RI: Small: Robot Motion Planning with an Experience Database

RI：小型：使用经验数据库进行机器人运动规划

• 批准号: 1718478
• 负责人: Lydia Kavraki
• 金额: $ 50万
• 依托单位: William Marsh Rice University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-08-15 至 2022-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1718478&HistoricalAwards=false
• 关键词: RI; Small; Robot; Motion; Planning

Motion planning is the problem of determining how to get the robot from one point to another. Ideally, robots should have past experiences, of their own and others, inform future actions to operate more robustly and improve their performance over time. Motion planning, as it is largely practiced today, focuses on solving one problem at a time and makes limited use of past history. The goal of this project is to transform the way robots plan their motions by learning to exploit similarities between different experiences and by creating strategies that can adapt to wide range of scenarios. The work will create a bridge between the motion planning community and the information retrieval community, potentially transforming both fields. Training opportunities for diverse students will be offered. All developed software is disseminated under an open source license and infrastructure will enable other researchers to use the experience databases and contribute to them.This project provides a two-pronged approach to transform motion planning using an experience database. First, hashing will be used on an environment to fetch roadmaps for similar environments from a database. A roadmap is a graph representing feasible motions for a robot. These fetched roadmaps will be then lazily composed and refined to allow the robot to plan efficiently in the current environment. The use of prior experience will be done in tandem with planning from scratch; the latter, if successful, can provide a path and add to the experience database. The second prong in the planned approach will be to maintain various performance characteristics of a library of motion planning algorithms. These characteristics will be then used to optimize algorithm performance and construct a portfolio of algorithms that is competitive across various problems. The overall framework will be implemented in the cloud.

运动计划是确定如何将机器人从一个点到另一个点的问题。理想情况下，机器人应该拥有自己和他人的过去经验，为未来的行动提供了更大努力并随着时间的推移提高其性能。如今，运动计划主要是在实践的，它一次侧重于解决一个问题，并有限使用过去的历史。该项目的目标是通过学习利用不同体验之间的相似性并创建可以适应各种场景的策略来改变机器人计划动作的方式。这项工作将在运动计划社区和信息检索社区之间建立桥梁，并有可能改变这两个领域。将为多元学生提供培训机会。 所有已开发的软件均在开源许可下传播，基础架构将使其他研究人员能够使用体验数据库并为它们做出贡献。该项目提供了一种使用经验数据库进行转换运动计划的两种方便的方法。首先，将在环境中使用哈希来从数据库中获取类似环境的路线图。路线图是代表机器人可行动作的图。然后将这些被提取的路线图懒散地组成并精制，以使机器人在当前环境中有效地计划。先前经验的使用将与从头开始的计划同时完成；后者，如果成功的话，可以提供一条路径并添加到体验数据库中。计划中的第二阶段将是保持运动计划算法库的各种性能特征。然后，这些特征将用于优化算法性能，并构建在各种问题上具有竞争力的算法组合。总体框架将在云中实现。

项目成果

Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search

• DOI: 10.1145/3183713.3196925
• 发表时间: 2018-05
• 期刊: Proceedings of the 2018 International Conference on Management of Data
• 作者: Yiqiu Wang;Anshumali Shrivastava;Jonathan Wang;Junghee Ryu

Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions

使用局部 3D 工作空间分解学习采样分布以进行高维运动规划

• 发表时间: 2022
• 期刊: Proceedings of the International Conference on Robotics and Automation 2021
• 作者: Chamzas, Constantinos;Kingston, Zachary;Quintero-Pena, Carlos;Shrivastava, Anshumali;Kavraki, Lydia E.
• 通讯作者: Kavraki, Lydia E.

MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets

MotionBenchMaker：生成运动规划数据集并对其进行基准测试的工具

• DOI: 10.1109/lra.2021.3133603
• 发表时间: 2022
• 期刊: IEEE Robotics and Automation Letters
• 影响因子: 5.2
• 作者: Chamzas, Constantinos;Quintero-Pena, Carlos;Kingston, Zachary;Orthey, Andreas;Rakita, Daniel;Gleicher, Michael;Toussaint, Marc;Kavraki, Lydia E.
• 通讯作者: Kavraki, Lydia E.

Learning to Retrieve Relevant Experiences for Motion Planning

学习检索运动规划的相关经验

• DOI: 10.1109/icra46639.2022.9812076
• 发表时间: 2022
• 期刊: 2022 International Conference on Robotics and Automation
• 作者: Chamzas, Constantinos;Cullen, Aedan;Shrivastava, Anshumali;Kavraki, Lydia E.
• 通讯作者: Kavraki, Lydia E.

Path Planning for Manipulation Using Experience-Driven Random Trees

• DOI: 10.1109/lra.2021.3063063
• 发表时间: 2021-04-01
• 期刊: IEEE ROBOTICS AND AUTOMATION LETTERS
• 影响因子: 5.2
• 作者: Pairet, Eric;Chamzas, Constantinos;Kavraki, Lydia E.
• 通讯作者: Kavraki, Lydia E.