Jitu Lv

About

Jitu Lv is a pioneering researcher at the intersection of artificial intelligence, robotics, and brain-computer interfaces. His work focuses on two transformative areas: creative robotic manipulation and human-in-the-loop reinforcement learning. In his highly cited 2018 paper on "Generative Adversarial Nets in Robotic Chinese Calligraphy" (36 citations), Lv revolutionized robotic artistry by using GANs to generate diverse, high-quality Chinese character strokes—overcoming the rigid, monotonous outputs of traditional methods. This breakthrough enables robots to produce authentic, varied calligraphy, bridging computational creativity with cultural heritage. Equally impactful is his 2018 study on "Deep reinforcement learning from error-related potentials via an EEG-based brain-computer interface" (28 citations). Here, Lv addressed a critical limitation in deep RL: the inability to provide real-time human feedback in dynamic environments. By integrating EEG-measured error-related potentials, he created a system where robots learn directly from neural signals, bypassing the need for explicit human preferences. This work paves the way for intuitive, real-world robotic training. With 64 total citations across these foundational papers, Lv is a rising star whose interdisciplinary contributions promise to reshape how robots learn, create, and interact with humans.

Research Focus

Key Achievements

Top Papers

1. 1
   Generative Adversarial Nets in Robotic Chinese Calligraphy

   36 citations · 2018
2. 2
   Deep reinforcement learning from error-related potentials via an EEG-based brain-computer interface

   28 citations · 2018

Key Collaborators

Contact & Links