用混合高斯过程流提升机器人策略的多模与间断建模能力
Composite Gaussian Processes Flows for Learning Discontinuous Multimodal Policies
- 将重叠高斯过程与连续归一化流结合，构建可处理多模态和局部不连续的策略模型
- 仿真与真实任务中成功率显著优于基线方法，卡方检验显示差异显著
- 适合需要高效、灵活控制策略的复杂机器人任务，如灵巧操作与路径规划
学习真实世界机器人任务的控制策略常面临多模态、局部不连续及计算效率要求高的挑战。这些挑战源于机器人环境的复杂性，其中可能并存多种解决方案。为此，我们提出复合高斯过程流（CGP-Flows），一种新型半参数机器人策略模型。该模型结合重叠高斯过程混合（OMGPs）与连续归一化流（CNFs），可有效建模复杂策略，解决多模态与局部不连续问题。该混合方法在保留OMGPs计算效率的同时，引入了CNFs的灵活性。在模拟与真实机器人任务中的实验表明，CGP-Flows在建模控制策略方面性能显著提升。仿真任务中，CGP-Flows的成功率高于基线方法，且其成功率与其它基线在卡方检验中存在显著差异。
原文摘要 · Abstract (English)
Learning control policies for real-world robotic tasks often involve challenges such as multimodality, local discontinuities, and the need for computational efficiency. These challenges arise from the complexity of robotic environments, where multiple solutions may coexist. To address these issues, we propose Composite Gaussian Processes Flows (CGP-Flows), a novel semi-parametric model for robotic policy. CGP-Flows integrate Overlapping Mixtures of Gaussian Processes (OMGPs) with the Continuous Normalizing Flows (CNFs), enabling them to model complex policies addressing multimodality and local discontinuities. This hybrid approach retains the computational efficiency of OMGPs while incorporating the flexibility of CNFs. Experiments conducted in both simulated and real-world robotic tasks demonstrate that CGP-flows significantly improve performance in modeling control policies. In a simulation task, we confirmed that CGP-Flows had a higher success rate compared to the baseline method, and the success rate of GCP-Flow was significantly different from the success rate of other baselines in chi-square tests.
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。