Juan Cristóbal Zagal

Combining Simulation and Reality in Evolutionary Robotics

Evolutionary Robotics (ER) is a promising methodology, intended for the autonomous development of robots, in which their behaviors are obtained as a consequence of the structural coupling between robot and environment. It is essential that there be a great amount of interaction to generate complex behaviors. Thus, nowadays, it is common to use simulation to speed up the learning process; however simulations are achieved from arbitrary off-line designs, rather than from the result of embodied cognitive processes. According to the reality gap problem, controllers evolved in simulation usually do not allow the same behavior to arise once transferred to the real robot. Some preliminary approaches for combining simulation and reality exist in the ER literature; nonetheless, there is no satisfactory solution available. In this work we discuss recent advances in neuroscience as a motivation for the use of environmentally adapted simulations, which can be achieved through the co-evolution of robot behavior and simulator. We present an algorithm in which only the differences between the behavior fitness obtained in reality versus that obtained in simulations are used as feedback for adapting a simulation. The proposed algorithm is experimentally validated by showing the successful development and continuous transference to reality of two complex low-level behaviors with Sony AIBO1 robots: gait optimization and ball-kicking behavior.

UCHILSIM: a dynamically and visually realistic simulator for the robocup four legged league

UCHILSIM is a robotic simulator specially developed for the RoboCup four-legged league. It reproduces with high accuracy the dynamics of AIBO motions and its interactions with the objects in the game field. Their graphic representations within the game field also possess a high level of detail. The main design goal of the simulator is to become a platform for learning complex robotic behaviors which can be directly transferred to a real robot environment. UCHILSIM is able to adapt its parameters automatically, by comparing robot controller behaviors in reality and in simulations. So far, the effectiveness of UCHILSIM has been tested in some robot learning experiments which we briefly discuss hereinafter. We believe that the use of a highly realistic simulator might speed up the progress in the four legged league by allowing more people to participate in our challenge.

Back to reality: Crossing the reality gap in evolutionary robotics

Abstract In this work a new method to evolutionary robotics is proposed, it combines into asingle framework, learning from reality and simulations. An illusory sub-system is incorporated as an integral part of an autonomous system. The adaptation of the illusory system results from minimizing differences of robot behavior evaluations in reality and in simulations. Behavior guides the illusory adaptation by sampling task-relevant instances of the world. Thus explicit calibration is not required. We remark two attributes of the presented methodology: (i) it is a promising approach for crossing the reality-gap among simulation and reality in evolutionary robotics, and (ii) it allows to generate automatically models and theories of the real robot environment expressed as simulations. We present validation experiments on locomotive behavior acquisition for legged robots.

Spectral sensitivities of photoreceptors and their role in colour discrimination in the green-backed firecrown hummingbird (Sephanoides sephaniodes)

We studied the photopic spectral sensitivity in the green-backed firecrown, Sephanoides sephaniodes, a South American hummingbird, and its possible ecological relationship with preferred flowers and body colouration. Avian colour vision is in general tetrachromatic with at least four types of cones, which vary in sensitivity from the near ultraviolet (UV) to the red wavelength range. Hummingbirds represent an important family of birds, yet little is known about their eye sensitivity, especially about the role of photoreceptors and their oil droplet complements. The photopic electroretinogram shows a main sensitivity peak at 560 nm and a secondary peak in the UV, and may be explained by the presence of four single cones (λmax at ~370, 440, 508 and 560 nm), and a double cone (λmax at 560 nm) screened by oil droplets. The flowers preferred by the firecrown are those in which the red–green wavelength region predominates and have higher contrast than other flowers. The crown plumage of males is highly iridescent in the red wavelength range (peak at 650 nm) and UV; when plotted in a high-dimensional tetrachromatic space, it falls in a “red + UV” purple hue line, suggesting a potential significant communication signal for sexual differentiation.

Evolving Visual Object Recognition for Legged Robots

Recognition of relevant game field objects, such as the ball and landmarks, is usually based upon the application of a set of decision rules over candidate image regions. Rule selection and parameters tuning are often arbitrarily done. We propose a method for evolving the selection of these rules as well as their parameters with basis on real game field images, and a supervised learning approach. The learning approach is implemented using genetic algorithms. Results of the application of our method are presented.

Learning to kick the ball using back to reality

Kicking the ball with high power, short reaction time and accuracy are fundamental requirements for any soccer player. Human players acquire these fine low-level sensory motor coordination abilities trough extended training periods that might last for years. In RoboCup the problem has been addressed by engineering design and acceptable, probably sub-optimal, solutions have been found. To our knowledge the automatic development of these abilities has not been yet employed. Certainly no one is willing to damage a robot during an extended, and probably violent, evolutionary learning process in a real environment. In this work we present an approach for the automatic generation (from scratch) of ball-kick behaviors for legged robots. The approach relies on the use of UCHILSIM, a dynamically accurate simulator, and the Back to Reality paradigm to evolutionary robotics, a recently proposed method for narrowing the difference between simulation and reality during robot behavior execution. After eight hours of simulations successful ball-kick behaviors emerged, being directly transferable to the real robot.

Self-modeling in humanoid soccer robots

In this paper we discuss the applicability, potential benefits, open problems and expected contributions that an emerging set of self-modeling techniques might bring on the development of humanoid soccer robots. The idea is that robots might continuously generate, validate and adjust physical models of their sensorimotor interaction with the world. These models are exploited for adapting behavior in simulation, enhancing the learning skills of a robot with the regular transference of controllers developed in simulation to reality. Moreover, these simulations can be used to aid the execution of complex sensorimotor tasks, speed up adaptation and enhance task planning. We present experiments on the generation of behaviors for humanoid soccer robots using the Back-to-Reality algorithm. General motivations are presented, alternative algorithms are discussed and, most importantly, directions of research are proposed.

Soft Modular Robotic Cubes: Toward Replicating Morphogenetic Movements of the Embryo.

In this paper we present a new type of simple, pneumatically actuated, soft modular robotic system that can reproduce fundamental cell behaviors observed during morphogenesis; the initial shaping stage of the living embryo. The fabrication method uses soft lithography for producing composite elastomeric hollow cubes and permanent magnets as passive docking mechanism. Actuation is achieved by controlling the internal pressurization of cubes with external micro air pumps. Our experiments show how simple soft robotic modules can serve to reproduce to great extend the overall mechanics of collective cell migration, delamination, invagination, involution, epiboly and even simple forms of self-reconfiguration. Instead of relying in complex rigid onboard docking hardware, we exploit the coordinated inflation/deflation of modules as a simple mechanism to detach/attach modules and even rearrange the spatial position of components. Our results suggest new avenues for producing inexpensive, yet functioning, synthetic morphogenetic systems and provide new tangible models of cell behavior.

BeamMaker: an open hardware high-resolution digital fabricator for the masses:

Purpose – The democratization of invention is a long lasting desire for the advancement of society. Having access to education and the means of production appears as the major factors for the implementation of this goal. 3D printing is a revolutionary technology that has the potential to bring digital manufacturing to everyone. However, the rise of personal fabrication requires an increase in printing quality, a reduction on machine cost and an increase in knowledge shared by the open hardware community. The purpose of this paper is to explore the development of a new Open Hardware printer project to address these points. Design/methodology/approach – The authors have designed and constructed a low-cost photopolymer-based 3D printer called BeamMaker. The printer is connected to a host computer and a digital-light-processing projector. This work details the design process and how improvements were implemented to reach good printing quality. The authors provide public access to the instructions, software, s...

How Contests Can Foster the Research Activities on Robotics in Developing Countries: Chile – A Case Study

The aim of this article is to describe our experience in the participation and organization of robot contests, and to show how these actions have increased the activities on robotics in Chile. We describe the annual Latin American IEEE Robotics Competition, we present the IEEE Latin American Robotics Council, we explain our participation in RoboCup, and we present our activities concerning robotic courses for children.