arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.01080cs.AIcs.LGcs.RO
收藏

基于学习的约束多准则路径规划偏好预测

Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning

Safran Electronics & Defense(赛峰电子与防务公司);LAMSADE, Université Paris-Dauphine(巴黎第九大学LAMSADE实验室);CREC, Ecoles de Saint-Cyr Coëtquidan(圣西尔军校CREC中心)

Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin

摘要:

基于学习的搜索算法在单准则优化问题中越来越受欢迎。相比之下,对于多准则优化,尽管存在许多应用程序,但方法明显较少。自主地面车辆(AGV)的约束路径规划就是这样一种应用,其中AGV通常部署在越野环境中的救灾或搜索和救援应用中。智能体可能面临以下困境:根据一个已知的标准和一个不确定的标准下的操作约束优化的源-目的地路径。已知的标准与路径的成本相关联,表示距离。不确定性标准表示在不需要人为干预的情况下驾驶通过路径的可行性。它取决于各种外部参数,如车辆的物理特性,探索地形或天气条件的状态。在这项工作中,我们利用离线模拟获得的知识,通过训练神经网络模型来预测不确定的标准。我们将此模型集成到一个路径规划器中,可以在线解决问题。最后,我们进行了实验,现实的AGV方案,这表明,所提出的框架需要人为干预的频率较低,交易的路径距离有限的增加。

英文摘要:

Learning-based methods are increasingly popular for search algorithms in single-criterion optimization problems. In contrast, for multiple-criteria optimization there are significantly fewer approaches despite the existence of numerous applications. Constrained path-planning for Autonomous Ground Vehicles (AGV) is one such application, where an AGV is typically deployed in disaster relief or search and rescue applications in off-road environments. The agent can be faced with the following dilemma : optimize a source-destination path according to a known criterion and an uncertain criterion under operational constraints. The known criterion is associated to the cost of the path, representing the distance. The uncertain criterion represents the feasibility of driving through the path without requiring human intervention. It depends on various external parameters such as the physics of the vehicle, the state of the explored terrains or weather conditions. In this work, we leverage knowledge acquired through offline simulations by training a neural network model to predict the uncertain criterion. We integrate this model inside a path-planner which can solve problems online. Finally, we conduct experiments on realistic AGV scenarios which illustrate that the proposed framework requires human intervention less frequently, trading for a limited increase in the path distance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑