研究发现进化算法难选最佳机器人形态，因常误判新形态潜力。
Evolutionary Brain-Body Co-Optimization Consistently Fails to Select for Morphological Potential
- 遍历130万种软体机器人形态，构建完整性能地图
- 算法常卡在近优解，因低估新形态个体而丢弃潜力方案
- 形态与控制协同优化可实现单形态无法达到的适应性
脑-体协同优化仍是难题。为深入理解并克服其挑战，我们系统绘制了形态-适应度景观：在包含1,305,840个基于体素的软体机器人设计中，为每种形态训练控制器。该设计空间能有效建模脑-体协同优化问题，且我们的映射大致捕捉了其景观特征。完备的景观知识使我们得以分析进化协同优化算法的演化过程。结果表明，所测试算法无法稳定找到近优解：搜索过程中，有时会陷入仅差一次突变即可改进的形态，因其频繁低估新突变体，导致有前景的形态被错误淘汰。另一方面，形态与控制协同优化能产生有效的目标切换能力，生成的形态-控制器组合性能远超固定形态下单独优化控制器的表现。这些结果验证了文献中的趋势，并为未来研究提供重要启示。
原文摘要 · Abstract (English)
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 each morphology in a design space of 1,305,840 voxel-based soft robots. We show that this design space constitutes a good model for studying brain-body co-optimization and that our mapping roughly captures its landscape. Complete knowledge of the landscape lets us analyze how evolutionary co-optimization algorithms unfold. We find that the tested algorithms cannot consistently find near-optimal solutions: the search, at times, gets stuck on morphologies one mutation away from better ones, because it regularly undervalues individuals with newly mutated bodies and eliminates promising morphologies. On the other hand, co-optimizing morphology and control creates useful goal-switching, yielding morphology-controller pairs whose performance cannot be reached by optimizing the controller alone for a fixed morphology. Together, these results ground trends in the literature and offer insights for future work.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。