Task2Morph: Differentiable Task-Inspired Framework for Contact-Aware Robot Design

Optimizing the morphologies and the controllers that adapt to various tasks is a critical issue in the field of robot design, aka. embodied intelligence. Previous works typically model it as a joint optimization problem and use search-based methods to find the optimal solution in the morphology space. However, they ignore the implicit knowledge of task-to-morphology mapping which can directly inspire robot design. For example, flipping heavier boxes tends to require more muscular robot arms. This paper proposes a novel and general differentiable task-inspired framework for contact-aware robot design called Task2Morph. We abstract task features highly related to task performance and use them to build a task-to-morphology mapping. Further, we embed the mapping into a differentiable robot design process, where the gradient information is leveraged for both the mapping learning and the whole optimization. The experiments are conducted on three scenarios, and the results validate that Task2Morph outperforms DiffHand, which lacks a task-inspired morphology module, in terms of efficiency and effectiveness.

Authors

• Yishuai Cai
• Shaowu Yang
• Minglong Li
• Xinglin Chen
• Yunxin Mao
• Xiaodong Yi 0002
• Wenjing Yang 0002

Keywords

• Adaptation models
• Morphology
• Optimization methods
• Aerospace electronics
• Search problems
• Manipulators
• Task analysis
• Design Framework
• Robot Design
• Intelligence
• Robotic Arm
• Task Characteristics
• Joint Optimization
• Issue In The Field
• Gradient Information
• Joint Optimization Problem
• Regression Model
• Deep Learning
• Computer Vision
• Shape Parameter
• Stochastic Gradient Descent
• Object Features
• Control Sequence
• Morphological Parameters
• Box Size
• Fewer Parameters
• Gradient Backpropagation
• Gradient-based Methods
• Final Morphology
• Baseline Algorithms
• Object Task