Robustness of different pattern recognition methods is one of the key challenges in autonomous driving, especially when driving in the high variety of road environments and weather conditions, such as gravel roads and snowfall. Although one can collect data from these adverse conditions using cars equipped with sensors, it is quite tedious to annotate the data for training. In this work, we address this limitation and propose a CNN-based method that can leverage the steering wheel angle information to improve the road area semantic segmentation. As the steering wheel angle data can be easily acquired with the associated images, one could improve the accuracy of road area semantic segmentation by collecting data in new road environments without manual data annotation. We demonstrate the effectiveness of the proposed approach on two challenging data sets for autonomous driving and show that when the steering task is used in our segmentation model training, it leads to a 0.1-2.9% gain in the road area mIoU (mean Intersection over Union) compared to the corresponding reference transfer learning model.
translated by 谷歌翻译
This work considers the path planning problem for a team of identical robots evolving in a known environment. The robots should satisfy a global specification given as a Linear Temporal Logic (LTL) formula over a set of regions of interest. The proposed method exploits the advantages of Petri net models for the team of robots and B\"uchi automata modeling the specification. The approach in this paper consists in combining the two models into one, denoted Composed Petri net and use it to find a sequence of action movements for the mobile robots, providing collision free trajectories to fulfill the specification. The solution results from a set of Mixed Integer Linear Programming (MILP) problems. The main advantage of the proposed solution is the completeness of the algorithm, meaning that a solution is found when exists, this representing the key difference with our previous work in [1]. The simulations illustrate comparison results between current and previous approaches, focusing on the computational complexity.
translated by 谷歌翻译
在动态和远程环境中,对自主系统的高级自治和鲁棒性的需求促使开发人员提出了新的软件体系结构。一种常见的架构样式是将机器人系统的功能总结为基本动作(称为技能)的功能,在该动作上,在该动作中实施了技能管理层以结构,测试和控制功能层。但是,当前可用的验证工具仅在不复制系统实际执行的模型上提供特定于任务的验证或验证,这使得难以确保其对意外事件的鲁棒性。为此,已经开发出一种工具,即Skinet,以将系统的基于技能的架构转换为Petri网络,以建模技能和资源的状态机器行为。 Petri NET允许使用模型检查,例如线性时间逻辑(LTL)或计算树逻辑(CTL),以供用户分析和验证系统的模型。
translated by 谷歌翻译
可靠的剩余时间预测正在进行的业务流程是一个高度相关的主题。一个例子是订单交付,这是一个关键的竞争因素,例如零售是因为它是客户满意度的主要驱动力。为了及时实现及时的交付,对交付过程剩余时间的准确预测至关重要。在过程挖掘领域内,已经提出了各种各样的剩余时间预测技术。在这项工作中,我们基于随机培养皿网的剩余时间预测,该预测通常分布在k-nearthiend邻居中。 k-nearest邻居算法是在存储过去的时间以完成先前活动的时间的简单矢量上执行的。通过仅采用一部分实例,获得了更具代表性和稳定的随机培养皿网,从而导致更准确的时间预测。我们讨论了该技术及其在Python中的基本实现,并使用不同的现实世界数据集来评估我们扩展的预测能力。这些实验在结合有关预测能力方面的两种技术方面都具有明显的优势。
translated by 谷歌翻译
最近引入了Petri网络的形式主义倡导适当的代表和案件物体的重要性以及他们的共同进化的重要性。在这项工作中,我们建立在一个这样的形式主义之上,并为此介绍了对其的声音概念。我们证明,对于案例对象之间具有非确定性同步的网络,声音问题是可解除的。
translated by 谷歌翻译
培养的网站,等效地作为具有状态的矢量加法系统,是具有广泛应用程序的建立的并发模型。到达性问题,在我们询问是否从给定的初始配置中存在一系列达到给定最终配置的有效执行步骤,是该模型的中央算法问题。问题的复杂性仍然存在,直到最近,验证并发系统中最困难的开放问题之一。仅在2015年由LEROUX和SCHMITZ提供的第一个上限,然后由同一位作者提炼于2019年的非原始递归Ackermannian上限。在1976年,Lipton所示的指数空间下限仍然是唯一已知的40多年来,在2019年Czerwi {\'n}滑雪道,Lasota,Lazic,Leroux和Mazowiecki的突破性非基本下限。最后,今年由Czerwi {}滑雪和orlikowski宣布了一个匹配的Ackermannian下限,独立于Leroux,建立了问题的复杂性。我们的主要贡献是对前建筑的改进,使其概念上更简单,更直接。在我们的方式,改善了与固定维度(或等效的Petri网)的载体添加系统的下限:虽然Czerwi {\'n} Ski和Orlikowski证明$ f_k $ -hardness(硬度$ k $ th水平在grzegorczyk层次结构中)在维度$ 6k $ 6k $,我们的简化施工会收益超过$ 3k + 2 $的$ f_k $ -hardness。
translated by 谷歌翻译