Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
This work addresses the problem of designing effective robotic hands and their control for robust grasping, which is crucial for embodied agents in robotics.
This paper introduces a data-driven approach to co-design hand morphology and control for robust grasping of diverse objects. The method uses a novel Bayesian Optimization algorithm with learned latent-space representations to efficiently optimize both aspects, demonstrating its effectiveness in discovering robust and cost-efficient hand morphologies for novel objects.
Evolution in nature illustrates that the creatures' biological structure and their sensorimotor skills adapt to the environmental changes for survival. Likewise, the ability to morph and acquire new skills can facilitate an embodied agent to solve tasks of varying complexities. In this work, we introduce a data-driven approach where effective hand designs naturally emerge for the purpose of grasping diverse objects. Jointly optimizing morphology and control imposes computational challenges since it requires constant evaluation of a black-box function that measures the performance of a combination of embodiment and behavior. We develop a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills jointly through learned latent-space representations. We design the grasping tasks based on a taxonomy of three human grasp types: power grasp, pinch grasp, and lateral grasp. Through experimentation and comparative study, we demonstrate the effectiveness of our approach in discovering robust and cost-efficient hand morphologies for grasping novel objects.