用经典控制方法替代强化学习，实现无需训练的障碍避让。
Avoidance of an unexpected obstacle without reinforcement learning: Why not using advanced control-theoretic tools?
- 用平坦性控制结合HEOL反馈替代强化学习
- 模型基于与模型无关的预测控制，效果接近且更鲁棒
- 计算量低，适合实时应用
本文针对意外障碍物避让问题，回应了对强化学习（RL）的批评——其需大量试错才能完成新任务。采用经典的杜宾斯小车模型，以基于平坦性的控制方法结合HEOL反馈机制，以及最新的无模型预测控制方法，替代传统强化学习。计算机仿真结果表明，两种方法均表现良好，基于模型的方法略优，但无模型方法在面对随机参数失配和扰动时表现出极强鲁棒性，远超当前主流机器学习技术所能达到的水平。此外，两种方法均具有极低的计算开销，适用于实时系统。
原文摘要 · Abstract (English)
This communication on collision avoidance with unexpected obstacles is motivated by some critical appraisals on reinforcement learning (RL) which "requires ridiculously large numbers of trials to learn any new task" (Yann LeCun). We use the classic Dubins' car in order to replace RL with flatness-based control, combined with the HEOL feedback setting, and the latest model-free predictive control approach. The two approaches lead to convincing computer experiments where the results with the model-based one are only slightly better. They exhibit a satisfactory robustness with respect to randomly generated mismatches/disturbances, which become excellent in the model-free case. Those properties would have been perhaps difficult to obtain with today's popular machine learning techniques in AI. Finally, we should emphasize that our two methods require a low computational burden.
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。