Evolving Reactive Controller for a Modular Robot: Benefits of the Property of State-Switching in Fractal Gene Regulatory Networks

Zahadat, Payam; Schmickl, Thomas

doi:10.1007/978-3-642-33093-3_21

Cited by 4 publications

(3 citation statements)

References 13 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, only open-ended, uninformed evolutionary computation will allow for generality in problem solving as required in long-term autonomous operations in unpredictable environments. For example, many studies in the literature that have evolved complex tasks of cooperation and coordination in robots used pre-structured software controllers [6,10], while many studies that have evolved robotic controllers in an uninformed open-ended way produced only simple behaviors, such as coupled oscillators that generate gaits in robots [11][12][13][14] including simple reactive gaits [15], homing, collision avoidance, area coverage, collective pushing/pulling, and similar straight-forward tasks [16].…”

Section: Introductionmentioning

confidence: 99%

Wankelmut: A Simple Benchmark for the Evolvability of Behavioral Complexity

2021

Self Cite

View full text Add to dashboard Cite

In evolutionary robotics, an encoding of the control software that maps sensor data (input) to motor control values (output) is shaped by stochastic optimization methods to complete a predefined task. This approach is assumed to be beneficial compared to standard methods of controller design in those cases where no a priori model is available that could help to optimize performance. For robots that have to operate in unpredictable environments as well, an evolutionary robotics approach is favorable. We present here a simple-to-implement, but hard-to-pass benchmark to allow for quantifying the “evolvability” of such evolving robot control software towards increasing behavioral complexity. We demonstrate that such a model-free approach is not a free lunch, as already simple tasks can be unsolvable barriers for fully open-ended uninformed evolutionary computation techniques. We propose the “Wankelmut” task as an objective for an evolutionary approach that starts from scratch without pre-shaped controller software or any other informed approach that would force the behavior to be evolved in a desired way. Our main claim is that “Wankelmut” represents the simplest set of problems that makes plain-vanilla evolutionary computation fail. We demonstrate this by a series of simple standard evolutionary approaches using different fitness functions and standard artificial neural networks, as well as continuous-time recurrent neural networks. All our tested approaches failed. From our observations, we conclude that other evolutionary approaches will also fail if they do not per se favor or enforce the modularity of the evolved structures and if they do not freeze or protect already evolved functionalities from being destroyed again in the later evolutionary process. However, such a protection would require a priori knowledge of the solution of the task and contradict the “no a priori model” approach that is often claimed in evolutionary computation. Thus, we propose a hard-to-pass benchmark in order to make a strong statement for self-complexifying and generative approaches in evolutionary computation in general and in evolutionary robotics specifically. We anticipate that defining such a benchmark by seeking the simplest task that causes the evolutionary process to fail can be a valuable benchmark for promoting future development in the fields of artificial intelligence, evolutionary robotics, and artificial life.

show abstract

Section: Introductionmentioning

confidence: 99%

Wankelmut: A Simple Benchmark for the Evolvability of Behavioral Complexity

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, only open-ended, uninformed evolutionary computation will allow for generality in problem solving as required in long-term autonomous operations in unpredictable environments. For example, most studies in literature that have evolved complex tasks of cooperation and coordination in robots used pre-structured software controllers [6,7] while most studies that have evolved robotic controllers in an uninformed open-ended way produced only simple behaviors, such as coupled oscillators that generate gaits in robots [8,9,10,11] including simple reactive gaits [12], homing, collision avoidance, area coverage, collective pushing/pulling, and similar straight-forward tasks [13].…”

Section: Introductionmentioning

confidence: 99%

Sooner than Expected: Hitting the Wall of Complexity in Evolution

Schmickl¹,

Zahadat²,

Hamann³

2016

Preprint

Self Cite

View full text Add to dashboard Cite

In evolutionary robotics an encoding of the control software, which maps sensor data (input) to motor control values (output), is shaped by stochastic optimization methods to complete a predefined task. This approach is assumed to be beneficial compared to standard methods of controller design in those cases where no a-priori model is available that could help to optimize performance. Also for robots that have to operate in unpredictable environments, an evolutionary robotics approach is favorable. We demonstrate here that such a model-free approach is not a free lunch, as already simple tasks can represent unsolvable barriers for fully open-ended uninformed evolutionary computation techniques. We propose here the "Wankelmut" task as an objective for an evolutionary approach that starts from scratch without pre-shaped controller software or any other informed approach that would force the behavior to be evolved in a desired way. Our focal claim is that "Wankelmut" represents the simplest set of problems that makes plain-vanilla evolutionary computation fail. We demonstrate this by a series of simple standard evolutionary approaches using different fitness functions and standard artificial neural networks as well as continuous-time recurrent neural networks. All our tested approaches failed. We claim that any other evolutionary approach will also fail that does per-se not favor or enforce modularity and does not freeze or protect already evolved functionalities. Thus we propose a hard-to-pass benchmark and make a strong statement for self-complexifying and generative approaches in evolutionary computation. We anticipate that defining such a "simplest task to fail" is a valuable benchmark for promoting future development in the field of artificial intelligence, evolutionary robotics and artificial life.

show abstract

“…Pouya et al [56] used particle swarm optimization to optimize CPG-based gaits for Roombot robots that both contained rotating and oscillating actuators. Evolutionary algorithms have also been used to optimize reactive locomotion controllers based on HyperNEAT [57], chemical hormones models [58] and fractal genetic regulatory network [59]. For co-evolution of morphology and control, Brunete et al [60] represented the morphology of a heterogeneous snake-like microrobot directly in the chromosome, Faíña et al [61] represented a legged robot morphology as a tree, and Bongard and Pfeifer [62] evolved a genetic regulatory that would direct the growth of the robot instead of a direct representation.…”

Section: Adaptive Self-reconfigurable Modular Robotsmentioning

confidence: 99%