Zobrazeno 1 - 10
of 1 026
pro vyhledávání: '"Li Keqiang"'
Autor:
Yue Chao, Zhong Jiaru, Ning Qili, Chen Xiaohui, Sun Chao, Wang Wenwei, Lian Yubo, Li Keqiang, Sun Fengchun
Publikováno v:
中国工程科学, Vol 26, Iss 1, Pp 45-58 (2024)
Vehicle ‒ energy‒road‒ cloud collaboration seamlessly integrates vehicles, energy, transportation, and the cloud, which is conducive to accelerating the formation of a new intelligent, low-carbon, safe, and efficient ecosystem of travel and lif
Externí odkaz:
https://doaj.org/article/977fe67e26084836b37a79ca906e4863
Publikováno v:
Jixie chuandong, Vol 47, Pp 131-137 (2023)
The cable-driven parallel robot is a special flexible mechanism in parallel mechanism, the end-effector of which is driven by cables instead of rigid rods. It integrates the advantages of flexible robots and parallel robots. A three-degree-of-freedom
Externí odkaz:
https://doaj.org/article/2761584d91df4d63b725fc5a4d7353c2
End-to-end autonomous driving offers a streamlined alternative to the traditional modular pipeline, integrating perception, prediction, and planning within a single framework. While Deep Reinforcement Learning (DRL) has recently gained traction in th
Externí odkaz:
http://arxiv.org/abs/2409.17659
End-to-end models are emerging as the mainstream in autonomous driving perception. However, the inability to meticulously deconstruct their internal mechanisms results in diminished development efficacy and impedes the establishment of trust. Pioneer
Externí odkaz:
http://arxiv.org/abs/2409.11969
Autor:
Zhang, Yichen, Wang, Zihan, Han, Jiali, Li, Peilin, Zhang, Jiaxun, Wang, Jianqiang, He, Lei, Li, Keqiang
3D Gaussian Splatting (3DGS) integrates the strengths of primitive-based representations and volumetric rendering techniques, enabling real-time, high-quality rendering. However, 3DGS models typically overfit to single-scene training and are highly s
Externí odkaz:
http://arxiv.org/abs/2409.11307
Autor:
He, Lei, Wang, Qiaoyi, Sun, Honglin, Xu, Qing, Gao, Bolin, Li, Shengbo Eben, Wang, Jianqiang, Li, Keqiang
Visual bird's eye view (BEV) perception, due to its excellent perceptual capabilities, is progressively replacing costly LiDAR-based perception systems, especially in the realm of urban intelligent driving. However, this type of perception still reli
Externí odkaz:
http://arxiv.org/abs/2409.05834
Perception is essential for autonomous driving system. Recent approaches based on Bird's-eye-view (BEV) and deep learning have made significant progress. However, there exists challenging issues including lengthy development cycles, poor reusability,
Externí odkaz:
http://arxiv.org/abs/2407.12491
Autor:
Sun, Jian, Dai, Yuqi, Vong, Chi-Man, Xu, Qing, Li, Shengbo Eben, Wang, Jianqiang, He, Lei, Li, Keqiang
Bird's-eye-view (BEV) semantic segmentation is becoming crucial in autonomous driving systems. It realizes ego-vehicle surrounding environment perception by projecting 2D multi-view images into 3D world space. Recently, BEV segmentation has made nota
Externí odkaz:
http://arxiv.org/abs/2407.13137
Autonomous driving perception models are typically composed of multiple functional modules that interact through complex relationships to accomplish environment understanding. However, perception models are predominantly optimized as a black box thro
Externí odkaz:
http://arxiv.org/abs/2405.04041
Autor:
He, Lei, Li, Leheng, Sun, Wenchao, Han, Zeyu, Liu, Yichen, Zheng, Sifa, Wang, Jianqiang, Li, Keqiang
Neural Radiance Field (NeRF) has garnered significant attention from both academia and industry due to its intrinsic advantages, particularly its implicit representation and novel view synthesis capabilities. With the rapid advancements in deep learn
Externí odkaz:
http://arxiv.org/abs/2404.13816