Professional Documents
Culture Documents
Object Handling Using Artificial Tactile Affordance System: Naoto Hoshikawa, Masahiro Ohka and Hanafiah Bin Yussof
Object Handling Using Artificial Tactile Affordance System: Naoto Hoshikawa, Masahiro Ohka and Hanafiah Bin Yussof
1. Introduction
Tactile sensation possesses a salient characteristic
Figure 1. Artificial tactile affordance system (ATAS)
among the five senses because it does not occur without
interaction between sensory organs and objects. Touching an
object induces both deformation of it and the sensory organ. Since ATAS is categorized as a behavior-based control
Since the tactile sensing of robots is crucial to perform any system, it more closely resembles subsumption architecture
task [1], we previously focused on tactile sensing and (SSA) [5][6]. Although in SSA each connection between
introduced a new concept called the artificial tactile sensors and actuators has priority, in ATAS no modules
affordance system (ATAS) [2], whose basic idea is an have priority, and they are arranged in parallel form. In
extension of the theory of affordance [3]. each module, we can include a relative complex procedure if
ATAS is based on a recurrent mechanism in which the needed. Therefore ATAS is suited to such rather complex
information obtained from the object and the behavior tasks as assembly and walking on uneven loads.
performed by the robot itself induce subsequent behavior. To In a previous paper [2], we implemented ATAS based on
explain ATAS, we introduce its schematic block diagram the following two methodologies. In methodology 1, ATAS
(Fig. 1). When the tactile information obtained from the is composed of several program modules, and a module is
environment is input into ATAS, a command for robot selected from the set of modules based on sensor
behavior is output, and the robot actuators are controlled information to perform a specified behavior intended by a
based on that command. After that, the environment is designer. In methodology 2, a set of rules is expressed as a
(IJCNS) International Journal of Computer and Network Security, 33
Vol. 2, No. 10, 2010
table composed of sensor input columns and behavior output the current values of A0, A1, A2, and A3 of Table 1 in every
columns, and each rule is transformed to a string of 0 and 1 set period to decide its behavior.
treated as a gene to obtain an optimum gene that adapts to 2.2 Behavior Acquisition Method
the environment using a genetic algorithm (GA) [7]. While
The behavior table is composed of the truth and motor status
methodology 1 was very effective for such fine control as
tables of the sensors. These tables can be expressed with a
handling tasks of humanoid robots, methodology 2 was very
one-dimensional array like genes because all of the truth-
useful to obtain general robotic behavior that was suitable values are Boolean data. Therefore, the behavior table can
for its environment. However, the possibility of method 2 for be designed as a model of a simple genetic algorithm (SGA)
object handling must be further pursued because the robot comprised of Boolean data [7]. Since the behavior table is
can automatically obtain the relationship between sensor evolvable, we call it the Evolutionary Behavior Table
input and behavior output patterns after it has committed to System (EBTS). The design procedure of the behavior table
the environment. using SGA is shown in the following.
In this paper, we apply the Evolutionary Behavior Table First, we design a genotype array that has information
System (EBTS) of methodology 2 to the object handling of a about the behavior table. The length of the genotype array is
two-arm hand because we are examining the possibility of shown with the next formula:
methodology 2 for fine control. After explaining the G = 4S × M (1),
behavior acquisition method using EBTS, we derive a
simulation procedure for a two-hand-arm robot that was where the number of sensors and the bit number of the
developed in another project. In computational experiments, output gradation are S and M , respectively. Sensor
the robot grasps an object and transfers it to a goal. We patterns are calculated as 4 S because each sensor has 2-bit
examine the difference of grasping efficiency between one- graduation.
and two-hand tasks. The genotype model used for the numerical experiments
described in the subsequent section is shown in Fig. 2. The
Table 1: Behavior tables agent possesses three sensing elements, the output of 4-bit
gradation, and a length of 64 × 4 = 256 bits as gene data
information.
The agent’s fitness value is calculated in a simulator that
is equipped with internal functions that evaluate the
efficiency and the task accuracy degrees of the agent. Then
the simulator generates a behavior table from the genotype
array of a one-dimensional vector composed of G elements
(Fig. 2). The agent is evaluated on the basis of the task
achievement degree in the simulator field during a specified
period. The evaluation value obtained by this simulation is
sent to the calculating system for genetic algorithms as
fitness.
advancement over the previously presented one-hand-arm 3.6 Simulator Design for Robotic Hands
robot [8]. The arm system’s DOF is 5, and each finger’s As an object handling task, we adopted an object
DOF is 3. To compensate for the lack of arm DOF, this transportation problem for easy comparison to previous
robot uses its finger’s root joint as its wrist’s DOF. research. In the task, a hemispherical fingertip equipped
with three tactile sensing elements is modeled (Fig. 5). The
motion of the modeled robotic hand is restricted within two
dimensions. Since the wrist is assumed to be fixed, it only
manipulates an object with its fingers. We presume that the
robotic fingertip transports the object to the goal.
difference between the fitness values of the first and second Figure 10. Relationship between maximum fitness and
elites is greater than that of one-hand case. The variation in generation for two-hand case
the top score of one population becomes steady after around
100 generations. Moreover, the fitness value of the first elite
at 1,000 generations is around 560 and is smaller than that
5. Conclusion
of one-hand case. Therefore, the efficiency of object
transportation with two-hand grasping saturated very We implemented an artificial tactile affordance system
rapidly. (ATAS) based on the following methodology. A set of rules
Since object grasping and transportation can be is expressed as a table composed of sensor input columns
performed by one hand, the two-hand case is obviously and behavior output columns, and a row of the table
redundant. Although redundant grasping induces stability, it corresponds to a rule. Since each rule is transformed to a
string of 0 and 1, we treat a long string composed of rule
decreases the efficiency of grasping and transferring.
strings as a gene to obtain an optimum gene that adapts to
Finally, we discuss the efficiency of acquiring autonomy
the environment using a genetic algorithm (GA). We
cooperation behavior of a multi-finger in this EBTS using
propose the Evolutionary Behavior Table System (EBTS)
GA. In this numerical experiment, the number of simulation using a GA to acquire the autonomous cooperation behavior
trials was 100,000, as a result of optimizing the gene data of multiple mobile robots.
until 1,000 generations. This final truth table obtained by In validation experiments, we assume that a robot
the gene data doesn’t always assure an optimum solution, grasps and transfers an object with one or two hands; each
but the calculation cost is reduced from 1.2 × 1077 to hand is equipped with two articulated fingers. In
1.0 × 10 5 because the combination numbers of the input and computational experiments, the robot grasped the object and
transferred it to the goal. This task is performed more
output patterns are calculated as 2 256 ≅ 1.2 ×10 77 , according efficiently in the one-hand case than in the two-hand case.
to Eq. (1). If we used top-down methodology, Although redundant grasping induces stability, it decreases
1.2 × 1077 trials are needed to specify the optimum pattern. the efficiency of grasping and transferring. Although the
Therefore, we accomplished the automatic design of present method requires many computational resources, it is
cooperative behavior of multi-agents for collective tasks. attractive because it is very useful for obtaining general
robotic behavior that is suitable for its environment.
700 References
600 [9] M. Ohka, “Robotic Tactile Sensors,” Encyclopedia of
500 Computer Science and Engineering, Wiley
Encyclopedia of Computer Science and Engineering,
400
Fitne ss