用学习+搜索提升机器人在杂乱环境中的高效物体重排能力
Efficiently Manipulating Clutter via Learning and Search-Based Reasoning
- 用深度网络预测推动物体的交互，提高动作准确性
- 结合蒙特卡洛树搜索实现复杂场景下100%完成的非抓取重排
- 并行化模拟加速规划，适合高效率机器人系统部署
本论文提出新算法以推进机器人物体重排任务，该任务在仓储自动化与家庭服务等自主系统中至关重要。针对高维规划、复杂物体交互及计算压力等挑战，研究融合深度学习进行交互预测、树搜索生成动作序列，并采用并行计算提升效率。核心贡献包括：用于精准推动物体运动预测的深度交互预测网络（DIPN），准确率达90%以上；与蒙特卡洛树搜索（MCTS）协同，实现特定复杂场景下100%完成的非抓取物体获取；以及支持批处理模拟的并行MCTS框架（PMBS），在保持或提升解质量的同时显著加速规划。研究还探索多种操作原语的组合，并通过仿真与真实实验充分验证。
原文摘要 · Abstract (English)
This thesis presents novel algorithms to advance robotic object rearrangement, a critical task for autonomous systems in applications like warehouse automation and household assistance. Addressing challenges of high-dimensional planning, complex object interactions, and computational demands, our work integrates deep learning for interaction prediction, tree search for action sequencing, and parallelized computation for efficiency. Key contributions include the Deep Interaction Prediction Network (DIPN) for accurate push motion forecasting (over 90% accuracy), its synergistic integration with Monte Carlo Tree Search (MCTS) for effective non-prehensile object retrieval (100% completion in specific challenging scenarios), and the Parallel MCTS with Batched Simulations (PMBS) framework, which achieves substantial planning speed-up while maintaining or improving solution quality. The research further explores combining diverse manipulation primitives, validated extensively through simulated and real-world experiments.
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。