Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds

Nygaard, Tønnes F.; Martín, Charles; Tørresen, Jim; Glette, Kyrre

doi:10.1007/978-3-030-16692-2_41

Cited by 10 publications

(9 citation statements)

References 15 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The robot uses a high-level spline-based gait controller detailed in [56]. It describes a continuous, regular crawl gait where the body moves at a static speed, and only one leg is lifted at a time.…”

Section: Robot Controlmentioning

confidence: 99%

Real-world embodied AI through a morphologically adaptive quadruped robot

et al. 2021

Self Cite

View full text Add to dashboard Cite

Section: Robot Controlmentioning

confidence: 99%

Real-world embodied AI through a morphologically adaptive quadruped robot

et al. 2021

Self Cite

View full text Add to dashboard Cite

“…The robot uses a high-level spline-based gait controller working in Cartesian space (Nygaard et al, 2019a). For generating the foot tip trajectory, a three-dimensional looping cubic Hermite spline is built using five control points.…”

Section: Parameterizable Control and Morphologymentioning

confidence: 99%

Environmental Adaptation of Robot Morphology and Control Through Real-World Evolution

Nygaard

Martín

Howard

et al. 2021

Evolutionary Computation

View full text Add to dashboard Cite

Robots operating in the real world will experience a range of different environments and tasks. It is essential for the robot to have the ability to adapt to its surroundings to work efficiently in changing conditions. Evolutionary robotics aims to solve this by optimizing both the control and body (morphology) of a robot, allowing adaptation to internal, as well as external factors. Most work in this field has been done in physics simulators, which are relatively simple and not able to replicate the richness of interactions found in the real world. Solutions that rely on the complex interplay between control, body, and environment are therefore rarely found. In this paper, we rely solely on real-world evaluations and apply evolutionary search to yield combinations of morphology and control for our mechanically self-reconfiguring quadruped robot. We evolve solutions on two distinct physical surfaces and analyze the results in terms of both control and morphology. We then transition to two previously unseen surfaces to demonstrate the generality of our method. We find that the evolutionary search finds high-performing and diverse morphology-controller configurations by adapting both control and body to the different properties of the physical environments. We additionally find that morphology and control vary with statistical significance between the environments. Moreover, we observe that our method allows for morphology and control parameters to transfer to previously-unseen terrains, demonstrating the generality of our approach.

show abstract

“…The robot uses a high-level spline-based gait controller working in Cartesian space [39]. For generating the foot tip trajectory, a three-dimensional looping cubic Hermite spline is built using five control points.…”

Section: B Parameterizable Control and Morphologymentioning

confidence: 99%

Environmental Adaptation of Robot Morphology and Control through Real-world Evolution

Nygaard¹,

Martín²,

Howard³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Robots operating in the real world will experience a range of different environments and tasks. It is essential for the robot to have the ability to adapt to its surroundings to work efficiently in changing conditions. Evolutionary robotics aims to solve this by optimizing both the control and body (morphology) of a robot, allowing adaptation to internal, as well as external factors. Most work in this field has been done in physics simulators, which are relatively simple and not able to replicate the richness of interactions found in the real world. Solutions that rely on the complex interplay between control, body, and environment are therefore rarely found. In this paper, we rely solely on real-world evaluations and apply evolutionary search to yield combinations of morphology and control for our mechanically self-reconfiguring quadruped robot. We evolve solutions on two very different physical surfaces and analyze the results in terms of both control and morphology. We then transition to two previously unseen surfaces to demonstrate the generality of our method. We find that the evolutionary search adapts both control and body to the different physical environments, yielding significantly different morphology-controller configurations. Moreover, we observe that the solutions found by our method work well on previously unseen terrains.1 although posture may change through control, the actual geometry of the robot is fixed

show abstract

Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds

Cited by 10 publications

References 15 publications

Real-world embodied AI through a morphologically adaptive quadruped robot

Real-world embodied AI through a morphologically adaptive quadruped robot

Environmental Adaptation of Robot Morphology and Control Through Real-World Evolution

Environmental Adaptation of Robot Morphology and Control through Real-world Evolution

Contact Info

Product

Resources

About