Yixiang Wang — accepted AI-conference papers

2024

Transformable Inspection Robot Design and Implementation for Complex Pipeline Environment

Jianlin Wang, Yixiang Wang, Lining Peng, Haixiang Zhang, Hang Gao, Chengjiang Wang +3

RA-L 2024

Pipeline inspections are crucial to ensure the reliability of the transmission system. However, with the growing complexity and aging of the pipe system, traditional pipeline inspection robots struggle to adapt to complex environments with obstacles, cracks, changing cross-section, and other challen

Cited by 6 Source ↗Scholar ↗

2020

Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping

Yujing Hu, Weixun Wang, Hangtian Jia, Yixiang Wang, Yingfeng Chen, Jianye Hao +2

NeurIPS 2020poster

Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However, since the transformation of human knowledge into numeric reward…

Cited by 246 Source ↗PDF ↗Scholar ↗