Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
arXiv:2012.12209
Abstract
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.
arXiv comment8 pages, 5 figures, Project website: https://xinleipan.github.io/emergent_morphology/
References in corpus (10)
- A Tutorial on Bayesian Optimization
- Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
- UniGrasp: Learning a Unified Model to Grasp with Multifingered Robotic Hands
- Learning a visuomotor controller for real world robotic grasping using simulated depth images
- Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
- Constrained Bayesian Optimization for Automatic Chemical Design
- Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration
- Neural Graph Evolution: Towards Efficient Automatic Robot Design
- Hardware Conditioned Policies for Multi-Robot Transfer Learning
- Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning