Zobrazeno 1 - 10
of 244
pro vyhledávání: '"Keng Peng"'
Publikováno v:
地质科技通报, Vol 41, Iss 2, Pp 309-314 (2022)
The constraint conditions have a great influence on the geometry of reservoir landslides during mass movement and are one of the most important parameters for predicting landslide-generated waves. To explore the effects of constraint conditions on th
Externí odkaz:
https://doaj.org/article/9535f02340d34517afe5fc96578861d4
Publikováno v:
Frontiers in Robotics and AI, Vol 9 (2022)
Externí odkaz:
https://doaj.org/article/e437f6b05b8744b0a168d1c3cb6733ff
Autor:
Sun, Jiawei, Li, Jiahui, Liu, Tingchen, Yuan, Chengran, Sun, Shuo, Huang, Zefan, Wong, Anthony, Tee, Keng Peng, Ang Jr, Marcelo H.
We introduce RMP-YOLO, a unified framework designed to provide robust motion predictions even with incomplete input data. Our key insight stems from the observation that complete and reliable historical trajectory data plays a pivotal role in ensurin
Externí odkaz:
http://arxiv.org/abs/2409.11696
Autor:
Yuan, Chengran, Zhang, Zhanqi, Sun, Jiawei, Sun, Shuo, Huang, Zefan, Lee, Christina Dao Wen, Li, Dongen, Han, Yuhang, Wong, Anthony, Tee, Keng Peng, Ang Jr, Marcelo H.
Motion planning is a challenging task to generate safe and feasible trajectories in highly dynamic and complex environments, forming a core capability for autonomous vehicles. In this paper, we propose DRAMA, the first Mamba-based end-to-end motion p
Externí odkaz:
http://arxiv.org/abs/2408.03601
Autor:
Sun, Jiawei, Yuan, Chengran, Sun, Shuo, Wang, Shanze, Han, Yuhang, Ma, Shuailei, Huang, Zefan, Wong, Anthony, Tee, Keng Peng, Ang Jr, Marcelo H.
The ability to accurately predict feasible multimodal future trajectories of surrounding traffic participants is crucial for behavior planning in autonomous vehicles. The Motion Transformer (MTR), a state-of-the-art motion prediction method, alleviat
Externí odkaz:
http://arxiv.org/abs/2404.10295
Publikováno v:
Robotics, Vol 4, Iss 3, Pp 365-397 (2015)
Multi-robot foraging has been widely studied in the literature, and the general assumption is that the robots are simple, i.e., with limited processing and carrying capacity. We previously studied continuous foraging with slightly more capable robots
Externí odkaz:
https://doaj.org/article/dfead6ee17164307accab754cea9f851
Autor:
Sun, Jiawei, Yuan, Chengran, Sun, Shuo, Liu, Zhiyang, Goh, Terence, Wong, Anthony, Tee, Keng Peng, Ang Jr, Marcelo H.
Accurately predicting interactive road agents' future trajectories and planning a socially compliant and human-like trajectory accordingly are important for autonomous vehicles. In this paper, we propose a planning-centric prediction neural network,
Externí odkaz:
http://arxiv.org/abs/2211.06031
The domain of robotics is challenging to apply deep reinforcement learning due to the need for large amounts of data and for ensuring safety during learning. Curriculum learning has shown good performance in terms of sample- efficient deep learning.
Externí odkaz:
http://arxiv.org/abs/2204.06835
Autor:
Acar, Cihan, Tee, Keng Peng
Sampling-based motion planning under task constraints is challenging because the null-measure constraint manifold in the configuration space makes rejection sampling extremely inefficient, if not impossible. This paper presents a learning-based sampl
Externí odkaz:
http://arxiv.org/abs/2204.06791
We present KOVIS, a novel learning-based, calibration-free visual servoing method for fine robotic manipulation tasks with eye-in-hand stereo camera system. We train the deep neural network only in the simulated environment; and the trained model cou
Externí odkaz:
http://arxiv.org/abs/2007.13960