learning by Active Imitation Juan Pedro Bandera, Rebeca Marfil, Luis Molina-Tanco, Juan Antonio Rodríguez, Antonio Bandera and Francisco Sandoval Grupo de Ingeniería de Sistemas Integrados, Universidad de Málaga Spain 1. Introduction A key area of robotics research is concerned with developing social robots for assisting humans in everyday tasks. Many of the motion skills required by the robot to perform such tasks can be pre-programmed. However, it is normally agreed that a truly useful robotic companion should be equipped with some learning capabilities, in order to adapt to unknown environments, or, what is most difficult, learn to perform new tasks. Many learning algorithms have been proposed for robotics applications. However, these learning algorithms are often task specific, and only work if the learning task is predefined in a delicate representation, and a set of pre-collected training samples is available. Besides, the distributions of training and test samples have to be identical and the world model is totally or partially given (Tan et al., 2005). In a human world, these conditions are commonly impossible to achieve. Therefore, these learning algorithms involve a process of optimization in a large search space in order to find the best behaviour fitting the observed samples, as well as some prior knowledge. If the task becomes more complicated or multiple tasks are involved, the search process is often incapable of satisfying real-time responses. Learning by observation and imitation constitute two important mechanisms for learning behaviours socially in humans and other animal species, e.g. dolphins, chimpanzees and other apes (Dautenhahn & Nehaniv, 2002). Inspired by nature, and in order to speed up the learning process in complex motor systems, Stefan Schaal appealed for a pragmatic view of imitation (Schaal, 1999) as a tool to improve the learning process. Current work has demonstrated that learning by observation and imitation is a powerful tool to acquire new abilities, which encourages social interaction and cultural transfer. It permits robots to quickly learn new skills and tasks from natural human instructions and few demonstrations (Alissandrakis et al., 2002, Breazeal et al., 2005, Demiris & Hayes, 2002, Sauser & Billard, 2005). In robotics, the ability to imitate relies upon the robot having many perceptual, cognitive and motor capabilities. The impressive advance of research and development in robotics over the past few years has led to the development of this type of robots, e.g. Sarcos (Ijspeert et al., 2002) or Kenta (Inaba et al., 2003). However, even if a robot has the necessary skills to imitate the human movement, most published work focus on specific components of an imitation system (Lopes & Santos-Victor, 2005). The development of a complete imitation architecture is difficult. Some of the main challenges are: how to identify which features of an action are important; how to reproduce such action; and how to evaluate the performance of the imitation process (Breazeal & Scassellati, 2002). Humanoid Robots, Human-like Machines 520 In order to understand and model imitation ability, psychology and brain science can provide important items and perspectives. Thus, the theory of the development of imitation in infants, starting from reflexes and sensory-motor learning, and leading to purposive and symbolic levels was proposed by Piaget (Piaget, 1945). This theory has been employed by several authors (Kuniyoshi et al., 2003, Lopes & Santos-Victor, 2005) to build robots that exhibit abilities for imitation as a way to bootstrap a learning process. Particularly, Lopes and Santos-Victor follow a previous work of Byrne and Russon (Byrne & Russon, 1998) to establish two modes of imitation defined in terms of what is shared between the model and the imitator (Lopes & Santos-Victor, 2005): • Action level: The robot replicates the behaviours of a demonstrator, without seeking to understand them. The robot does not relate the observed behaviour with previously memorized ones. This mode is also called ‘mimicking’ by the authors. • Program level: The robot recognizes the performed behaviour so it can produce its own interpretation of the action effect. These modes can be simultaneously active, allowing for an integrated effect. This chapter is focused on the development of a complete architecture for human upper- body behaviour imitation that integrates these two first modes of imitation (action and program levels). However, in order to simplify the described imitation architecture, and, in particular, to simplify the perception system, manipulated tools will not be taken into account. Two main hypothesis guide the proposed work. The first is the existence of an innate mechanism which represents the gestural postures of body parts in supra-model terms, i.e. representations integrating visual and motor domains (Meltzoff & Moore, 1977). This mechanism provides the action level ability and its psychological basis will be briefly described in Section 2. The second hypothesis is that imitation and learning by imitation must be achieved by the robot itself, i.e. without employing external sensors. Thus, invasive items are not used to obtain information about the demonstrator's behaviour. This approach is exclusively based on the information obtained from the stereo vision system of a HOAP-I humanoid robot. Its motor systems will be also actively involved during the perception and recognition processes. Therefore, in the program level, the imitator generates and internally performs candidate behaviours while the demonstrator's behaviour is unfolding, rather than attempting to classify it after it is completed. Demiris and Hayes call this "active imitation", to distinguish it from passive imitation which follows a one-way perceive - recognize - act sequence (Demiris & Hayes, 2002). The remainder of this chapter is organized as follows: Section 2 briefly discusses several related work. Section 3 presents an overview of the proposed architecture. Sections 4 and 5 describe the proposed visual perception and active imitation modules. Section 6 shows several example results. Finally, conclusions and future work are presented in Section 7. 2. Related work 2.1 Action level imitation Action level imitation or mimicking consists of replicating the postures and movements of a demonstrator, without seeking to understand these behaviours or the action's goal (Lopes & Santos-Victor, 2005). This mode of imitation can be shared with the appearance and action levels of imitation proposed in (Kuniyoshi et al., 2003). [...]... model was used to enhance the interaction between human and humanoid robot Accordingly, we designed and implemented the methods which are mentioned above 546 Humanoid Robots, Human-like Machines and successfully verified the feasibility through the demonstrations of human and humanoid robot interactions with AIM Lab’s humanoids 2 Previous Sociable Robots and Affective Communication Model In recent times,... M (2005) Task learning through imitation and human-robot interaction, In: Models and mechanisms of imitation and social learning in robots, humans and animals, Dautenhahn, K & Nehaniv, C (Ed.), Cambridge University Press, Cambridge, UK 544 Humanoid Robots, Human-like Machines Ogata, H & Takahashi, T (1994) Robotic assembly operation teaching in a virtual environment, IEEE Trans on Robotics and Automation,... focused on building new humanoid robots with a self-contained physical body, perception to a degree which allows the robot to be autonomous, and social interaction capabilities of an actual human symbiotic robot This study was built on previous researches about the social interactions and the developments of the first generation humanoid robots, AMI, AMIET coupled with a humansize biped humanoid robot, AMIO... a means to acquire knowledge That is, it is 522 Humanoid Robots, Human-like Machines typically assumed the innate presence of an imitation ability in the robot Thus, the robot in (Hayes & Demiris, 1994) tries to negotiate a maze by imitating the motion of another robot, and it only maintains the distance between itself and the demonstrator constant The humanoid robot Leonardo imitates facial expressions... successive children For upper-body motion tracking, it is assumed that only needs to be updated –this can be seen intuitively as assuming that the tracked human is seated on a chair 530 Humanoid Robots, Human-like Machines The special kinematic structure of the model can be exploited to apply a simple and fast analytic inverse kinematics method which will provide the required joint angles from the... 2005) Several authors propose a VMM algorithm that defines a direct translation from the imitator's end-effector coordinates to the imitator's joint angles which must be sent to the 532 Humanoid Robots, Human-like Machines robot motors to achieve a pose similar to the observed one (Lopes & Santos-Victor, 2005, Molina-Tanco et al., 2005) In the proposed approach, from the coordinates of the hands on... system consider the unrecognized motion as a new behaviour, and consequently it is stored again in the data base The rest of the movements were correctly recognized as Table 1 depicts 534 Humanoid Robots, Human-like Machines 1 Performer #1 Performer #2 Performer #3 Stored behaviours 2 [Cold] [Cold] [OK] [Help] [Well] 3 [OK] 4 [Help] 5 [Well] [Cold] [OK] [Help] [Well] [Help] [Well] 1.00 0.39 0.16 0.26... Future Work In this chapter, an architecture that endows a robot with the ability to imitate has been described This architecture has modules that provide action level and program level 536 Humanoid Robots, Human-like Machines capabilities The program level imitation is achieved by a behaviour recognition module which compares previously memorized and observed behaviours If there are no behaviours that... frame: m(t ) (i , j , l ) ifnomatch m(t + 1) ( i , j , l ) = − 1 (q (t ) (i , j , l ), a(t ) ) ifmatch f w(t + 1) (m(i , j , l )) = w(t ) (m( i , j , l )) − α ifnomatch 1 ifmatch (5) (6) 538 Humanoid Robots, Human-like Machines where the superscript (t) denotes the current frame and the forgetting constant, , is a predefined coefficient that belongs to the interval [0,1] This constant dictates how fast... joint angles, so the local axes referred angles are converted to DH parameters The shoulder conversion can be done applying the following w parameterization to the rotation matrix 1 R : 540 Humanoid Robots, Human-like Machines w 1 R= cθ 2 cθ 3 sθ 1sθ 2 cθ 3 + cθ 1sθ 3 − cθ 1sθ 2 cθ 3 + sθ 1sθ 3 − cθ 2 sθ 3 − sθ 1sθ 2 sθ 3 + cθ 1cθ 3 cθ 1sθ 2 sθ 3 + sθ 1cθ 3 sθ 2 − sθ 1cθ 2 (8) cθ 1cθ 2 where 1, 2 and 3 . Non-cyclic motion Figure 18. Typical perturbation process for motion neural network Humanoid Robots, Human-like Machines 514 ε 0 0 0 ε 0 0 0 0 0 0 0 0 0 … … Joint neurons ε ε ε ε Smoothing neurons ε ε … Figure. sympathetically with the input signal and this can recognize a specific frequency signal. I Humanoid Robots, Human-like Machines 516 call this network Central Patten Recognizer (CPR). Using a number of. This chapter is originally written for the RSJ paper in Japanese (Nagashima, 2006). Humanoid Robots, Human-like Machines 518 7. References Barron, A,(1993). Universal Approximation Bounds for