Co-Evolution of Sensor Morphology and Control on a Simulated Legged Robot

Parker, G.B.; Nathan, P.J.

doi:10.1109/cira.2007.382874

Cited by 7 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A wide variety of controller designs for that purpose can be found in the literature. Parker and Nathan [14] as well as Bugajska and Schutz [4] implemented a controller as a reactive system which uses "if...then" rules to control a simulated robot. Haller, Ijspeert and Floreano [10] implemented a controller inspired by the central pattern generators underlying locomotion in animals.…”

Section: Adaptive Wing Controllermentioning

confidence: 99%

Growth in co-evolution of sensory system and signal processing for optimal wing control

Smalikho

Olhofer

2014

Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

The development of adaptive systems, which react autonomously to changes in their environment, require the coordinated generation of sensors, providing information about the environment and signal processing structures, which generate suitable reactions to changed conditions. In this work we demonstrate the applicability of a concurrent evolutionary design of the optimal sensory and controller parts of a system for the example of an adaptive wing design. The focus of the work is twofold. First on the realization of developmental stages of the sensory and controlling systems design, defined as a growth process, and second on the comparison of the differences in structures of the systems developed through the presented evolutionary growth method and of evolved systems, having fixed set of sensory elements. We ascertained that the success of the realized growth process depends among others on the relation between the triggering methods and timing of the system enlargement and on parameter settings of the optimization strategy after a growth phase.

show abstract

Section: Adaptive Wing Controllermentioning

confidence: 99%

Growth in co-evolution of sensory system and signal processing for optimal wing control

Smalikho

Olhofer

2014

Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Other than in [55,79], a 3-D arena was always necessary for simulation. In a unique approach to building simulation platforms, [63] and [98] modelled them by converting the behaviour of a robot in reality to a virtual environment. The only online driven evaluation process was reported in [72].…”

Section: Simulators and The Reality Gapmentioning

confidence: 99%

“…Parker et al [98] designed a reactive controller where a GA selected the rules for the sensor system to act. Simple inverse kinematic control evolved by an EA [47], Constraint Compliant Control (CCC) law which relied on velocity kinematic principles [81] and a simple periodic open loop control [70,86]…”

Section: Algorithms In Controllermentioning

confidence: 99%

A survey on evolutionary-aided design in robotics

Prabhu¹,

Seals²,

Kyberd³

et al. 2018

Robotica

View full text Add to dashboard Cite

SUMMARYThe evolutionary-aided design process is a method to find solutions to design and optimisation problems. Evolutionary algorithms (EAs) are applied to search for optimal solutions from a solution space that evolves over several generations. EAs have found applications in many areas of robotics. This paper covers the efforts to determine body morphology of robots through evolution and body morphology with the controller of robots or similar creatures through co-evolution. The works are reviewed from the perspective of how different algorithms are applied and includes a brief explanation of how they are implemented.

show abstract

“…the type of the sensed physical phenomenon, such as visual (light) [20 -27,32,33,35-46], somatosensory (touch and perception) [47,48,49,[50][51][52][53][54][55][56][58][59][60][61][62][63][64][65][66][67][68], auditory (hearing) [71,72] and even electric [73][74][75][76][77] or magnetic field [78,79]. Some researchers also investigated sensor morphology of multimodal systems, where a combination of multiple sensors is used, each sensing a different physical phenomenon [80][81][82][83][84].…”

Section: The Research Landscapementioning

confidence: 99%

Adaptation of sensor morphology: an integrative view of perception from biologically inspired robotics perspective

Iida

Nurzaman

2016

Interface Focus.

View full text Add to dashboard Cite

Sensor morphology, the morphology of a sensing mechanism which plays a role of shaping the desired response from physical stimuli from surroundings to generate signals usable as sensory information, is one of the key common aspects of sensing processes. This paper presents a structured review of researches on bioinspired sensor morphology implemented in robotic systems, and discusses the fundamental design principles. Based on literature review, we propose two key arguments: first, owing to its synthetic nature, biologically inspired robotics approach is a unique and powerful methodology to understand the role of sensor morphology and how it can evolve and adapt to its task and environment. Second, a consideration of an integrative view of perception by looking into multidisciplinary and overarching mechanisms of sensor morphology adaptation across biology and engineering enables us to extract relevant design principles that are important to extend our understanding of the unfinished concepts in sensing and perception.

show abstract

Co-Evolution of Sensor Morphology and Control on a Simulated Legged Robot

Cited by 7 publications

References 8 publications

Growth in co-evolution of sensory system and signal processing for optimal wing control

Growth in co-evolution of sensory system and signal processing for optimal wing control

A survey on evolutionary-aided design in robotics

Adaptation of sensor morphology: an integrative view of perception from biologically inspired robotics perspective

Contact Info

Product

Resources

About