With the advantage of fast calculation and map resources on cloud control system(CCS), cloud-based predictive cruise control(CPCC) for heavy trucks has great potential to improve energy efficiency, which is significan...With the advantage of fast calculation and map resources on cloud control system(CCS), cloud-based predictive cruise control(CPCC) for heavy trucks has great potential to improve energy efficiency, which is significant to achieve the goal of national carbon neutrality. However, most investigations focus on the on-board predictive cruise control(PCC) system,lack of research on CPCC architecture under CCS. Besides, the current PCC algorithms have the problems of a single control target and high computational complexity, which hinders the improvement of the control effect. In this paper, a layered architecture based on CCS is proposed to effectively address the realtime computing of CPCC system and the deployment of its algorithm on vehicle-cloud. In addition, based on the dynamic programming principle and the proposed road point segmentation method(RPSM), a PCC algorithm is designed to optimize the speed and gear of heavy trucks with slope information. Simulation results show that the CPCC system can adaptively control vehicle driving through the slope prediction, with fuel-saving rate of 6.17% in comparison with the constant cruise control. Also,compared with other similar algorithms, the PCC algorithm can make the engine operate more in the efficient zone by cooperatively optimizing the gear and speed. Moreover, the RPSM algorithm can reconfigure the road in advance, with a 91% roadpoint reduction rate, significantly reducing algorithm complexity.Therefore, this study has essential research significance for the economic driving of heavy trucks and the promotion of the CPCC system.展开更多
With the advantage of exceptional long-range traffic perception capabilities and data fusion computational prowess,the cloud control system(CCS)has exhibited formidable poten-tial in the realm of connected assisted dr...With the advantage of exceptional long-range traffic perception capabilities and data fusion computational prowess,the cloud control system(CCS)has exhibited formidable poten-tial in the realm of connected assisted driving,such as the adap-tive cruise control(ACC).Based on the CCS architecture,this paper proposes a cloud-based predictive ACC(PACC)strategy,which fully considers the road slope information and the preced-ing vehicle status.In the cloud,based on the dynamic program-ming(DP),the long-term economic speed planning is carried out by using the slope information.At the vehicle side,the real-time fusion planning of the economic speed and the preceding vehi-cle state is realized based on the model predictive control(MPC),taking into account the safety and economy of driving.In order to ensure the safety and stability of the vehicle-cloud cooperative control system,an event-triggered cruise mode switching method is proposed based on the state of each sub-system of the vehicle-cloud-network-map.Simulation results indicate that the PACC system can still ensure stable cruising under delays and some complex conditions.Moreover,under normal conditions,compared to the ACC system,the PACC sys-tem can further improve economy while ensuring safety and improve the overall energy efficiency of the vehicle,thus achiev-ing fuel savings of 3%to 8%.展开更多
针对当前两阶段的点云目标检测算法PointRCNN:3D object proposal generation and detection from point cloud在点云降采样阶段时间开销大以及低效性的问题,本研究基于PointRCNN网络提出RandLA-RCNN(random sampling and an effectivel...针对当前两阶段的点云目标检测算法PointRCNN:3D object proposal generation and detection from point cloud在点云降采样阶段时间开销大以及低效性的问题,本研究基于PointRCNN网络提出RandLA-RCNN(random sampling and an effectivelocal feature aggregator with region-based convolu-tional neural networks)架构。首先,利用随机采样方法在处理庞大点云数据时的高效性,对大场景点云数据进行下采样;然后,通过对输入点云的每个近邻点的空间位置编码,有效提高从每个点的邻域提取局部特征的能力,并利用基于注意力机制的池化规则聚合局部特征向量,获取全局特征;最后使用由多个局部空间编码单元和注意力池化单元叠加形成的扩展残差模块,来进一步增强每个点的全局特征,避免关键点信息丢失。实验结果表明,该检测算法在保留PointRCNN网络对3D目标的检测优势的同时,相比PointRCNN检测速度提升近两倍,达到16 f/s的推理速度。展开更多
基金supported by the National Key Research and Development Program (2021YFB2501003)the Key Research and Development Program of Guangdong Province (2019B090912001)the China Postdoctoral Science Foundation (2020M680531)。
文摘With the advantage of fast calculation and map resources on cloud control system(CCS), cloud-based predictive cruise control(CPCC) for heavy trucks has great potential to improve energy efficiency, which is significant to achieve the goal of national carbon neutrality. However, most investigations focus on the on-board predictive cruise control(PCC) system,lack of research on CPCC architecture under CCS. Besides, the current PCC algorithms have the problems of a single control target and high computational complexity, which hinders the improvement of the control effect. In this paper, a layered architecture based on CCS is proposed to effectively address the realtime computing of CPCC system and the deployment of its algorithm on vehicle-cloud. In addition, based on the dynamic programming principle and the proposed road point segmentation method(RPSM), a PCC algorithm is designed to optimize the speed and gear of heavy trucks with slope information. Simulation results show that the CPCC system can adaptively control vehicle driving through the slope prediction, with fuel-saving rate of 6.17% in comparison with the constant cruise control. Also,compared with other similar algorithms, the PCC algorithm can make the engine operate more in the efficient zone by cooperatively optimizing the gear and speed. Moreover, the RPSM algorithm can reconfigure the road in advance, with a 91% roadpoint reduction rate, significantly reducing algorithm complexity.Therefore, this study has essential research significance for the economic driving of heavy trucks and the promotion of the CPCC system.
基金supported by the National Key R&D Program of China(2021YFB2501000)the Consultancy Research Project on the Strategic Study of the Integration and Innovative Development of Intelligent Connected Vehicles and New Energy Ecology in Zhejiang Province(2023ZL0007)+1 种基金the Hetao Shenzhen-HongKong Science and Technology Innovation Cooperation Zone(HZQB-KCZYZ-2021055)the Open Project of the Key Laboratory of Modern Measurement and Control Technology of the Ministry of Education(KF2022-1123202).
文摘With the advantage of exceptional long-range traffic perception capabilities and data fusion computational prowess,the cloud control system(CCS)has exhibited formidable poten-tial in the realm of connected assisted driving,such as the adap-tive cruise control(ACC).Based on the CCS architecture,this paper proposes a cloud-based predictive ACC(PACC)strategy,which fully considers the road slope information and the preced-ing vehicle status.In the cloud,based on the dynamic program-ming(DP),the long-term economic speed planning is carried out by using the slope information.At the vehicle side,the real-time fusion planning of the economic speed and the preceding vehi-cle state is realized based on the model predictive control(MPC),taking into account the safety and economy of driving.In order to ensure the safety and stability of the vehicle-cloud cooperative control system,an event-triggered cruise mode switching method is proposed based on the state of each sub-system of the vehicle-cloud-network-map.Simulation results indicate that the PACC system can still ensure stable cruising under delays and some complex conditions.Moreover,under normal conditions,compared to the ACC system,the PACC sys-tem can further improve economy while ensuring safety and improve the overall energy efficiency of the vehicle,thus achiev-ing fuel savings of 3%to 8%.
文摘针对当前两阶段的点云目标检测算法PointRCNN:3D object proposal generation and detection from point cloud在点云降采样阶段时间开销大以及低效性的问题,本研究基于PointRCNN网络提出RandLA-RCNN(random sampling and an effectivelocal feature aggregator with region-based convolu-tional neural networks)架构。首先,利用随机采样方法在处理庞大点云数据时的高效性,对大场景点云数据进行下采样;然后,通过对输入点云的每个近邻点的空间位置编码,有效提高从每个点的邻域提取局部特征的能力,并利用基于注意力机制的池化规则聚合局部特征向量,获取全局特征;最后使用由多个局部空间编码单元和注意力池化单元叠加形成的扩展残差模块,来进一步增强每个点的全局特征,避免关键点信息丢失。实验结果表明,该检测算法在保留PointRCNN网络对3D目标的检测优势的同时,相比PointRCNN检测速度提升近两倍,达到16 f/s的推理速度。
