116 citations · 139 across the 15 of their papers we have counts for
7 papers · 1 filter
Morphological Cognition: Classifying MNIST Digits Through Morphological Computation Alone
Alican Mertan, Nick Cheney
With the rise of modern deep learning, neural networks have become an essential part of virtually every artificial intelligence system, making it difficult even to imagine differen…
Evolutionary Brain-Body Co-Optimization Consistently Fails to Select for Morphological Potential
Alican Mertan, Nick Cheney
Brain-body co-optimization remains a challenging problem. To understand and overcome its challenges, we exhaustively map a morphology-fitness landscape: we train controllers for ea…
Controller Distillation Reduces Fragile Brain-Body Co-Adaptation and Enables Migrations in MAP-Elites
Alican Mertan, Nick Cheney
Brain-body co-optimization suffers from fragile co-adaptation where brains become over-specialized for particular bodies, hindering their ability to transfer well to others. Evolut…
No-brainer: Morphological Computation driven Adaptive Behavior in Soft Robots
Alican Mertan, Nick Cheney
It is prevalent in contemporary AI and robotics to separately postulate a brain modeled by neural networks and employ it to learn intelligent and adaptive behavior. While this meth…
Towards Multi-Morphology Controllers with Diversity and Knowledge Distillation
Alican Mertan, Nick Cheney
Finding controllers that perform well across multiple morphologies is an important milestone for large-scale robotics, in line with recent advances via foundation models in other a…
Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots
Alican Mertan, Nick Cheney
Evolving virtual creatures is a field with a rich history and recently it has been getting more attention, especially in the soft robotics domain. The compliance of soft materials…
Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots
Alican Mertan, Nick Cheney
Soft robotics is a rapidly growing area of robotics research that would benefit greatly from design automation, given the challenges of manually engineering complex, compliant, and…