王纪龙 | Jilong(Jaylon) Wang
I am a researcher at Peking University - GALBOT Joint Lab and Center on Frontiers of Computing Studies (CFCS), directed by He Wang. I received my B.S. from UC Santa Cruz in 2023. I have previously interned at BAAI, SenseTime, Westlake University, and Tsinghua University, and have also participated in exchange programs at UC Berkeley and Shanghai Jiao Tong University.
My research interests lie at the intersection of robotics and machine learning. Regarding the RL vs. MPC debate, I believe the distinction is subtle. Both frameworks demand human-in-the-loop refinement during development. While RL employs reward-driven trial-and-error learning, MPC utilizes model-based real-time optimization. Neither evolves autonomously: human expertise shapes their architectures, hyperparameters, and failure recovery strategies.
Publications
GAMMA: Graspability-Aware Mobile MAnipulation Policy Learning based on Online Grasping Pose FusionICRA 2024
Adaptive legged manipulation: Versatile disturbance predictive control for quadruped robots with robotic armsRobotics and Autonomous Systems
Terrain-Aware Risk-Assessment-Network-Aided Deep Reinforcement Learning for Quadrupedal Locomotion in Tough TerrainIROS 2021
Hierarchical terrain-aware control for quadrupedal locomotion by combining deep reinforcement learning and optimal controlIROS 2021
