Evolving soft locomotion in aquatic and terrestrial environments: effects of material properties and environmental transitions (1711.06605v1)

Abstract: Designing soft robots poses considerable challenges: automated design approaches may be particularly appealing in this field, as they promise to optimize complex multi-material machines with very little or no human intervention. Evolutionary soft robotics is concerned with the application of optimization algorithms inspired by natural evolution in order to let soft robots (both morphologies and controllers) spontaneously evolve within physically-realistic simulated environments, figuring out how to satisfy a set of objectives defined by human designers. In this paper a powerful evolutionary system is put in place in order to perform a broad investigation on the free-form evolution of walking and swimming soft robots in different environments. Three sets of experiments are reported, tackling different aspects of the evolution of soft locomotion. The first two sets explore the effects of different material properties on the evolution of terrestrial and aquatic soft locomotion: particularly, we show how different materials lead to the evolution of different morphologies, behaviors, and energy-performance tradeoffs. It is found that within our simplified physics world stiffer robots evolve more sophisticated and effective gaits and morphologies on land, while softer ones tend to perform better in water. The third set of experiments starts investigating the effect and potential benefits of major environmental transitions (land - water) during evolution. Results provide interesting morphological exaptation phenomena, and point out a potential asymmetry between land-water and water-land transitions: while the first type of transition appears to be detrimental, the second one seems to have some beneficial effects.

• The paper demonstrates that material stiffness critically influences locomotion, with stiffer materials benefiting land gaits and softer ones improving aquatic swimming.
• It employs a CPPN-based evolutionary algorithm with VoxCAD and fluid dynamics simulations to evolve both morphology and control in soft robots.
• The study reveals that environmental transitions impact evolutionary paths, with water-to-land changes fostering enhanced terrestrial adaptations.

Evolving Soft Locomotion in Aquatic and Terrestrial Environments

The paper "Evolving soft locomotion in aquatic and terrestrial environments: effects of material properties and environmental transitions" investigates the evolutionary processes of soft robots through automated design approaches, particularly in different environmental settings. The primary focus is on understanding how varying material properties influence the evolution of soft robots in both terrestrial and aquatic environments and the potential effects of transitioning between these environments on the morphological and behavioral evolution of these robots.

The paper employs an advanced evolutionary system, utilizing the VoxCAD simulator augmented with a fluid dynamics model to simulate both terrestrial and aquatic conditions. This setup incorporates Compositional Pattern Producing Networks (CPPNs) for genetic representation, which encode spatially distributed phenotypic traits to evolve both morphology and control of soft robots through a multi-objective evolutionary algorithm.

Key Experimental Insights

1. Material Stiffness and Locomotion Performance:

Experiments exhibited distinct trends based on the stiffness of materials the robots were composed of: - Terrestrial Locomotion: Stiffer materials (increasing modulus from 0.001 MPa to 10 MPa) resulted in more efficient and complex morphologies and behaviors. The robots evolved with stiff materials achieved sophisticated walking gaits, demonstrating a correlation between stiffness and effective terrestrial locomotion. - Aquatic Locomotion: Conversely, softer materials thrived in aquatic environments, facilitating better locomotion than their stiffer counterparts. However, a mid-level stiffness offered superior energy-performance tradeoffs, aligning with biological observations where flexibility enhances swimming efficiency.

1. Environmental Transitions:

The paper probed the evolutionary impacts of environmental transitions—land to water and water to land: - Transitioning from land to water proved detrimental to swimming evolution, suggesting a difficulty in adapting land-evolved structures for effective swimming. - The reverse transition, water to land, showed potential benefits, yielding more elaborate terrestrial solutions and superior energy-performance tradeoffs.

1. Morphological Complexity: Irrespective of the environment, an increase in the morphological complexity was observed over evolutionary time. The CPPN-based encoding inherently biases towards regular, symmetric structures, although more complex, asymmetric forms evolved as well.

Implications and Future Directions

The paper's findings contribute significantly to the field of evolutionary robotics, particularly in understanding adaptive morphology and behavior across diverse environments. The observed dependency between material stiffness and locomotion efficiency has critical implications for the design of soft robots, suggesting that material properties should be strategically tailored to match the intended environment.

From a theoretical standpoint, the paper enriches our understanding of morphological computation and the role of material properties in evolution. Practically, these insights could inform the design of soft robots capable of operating efficiently in variable environments, such as those encountered in real-world applications involving complex terrain and aquatic exploration.

The research opens several avenues for further exploration. A notable extension includes refining the environmental transitions to test gradual adaptation techniques and expanding the experimental scope to evolve material stiffness adaptively. Additionally, the simulation models could be enhanced to include more complex fluid dynamics to better replicate real-world conditions. Integrating more robust evolutionary algorithms may also improve the consistency and efficacy of evolution, potentially leading to more statistically significant outcomes across various conditions. This aligns with evolving trends in bio-inspired robotics where integration of morphological intelligence with adaptable material properties is increasingly seen as a pathway for creating truly autonomous and versatile robotic systems.