We consider the area of intelligent road vehicles, especially, the topic of automated vehicles. Focusing on the importance of the automated steering, we address the challenge of automated keeping of a car in the middle of the driving lane. Our objective is to investigate the feasibility of employing genetic programming (GP) to evolve the automated steering of a car. The latter is implemented in the Open Source Racing Car Simulator (TORCS) with a realistically modeled steering featuring both a delay of response and a rate limit. We propose two approaches aimed at improving the efficiency of evolution via GP. In the first approach we implement an incremental evolution of the steering function by commencing the evolution with an ideal car and gradually increasing the degree of its realism (i.e., the amount of steering delay) in due course of evolution. The second approach is based on incorporating expert knowledge about the (expected) structure of the steering function according to the servo control model of steering. The experimental results verify that the proposed approaches yield an improved efficiency of evolution in that the obtained solutions are both of a better quality and could be obtained faster than those of the canonical GP.

The proposed method applies genetic algorithms (GA) to optimize the weight coefficients of the power spectrum of the Fourier-transformed signal of lateral acceleration of a moving car. The evolved weighted power spectrum detects the steering oscillations caused by the delayed steering response of a human driver in normal, routine driving situations - traffic-less driving on straight and curved roads. Delayed steering response is often a result of drivers having an inadequate cognitive load due to either distraction or cognitive overload. The experimental results, conducted on a realistically simulated car and its environment, indicate that, compared to the power spectrum featuring equal (flat) weight coefficients, the evolved weighted power spectrum facilitates improved discrimination between (i) signals of the lateral acceleration of the car driven by cognitively impaired (i.e., distracted by texting on a mobile phone while driving) drivers and (ii) analog signals of the car, driven by fully attentive drivers. Moreover, for all human drivers who participated in the experiments, the weighted power spectrum of the lateral acceleration of the car driven with distraction, even on a straight section of the road (i.e., inherently featuring lower values of the power spectrum) is even higher than that of the car driven by attentive drivers along curved roads (inherently, featuring higher values of the power spectrum). These results suggest that the proposed method would be applicable for discriminating between subtle driver-induced steering oscillations on straight roads and well-manifested, yet normal steering behavior of drivers when cornering. We view the obtained results as a step towards the development of an early warning system of the inadequate cognitive load of drivers under routine driving conditions - well before any urgent reaction to an eventually dangerous traffic situation might be needed.

In our work we consider the area of intelligent road vehicles, especially, the topic of automated vehicles. Our objective is to automatically develop - by applying a supervised learning approach - the steering of a realistically simulated car featuring a steering delay and rate limit of turning of front wheels. Due to the adopted physical constrains, the typically used steering mechanisms (based on servo-control model) result in a non-stable, oscillating behavior of the controlled car. The proposed approach of automated development of steering for such a realistically simulated car employs the perception-action relationship obtained from the sample runs of an ideal car (featuring instant steering response) steered by the servo-control model. Then, implying that offsetting the perceptions in the obtained relationship back in time to the value equal to the steering delay would mimic the behavior of the car featuring steering delays, we used the so modified perception-action relationship to train the proposed regression based model. The experimental results verify that the derived automated steering controls the car featuring steering delays of 100 ms and 200 ms in a much similar way as the servo-control steers an ideal car. Moreover, for delay of 400 ms the steering, developed via proposed approach provides a better quality of control than that obtained from one of the most versatile unsupervised machine learning approaches - genetic programming.

Haptic interaction is a key capability for social robots that closely interact with people in daily environments. Such human communication cues as gaze behaviors make haptic interaction look natural. Since the purpose of this study is to increase human-robot touch interaction, we conducted an experiment with 20 participants who interacted with a robot with different combinations of gaze behaviors and touch styles. The experimental results showed that both gaze behaviors and touch styles influence the changes in the perceived feelings of touch interaction with a robot.

The recognition of an indicated object by an interacting person is an essential function for a robot that acts in daily environments. To improve recognition accuracy, clarifying the goal of the indicating behaviors is needed. For this purpose, we experimentally compared two kinds of interaction strategies: a robot that explicitly provides instructions to people about how to refer to objects or a robot that implicitly aligns with the people's indicating behaviors. Even though our results showed that participants evaluated the implicit approach to be more natural than the explicit approach, the recognition performances of the two approaches were not significantly different.

We propose an approach of applying genetic programming (GP) for automated development of electronic stability program (ESP) of a car, realistically simulated in The Open Source Racing Car Simulator (TORCS). ESP facilitates the yaw rotation of an unstable (e.g., understeering or oversteering) car in slippery road conditions by applying asymmetric braking forces to its wheels. In the proposed approach, the amount of ESP-induced braking force is evolved - via GP - as an algebraic function of the parameters, pertinent to the state of the car, and their derivatives. The experimental results suggest that, compared to the car without ESP, the best evolved ESP offers a superior controllability - in terms of both (i) a smaller deviation from the ideal trajectory and (ii) faster average speed on a given, “snowy” test track. Presented work could be viewed as step towards the verification of the feasibility of GP for automated development of ESP. Also, we hope that the ESP, as a contributed new functionality of TORCS, would enrich the experience of gamers by adding an enhanced controllability of their cars in challenging road conditions.

Analysis of human motion is one of the most curious fields among different disciplines of socio-psychology, neuro biology and computer science. A person's walk is so crucial because it is associated with lots of other aspects which yield very important information related to emotions, personality, and neurological disorder. The morphological and psychological information induced from both the physiology and neurology involved in motion is one of the key research fields that could one day resolve the various challenges existing in today's intelligent systems inspired from nature. The most interesting among all these is, those wealth of data can be artificially trained using the complex systems in response to generate evidences for identifying the particular person [1]. This paper is the extension of human gait recognition which presents the analysis of efficiency of genetic programming in different cases involved in feature extraction and gait recognition.

This paper will discuss about implementation of a voting system and weighted credibility to augment evolution process of an emotion recognition module. The evolution process of the emotion recognition module is one part of ongoing research on designing an intelligent agent capable of emotion recognition, interaction, and expression. Genetic programming evolves the classifiers, while genetic algorithm evolves the weighted credibility as a modification of parallel voting systems. The experimental results suggest that the implementation of weighted credibility evolution improves the performance of training, in the form of significantly reduced training time needed.

This paper reports an interactive approach to improve the recognition performance by robots of objects indicated by humans during human-robot interaction. We developed an approach based on two findings in conversations where a human refers to an object, which is confirmed by a robot. First, humans tend to use the same words or gestures as the robot in a phenomenon called alignment. Second, humans tend to decrease the amount of information in their references when the robot uses excess information in its confirmations: in other words, alignment inhibition. These findings lead to the following design; a robot should use enough information without being excessive to identify objects to improve recognition accuracy because humans will eventually use similar information to refer to those objects by alignment. If humans more frequently use the same information to identify objects, the robot can more easily recognize those being indicated by humans. To verify our design, we developed a robotic system to recognize the objects to which humans referred and conducted a control experiment that had 2 × 3 conditions; one factor was the robot's confirmation way and another was the arrangement of the objects. The first factor had two levels to identify objects: enough information and excess information. The second factor had three levels: congestion, two groups, and a sparse set. We measured the recognition accuracy of the objects humans referred to and the amount of information in their references. The success rate of the recognition and information amount was higher in the adequate information condition than in the excess condition in a particular situation. The results suggested the possibility that our proposed interactive approach improved recognition performance.

We propose a wolf-caribou predator-prey system to verify our hypothesis that relatively complex collective escaping behavior may emerge from simple, implicit, locally defined, and therefore scalable interactions between the caribou (prey) agents. Proposing two different communication mechanisms – (i) simple, basic mechanism of implicit interaction, and (ii) explicit communications promoting the awareness of the caribou about the identity of the chased one (i.e., empathy), we present a comparative analysis of the implications of these communication mechanisms on the efficiency of evolution of the emerged collective behavior. We used strongly typed genetic programming with exception handling capabilities to evolve the collective behavior of caribou agents. The experimental results suggest that the empathy facilitates the evolution of collective escaping behavior of the team of caribou agents..

The social brain hypothesis suggests that humans evolved larger brains and intelligence as adaptations to an increasingly complex social environment. We believe that social role division is a key factor in the evolution of social intelligence. To examine the the role of this factor, we extend Challet and Zhang’s Minority Game by adding a pre-decision communication stage and using a continuous strategy space instead of a binary one, and develop an evolutionary model based on this game. The evolutionary simulations demonstrate that the system alternates between two states: one with homogeneous social behavior and the other with heterogeneous behavior. We observe differentiation of social roles in the latter state: we find a “pivotal agent ” that tends to adopt low-risk, low payoff strategies but determines which strategy will be in the minority and which in the majority, and we find “risk taker” that tend to adopt high-risk, high pay-off strategies. Using social sensitivity as a measure of social intelligence, we show that the level of social sensitivity correlates with the social roles, and is also a major factor in the mechanisms by which social roles switch.

We present a study on the cumulative effect of the bloat and the seeding of the initial population, inspired by genetic transposition (GT), on the efficiency of incremental evolution of simulated snake-like robot (Snakebot). In the proposed incremental genetic programming (IGP), the task of coevolving the locomotion gaits and sensing of the bot in a challenging environment is decomposed into two sub-tasks, implemented as two consecutive evolutionary stages. First, we use genetic programming (GP) with two ways of bloat management, (i) parsimony pressure which penalizes the bloat and (ii) no bloat control, to evolve two pools of sensor-less Snakebots. During the second stage of IGP, we use these pools to seed the initial population of Snakebots applying two methods of seeding: canonical seeding and GT-inspired seeding. The empirical results indicate that the efficiency of the first stage of IGP for both bloat control techniques is similar. However, the bloated bots contribute to a much more efficient second stage of evolution. Compared to the canonical seeding with parsimony bots, the GT-inspired seeding with bloated Snakebots yields about five times higher probability of success and similar decrease of computational effort of the second stage of IGP.

We present an approach for automated evolutionary design of the functionary of driving agent, able to operate a software model of fast running car. The objective of our work is to automatically discover a set of driving rules (if existent) that are general enough to be able to adequately control the car in all sections of predefined circuits. In order to evolve an agent with such capabilities, we propose an indirect, generative representation of the driving rules as algebraic functions of the features of the current surroundings of the car. These functions, when evaluated for the current surrounding of the car yield concrete values of the main attributes of the driving style (e.g., straight line velocity, turning velocity, etc.), applied by the agent in the currently negotiated section of the circuit. Experimental results verify both the very existence of the general driving rules and the ability of the employed genetic programming framework to automatically discover them. The evolved driving rules offer a favorable generality, in that a single rule can be successfully applied (i) not only for all the section of a particular circuit, but also (ii) for the sections in several a priori defined circuits featuring different characteristics.

We propose an approach of automated co-evolution of the optimal values of attributes of active sensing (orientation, range and timing of activation of sensors) and the control of locomotion gaits of simulated snake-like robot (Snakebot) that result in a fast speed of locomotion in a confined environment. The experimental results illustrate the emergence of a contactless wall-following navigation of fast sidewinding Snakebots. The wall-following is accomplished by means of differential steering, facilitated by the evolutionary defined control sequences incorporating the readings of evolutionary optimized sensors.

We present an approach for evolutionary design of the driving style of an agent, remotely operating a scale model of a car in a human competitive way. The agent perceives the environment from an overhead video camera and conveys its actions to the car via standard radio remote control transmitter. In order to cope with the video feed latency we propose an anticipatory modeling in which the agent considers its current actions based on the anticipated intrinsic (rather than currently available, outdated) state of the car and its surrounding. We formalized the notion of driving style by defining the key parameters, which describe it, and demonstrated the feasibility of applying genetic algorithms to evolve the optimal values of these parameters. The optimized driving style, employed by the agent, is human competitive in that it yields both faster and more consistent lap times than those of a human around a predefined circuit. Presented work can be viewed as a step towards the automated design of the control software of remotely operated vehicles capable to find an optimal solution to various tasks in a priori known environmental situations. Also, the results can be seen as a verification of the feasibility of developing a framework of adaptive racing games in which the human competes against a computerized opponent with matching capabilities, both operating physical, scale models of cars.

We discuss an approach of incorporating interactively learned consensus sequences (ILCS) in genetic programming (GP) for efficient evolution of simulated Snakebot situated in a challenging environment. ILCS introduce a biased mutation in GP via probabilistic context sensitive grammar, in which the probabilities of applying the production rules with multiple right-hand side alternatives depend on the grammatical context. The distribution of these probabilities is learned interactively from the syntax of the Snakebots, exhibiting behavioral traits that according to the human observer are relevant for the emergence of ability to overcome obstacles. Because at the earlier stages of evolution these behavioral traits are not necessarily pertinent to the best performing (i.e. fastest) Snakebots, the user feedback provides the evolution with an additional insight about the promising areas in the fitness landscape. Empirical results verify that employing ILCS improves the efficiency of GP in that the evolved Snakebots are faster than those obtained via canonical GP.

We present an approach for evolutionary design of an agent, remotely operating a scale model of a car running in a fastest possible way. The agent perceives the environment from a video camera and conveys its actions to the car via standard radio control transmitter. In order to cope with the video feed latency we propose an anticipatory modeling in which the agent considers its current actions based on the anticipated intrinsic (rather than currently available, outdated) state of the car and its surrounding. The agent is first evolved on software models of the car and tracks, and then adapted to the real world. During the adaptation, the lap times improve steadily to the values close to the values obtained from the evolution on the models. An evolutionary optimization of the avoidance of a small obstacle results in lap times that are virtually the same as the best lap times achieved on the same track without obstacles. Presented work can be viewed as a step towards developing a racing game in which the human competes against a computer, both operating scale models of racing cars.

We present an approach for automated evolutionary design of driving agent, able to remotely operate a scale model of racing car running in a fastest possible way. The agent's actions are conveyed to the car via standard radio control transmitter. The agent perceives the environment from a live video feedback of an overhead camera. In order to cope with the inherent video feed latency, which renders even the straightforward tasks of following simple routes unsolvable, we implement an anticipatory modeling - the agent considers its current actions based on anticipated intrinsic (rather than currently available, outdated) state of the car and its surrounding. The driving style (i.e. the driving line combined with the speed at which the car travels along this line) is first evolved offline on a software simulator of the car and then adapted online to the real world. Experimental results demonstrate that on long runs the agent-operated car is only marginally slower than a human-operated one, while the consistence of lap times posted by the evolved driving style of the agent is better than that of a human. This work can be viewed as a step towards the development of a framework for automated design of the controllers of remotely operated vehicles capable to find an optimal solution to various tasks in different traffic situations and road conditions.

In this work we propose an approach of incorporating learned mutation strategies (LMS) in genetic programming (GP) employed for evolution and adaptation of locomotion gaits of simulated snake-like robot (Snakebot). In our approach the LMS are implemented via learned probabilistic context-sensitive grammar (LPCSG). The LPCSG is derived from the originally defined context-free grammar, which usually expresses the syntax of genetic programs in canonical GP. Applying LMS implies that the probabilities of applying each of particular production rules in LPCGS during the mutation depend on the context. These probabilities are learned from the aggregated reward values obtained from the parsed syntax of the evolved best-of-generation Snakebots. Empirically obtained results verify that LMS contributes to the improvement of computational effort of both (i) the evolution of the fastest possible locomotion gaits for various fitness conditions and (ii) the adaptation of these locomotion gaits to challenging environment and degraded mechanical abilities of Snakebot. In all of the cases considered in this study, the locomotion gaits, evolved and adapted employing GP with LMS feature higher velocity and are obtained faster than with canonical GP.

Inspired by the efficient method of locomotion of the rattlesnake Crotalus cerastes, the objective of this work is automatic design through genetic programming (GP) of the fastest possible (sidewinding) locomotion of simulated limbless, wheelless snake-like robot (Snakebot). The realism of simulation is ensured by employing the Open Dynamics Engine (ODE), which facilitates implementation of all physical forces, resulting from the actuators, joints constrains, frictions, gravity, and collisions. Reduction of the search space of the GP is achieved by representation of Snakebot as a system comprising identical morphological segments and by automatic definition of code fragments, shared among (and expressing the correlation between) the evolved dynamics of the vertical and horizontal turning angles of the actuators of Snakebot. Empirically obtained results demonstrate the emergence of sidewinding locomotion from relatively simple motion patterns of morphological segments. Robustness of the sidewinding Snakebot, which is considered to be the ability to retain its velocity when situated in an unanticipated environment, is illustrated by the ease with which Snakebot overcomes various types of obstacles such as a pile of or burial under boxes, rugged terrain, and small walls. The ability of Snakebot to adapt to partial damage by gradually improving its velocity characteristics is discussed. Discovering compensatory locomotion traits, Snakebot recovers completely from single damage and recovers a major extent of its original velocity when more significant damage is inflicted. Exploring the opportunity for automatic design and adaptation of a simulated artifact, this work could be considered as a step toward building real Snakebots, which are able to perform robustly in difficult environments.

The objective of this work is automatic design through genetic programming, of the fastest possible locomotion of simulated snake-like robot (Snakebot). The realism of simulation is ensured by employing the Open Dynamics Engine software library. Empirical results demonstrate the emergence of sidewinding as fastest locomotion gait. Robustness of the sidewinding is illustrated by the ease with which Snakebot overcomes various types of obstacles. The ability of Snakebot to adapt to partial damage by gradually improving its velocity characteristics is shown. Discovering compensatory locomotion traits, Snakebot recovers completely from single damage and recovers a major extent of its original velocity when more significant damage is inflicted.

Extending the notion of inheritable genotype in genetic programming (GP) from the common model of DNA into chromatin (DNA and histones), we propose epigenetic programming as an approach, embedding an explicitly controlled gene expression via modification of histones in GP. We propose double cell representation of the simulated individuals, comprising somatic cell and germ cell, both represented by their respective chromatin structures. Following biologically plausible concepts, we regard the plastic phenotype of the somatic cell, achieved via controlled gene expression owing to modifications to histones (epigenetic learning, EL) as relevant for fitness evaluation, while the genotype of the germ cell - to the phylogenesis of the individuals. The approach is verified on evolution of social behavior of team of predator agents in predator-prey pursuit problem. The empirically obtained performance evaluation results indicate that EL contributes to more than 2-fold improvement of computational effort of the phylogenesis via GP. We view the cause for that in the cumulative effect of polyphenism and epigenetic stability. The former allows for phenotypic diversity of genotypically similar individuals, while the latter robustly preserves the individuals from the destructive effects of crossover by silencing of certain genotypic combinations and explicitly activating them only when they are most likely to be expressed in corresponding beneficial phenotypic traits.