IEEE Computational Intelligence Magazine - May 2018 - 15

AI characters using a computationally
cheap process without the intervention
of the expert developer. The approach
uses a genetic programming algorithm
that refines randomly generated character strategies into better ones using
tournament selection. The generated AI
characters were tested by 27 human
players and were rated according to
results, perceived difficulty and how
engaging the gameplay was. The main
advantages of this procedure are that no
prior knowledge of how to code the
strategies of the AI character is needed
and there is no need to interact with the
internal code of the game. In addition,
the procedure is capable of creating a
wide diversity of players with different
strategic skills, which could be potentially used as a starting point to a further
adaptive process."
IEEE Transactions on Cognitive
and Developmental Systems

Deep Reinforcement Learning With
Visual Attention for Vehicle Classification, by D. Zhao, Y. Chen, and L. Lv,
IEEE Transactions on Cognitive and
Developmental Systems, Vol. 9, No. 4,
December 2017, pp. 356-367.
Digital Object Identifier: 10.1109/
TCDS.2016.2614675
"Automatic vehicle classification is
crucial to intelligent transportation system, especially for vehicle-tracking by
police. Due to the complex lighting and
image capture conditions, image-based
vehicle classification in real-world environments is still a challenging task and
the performance is far from being satisfactory. However, owing to the mecha-

nism of visual attention, the human
vision system shows remarkable capability compared with the computer vision
system, especially in distinguishing
nuances processing. Inspired by this
mechanism, we propose a convolutional
neural network (CNN) model of visual
attention for image classification. A visual attention-based image processing
module is used to highlight one part of
an image and weaken the others, generating a focused image. Then the focused
image is input into the CNN to be classified. According to the classification
probability distribution, we compute the
information entropy to guide a reinforcement learning agent to achieve a
better policy for image classification to
select the key parts of an image. Systematic experiments on a surveillancenature dataset which contains images
captured by surveillance cameras in the
front view, demonstrate that the proposed model is more competitive than
the large-scale CNN in vehicle classification tasks."
IEEE Transactions on Emerging
Topics in Computational
Intelligence

A Strategy for Self-Organized Coordinated Motion of a Swarm of Minimalist
Robots, by A. R. Shirazi and Y. Jin,
IEEE Transactions on Emerging Topics in
Computational Intelligence, Vol. 1, No. 5,
October 2017, pp. 326-338.
Digital Object Identifier: 10.1109/
TETCI.2017.2741505
"Minimalist robots are functionally
highly restricted but well suited for
swarm robotic applications because of

their low costs and small sizes. Connectivity maintenance and collision avoidance are challenging in minimalist
swarm robotic systems due to a short
communication range and the lack of
positional and directional sensing. In this
paper, we introduce a self-organizing
control strategy for collective flocking of
a swarm of minimalist robots with an
aim to improve swarm connectivity and
to reduce the chance of collision between robots. Based on the relative
positional information built up via collaborations, each robot determines a
collision-free operational polygon. This
scheduling scheme coordinates the
motion of the robots by dividing them
into one group of immobile and one
group of mobile robots, such that each
mobile robot is surrounded by immobile robots serving as beacons. In addition, we introduce a cohesive force into
motion planning, which has been shown
to play an important role in maintaining
a swarm during flocking. A new quantitative metric is introduced for measuring the connectivity of a swarm of agents
with local communications, thereby,
evaluating the performance of the proposed control scheme. We run extensive
simulations using simulated Kilobots to
examine the influence of different
sources of noise and the size of swarms
on the connectivity in the swarm and
the speed of flocking. Finally, we implement the proposed algorithm on a
swarm of real Kilobots to compare the
flocking performance with and without
the proposed control strategy for coordinated and collective motion."

May 2018 | IEEE CoMputatIonal IntEllIgEnCE MagazInE

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - May 2018