no code implementations • 17 Jul 2022 • QIUJING LU, YiPeng Zhang, Mingjian Lu, Vwani Roychowdhury
We propose a novel framework, On-Demand MOtion Generation (ODMO), for generating realistic and diverse long-term 3D human motion sequences conditioned only on action types with an additional capability of customization.
no code implementations • 10 May 2022 • QIUJING LU, Weiqiao Han, Jeffrey Ling, Minfa Wang, Haoyu Chen, Balakrishnan Varadarajan, Paul Covington
Predicting future trajectories of road agents is a critical task for autonomous driving.
no code implementations • 6 May 2022 • Arash Vahabpour, Tianyi Wang, QIUJING LU, Omead Pooladzandi, Vwani Roychowdhury
Imitation learning is the task of replicating expert policy from demonstrations, without access to a reward function.
no code implementations • 29 Sep 2021 • Arash Vahabpour, QIUJING LU, Tianyi Wang, Omead Pooladzandi, Vwani Roychowhury
To address this problem, we introduce a novel generative model for behavior cloning, in a mode-separating manner.