Back to reality: Crossing the reality gap in evolutionary robotics

Zagal, Juan Cristóbal; Ruíz-del-Solar, Javier; Vallejos, Paul

doi:10.1016/s1474-6670(17)32084-0

Cited by 53 publications

(53 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We do not assume that any particular gait type will evolve. Therefore, we evolve whole leg co-ordination patterns instead of just evolutionary optimization of known gait parameters, which is the case in some other works (Hornby et al, 2005;Zagal et al, 2004).…”

Section: Related Workmentioning

confidence: 99%

A biologically inspired approach to feasible gait learning for a hexapod robot

Belter¹,

Skrzypczyński²

2010

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

The objective of this paper is to develop feasible gait patterns that could be used to control a real hexapod walking robot. These gaits should enable the fastest movement that is possible with the given robot's mechanics and drives on a flat terrain. Biological inspirations are commonly used in the design of walking robots and their control algorithms. However, legged robots differ significantly from their biological counterparts. Hence we believe that gait patterns should be learned using the robot or its simulation model rather than copied from insect behaviour. However, as we have found tahula rasa learning ineffective in this case due to the large and complicated search space, we adopt a different strategy: in a series of simulations we show how a progressive reduction of the permissible search space for the leg movements leads to the evolution of effective gait patterns. This strategy enables the evolutionary algorithm to discover proper leg co-ordination rules for a hexapod robot, using only simple dependencies between the states of the legs and a simple fitness function. The dependencies used are inspired by typical insect behaviour, although we show that all the introduced rules emerge also naturally in the evolved gait patterns. Finally, the gaits evolved in simulations are shown to be effective in experiments on a real walking robot.

show abstract

Section: Related Workmentioning

confidence: 99%

A biologically inspired approach to feasible gait learning for a hexapod robot

Belter¹,

Skrzypczyński²

2010

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

“…That we did not model the servos in simulation, especially with their frequent failures, suggests that even better results could be obtained via a simulator that contained or learned servo models. In future work we will also incorporate techniques to minimize the gap between the simulator and reality [2,13,26]. previous publications [9,18,25], including an improvement of 52.1% in simulation and 5.1% in reality over the previous best QuadraTot gait by Glette et al These results provide an important demonstration that the HyperNEAT generative encoding can evolve state-of-the-art results for challenging engineering problems, in this case evolving gaits for a legged robot.…”

Section: Resultsmentioning

confidence: 71%

Evolving Gaits for Physical Robots with the HyperNEAT Generative Encoding: The Benefits of Simulation

Lee

Yosinski

Glette

et al. 2013

Applications of Evolutionary Computation

View full text Add to dashboard Cite

Abstract.Creating gaits for physical robots is a longstanding and open challenge. Recently, the HyperNEAT generative encoding was shown to automatically discover a variety of gait regularities, producing fast, coordinated gaits, but only for simulated robots. A follow-up study found that HyperNEAT did not produce impressive gaits when they were evolved directly on a physical robot. A simpler encoding hand-tuned to produce regular gaits was tried on the same robot, and outperformed HyperNEAT, but these gaits were first evolved in simulation before being transferred to the robot. In this paper, we tested the hypothesis that the beneficial properties of HyperNEAT would outperform the simpler encoding if HyperNEAT gaits are first evolved in simulation before being transferred to reality. That hypothesis was confirmed, resulting in the fastest gaits yet observed for this robot, including those produced by nine different algorithms from three previous papers describing gaitgenerating techniques for this robot. This result is important because it confirms that the early promise shown by generative encodings, specifically HyperNEAT, are not limited to simulation, but work on challenging real-world engineering challenges such as evolving gaits for real robots.

show abstract

“…proposed the back-to-reality algorithm [189,188,187], a similar approach that consists in performing an optimization in simulation, transferring some selected solutions to reality and exploiting the corresponding data to improve the simulation before optimizing in simulation again. These different steps are repeated until the behavioral requirements are met.…”

Section: Reality Gapmentioning

confidence: 99%

“…These different steps are repeated until the behavioral requirements are met. The approach has been used for a locomotion task on a quadruped robot [189,188] and on a humanoid robot [187]. Farchy et al propose a similar approach with a choice made by the experimenter on which parameters to focus on for the next optimization [57].…”

Section: Reality Gapmentioning

confidence: 99%

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Doncieux

Mouret

2014

Evol. Intel.

View full text Add to dashboard Cite

Evolutionary robotics is often viewed as the application of a family of black-box optimization algorithms -evolutionary algorithms -to the design of robots, or parts of robots. When considering evolutionary robotics as black-box optimization, the selective pressure is mainly driven by a user-defined, black-box fitness function, and a domain-independent selection procedure. However, most evolutionary robotics experiments face similar challenges in similar setups: the selective pressure, and, in particular, the fitness function, is not a pure user-defined black box. The present review shows that, because evolutionary robotics experiments share common features, selective pressures for evolutionary robotics are a subject of research on their own. The literature has been split into two categories: goal refiners, aimed at changing the definition of a good solution, and process helpers, designed to help the search process. Two subcategories are further considered: task-specific approaches, which require knowledge on how to solve the task and taskagnostic ones, which do not need it. Besides highlighting the diversity of the approaches and their respective goals, the present review shows that many task-agnostic process helpers have been proposed during the last years, thus bringing us closer to the goal of a fully automated robot behavior design process.

show abstract

Back to reality: Crossing the reality gap in evolutionary robotics

Cited by 53 publications

References 3 publications

A biologically inspired approach to feasible gait learning for a hexapod robot

A biologically inspired approach to feasible gait learning for a hexapod robot

Evolving Gaits for Physical Robots with the HyperNEAT Generative Encoding: The Benefits of Simulation

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Contact Info

Product

Resources

About