Multi-Objective Graph Heuristic Search for Terrestrial Robot Design

Abstract

We present methods for co-designing rigid robots over control and morphology (including discrete topology) over multiple objectives. Previous work has addressed problems in single-objective robot co-design or multi-objective control. However, the joint multi-objective co-design problem is extremely important for generating capable, versatile, algorithmically designed robots. In this work, we present Multi-Objective Graph Heuristic Search, which extends a single-objective graph heuristic search from previous work to enable a highly efficient multi-objective search in a combinatorial design topology space. Core to this approach, we introduce a new universal, multi-objective heuristic function based on graph neural networks that is able to effectively leverage learned information between different task trade-offs. We demonstrate our approach on six combinations of seven terrestrial locomotion and design tasks, including one three-objective example. We compare the captured Pareto fronts across different methods and demonstrate that our multi-objective graph heuristic search quantitatively and qualitatively outperforms other techniques.

arXiv commentIEEE International Conference on Robotics and Automation (ICRA 2021)

References in corpus (4)

• Deep Reinforcement Learning for Multi-objective Optimization
• How to Evaluate Solutions in Pareto-based Search-Based Software Engineering? A Critical Review and Methodological Guidance
• Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
• Neural Graph Evolution: Towards Efficient Automatic Robot Design

Cited by in corpus (2)

• An End-to-End Differentiable Framework for Contact-Aware Robot Design
• Learning Robot Structure and Motion Embeddings using Graph Neural Networks