About this Research Topic
Morphological adaptation is a key challenge for Evolutionary Robotics (ER). Consideration of a robot’s physical form, as well as its control system, holds particular promise for imbuing robotic systems with task and environmental adaptability. The additional degrees of behavioural freedom that can be unlocked when morphology is considered in the evolutionary process allows access to a wide design space, providing a pathway towards resilient, rugged, and adaptable robots that can cope with unforeseen circumstances and be realistically deployed in real-world scenarios, with corresponding real-world impacts.
Morphology evolution allows us to create and study systems based on the principles of embodied cognition, whereby coupling (evolved) controllers to (evolved) physical substrates in a meaningful environment allows for rich behaviours that emerge from interactions between the three. Embodied cognition provides a route towards improving the complexity and adaptivity of evolved behaviours, leading to a corresponding increase in the applicability of evolutionary robotics systems to challenging scenarios.
Systems that can fully exploit the principles of embodied cognition and automatically evolve environment-adapted and task-specific robots is an ambitious and challenging endeavour. To date, evolutionary robotics research is largely conducted on morphologically static robots, mainly due to difficulties in either developing encodings that can effectively navigate the expanded search space of morphology-plus-controller, and/or constructing and assessing morphologically adaptable robotic hardware.
A recent trend has seen implementations of morphological evolutionary robotics for challenging design domains, which has been shown to be effective in designing robots that are, for example, multi-material, soft, or physically-embodied. Emerging technologies offer the opportunity to push the boundaries of possibility for morphology evolution, and numerous recent examples from the literature harness principles including multi-material 3D printing, differentiable simulation, and representation learning to create promising evolutionary robotics systems, accompanied by the development of frameworks that allow researchers to operate in this rapidly-developing scientific field.
This Research Topic calls for contributions that illustrate and discuss innovative methods, technologies, software, and philosophical viewpoints that advance the field of evolving robotic morphologies. Studies on the evolution of unconventional ‘robots’, including living cells, as well as robot-assisted evolutionary experimentation are also in scope. Subject areas include but are not limited to:
• Design and control for adaptable robotics
• Representations for robotic systems (biology, evolvability, representation learning)
• Co-evolution, coupled body-brain learning
• Differentiable simulation
• Unconventional ‘robots’ – cellular, chemical, etc.
• Robot-assisted evolutionary experimentation
• Studies in embodiment (programmed body-brain-environment interactions)
• Tools for design space exploration
• Methods for rapid evolution (few-shot learning, surrogate modelling, differentiable simulation, design space
compression, sim2real and reality gap).
• Demonstration of hardware morphological evolution, including whole robots and robotic subsystems and
components
• Reasonable expectations for evolved robotic systems
To summarise, this research topic focuses on advancing the state of the art in morphology evolution in evolutionary robotics, leading to a future where robots with evolved morphology embody high-performance in-environment behaviours across a range of challenging deployment scenarios.
Any manuscripts that are based on conference papers should be extended to be considered original work. As a rule of thumb, at least 30% of content should be original. If the authors do not own the copyright to their paper, they should also seek permission from the copyright holder. Please see our policies and publication ethics (section 3.4) for more information.
Morphology evolution allows us to create and study systems based on the principles of embodied cognition, whereby coupling (evolved) controllers to (evolved) physical substrates in a meaningful environment allows for rich behaviours that emerge from interactions between the three. Embodied cognition provides a route towards improving the complexity and adaptivity of evolved behaviours, leading to a corresponding increase in the applicability of evolutionary robotics systems to challenging scenarios.
Systems that can fully exploit the principles of embodied cognition and automatically evolve environment-adapted and task-specific robots is an ambitious and challenging endeavour. To date, evolutionary robotics research is largely conducted on morphologically static robots, mainly due to difficulties in either developing encodings that can effectively navigate the expanded search space of morphology-plus-controller, and/or constructing and assessing morphologically adaptable robotic hardware.
A recent trend has seen implementations of morphological evolutionary robotics for challenging design domains, which has been shown to be effective in designing robots that are, for example, multi-material, soft, or physically-embodied. Emerging technologies offer the opportunity to push the boundaries of possibility for morphology evolution, and numerous recent examples from the literature harness principles including multi-material 3D printing, differentiable simulation, and representation learning to create promising evolutionary robotics systems, accompanied by the development of frameworks that allow researchers to operate in this rapidly-developing scientific field.
This Research Topic calls for contributions that illustrate and discuss innovative methods, technologies, software, and philosophical viewpoints that advance the field of evolving robotic morphologies. Studies on the evolution of unconventional ‘robots’, including living cells, as well as robot-assisted evolutionary experimentation are also in scope. Subject areas include but are not limited to:
• Design and control for adaptable robotics
• Representations for robotic systems (biology, evolvability, representation learning)
• Co-evolution, coupled body-brain learning
• Differentiable simulation
• Unconventional ‘robots’ – cellular, chemical, etc.
• Robot-assisted evolutionary experimentation
• Studies in embodiment (programmed body-brain-environment interactions)
• Tools for design space exploration
• Methods for rapid evolution (few-shot learning, surrogate modelling, differentiable simulation, design space
compression, sim2real and reality gap).
• Demonstration of hardware morphological evolution, including whole robots and robotic subsystems and
components
• Reasonable expectations for evolved robotic systems
To summarise, this research topic focuses on advancing the state of the art in morphology evolution in evolutionary robotics, leading to a future where robots with evolved morphology embody high-performance in-environment behaviours across a range of challenging deployment scenarios.
Any manuscripts that are based on conference papers should be extended to be considered original work. As a rule of thumb, at least 30% of content should be original. If the authors do not own the copyright to their paper, they should also seek permission from the copyright holder. Please see our policies and publication ethics (section 3.4) for more information.
Keywords: Embodied Cognition, Morphology, Robot Design, Robot-assisted Evolution, Bio-machines
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
