RedNote
NoSB01
Active Perceptive Whole-Body Control
Integrating vision, proprioception, and active sensing so robots can coordinate their whole body around terrain and tasks.
PhD Researcher · National University of Singapore
LI Peizhuo李培卓
I study how legged robots can perceive, decide, and work in complex environments.
My research sits at the intersection of reinforcement learning and active perceptive whole-body control — building adaptive robotic systems that work reliably beyond the lab.
Research focus
- Legged robotics
- Reinforcement learning
- Active perceptive whole-body control
02 / Research
Building robots that work in the real world.
I build learning-based control systems that connect perception to action, with an emphasis on reliability, adaptability, and deployment beyond controlled settings.
02
Adaptive Robot Learning
Developing reinforcement learning methods that remain robust, responsive, and adaptable when transferred to real robots.
03
Loco-Manipulation
Coordinating mobility and manipulation through hierarchical policies so legged robots can complete whole-body tasks.
03 / Publications
Selected research
Recent work on humanoid and quadruped locomotion, reinforcement learning, and whole-body control.
Featured work
All publications
14 papers · Scroll
01
PGMT: Perceptive General Motion Tracking for Humanoid Robots
arXiv preprint · 2026
02TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
Under review · 2026
03KiVi: Kinesthetic-Visuospatial Integration for Dynamic and Safe Egocentric Legged Locomotion
IEEE/RSJ IROS · 2026
04LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control
arXiv preprint · 2026
05GPO: Growing Policy Optimization for Legged Robot Locomotion and Whole-Body Control
arXiv preprint · 2026
06FARE: Fast-Slow Agentic Robotic Exploration
arXiv preprint · 2026
07Unicorn: A Universal and Collaborative Reinforcement Learning Approach Toward Generalizable Network-Wide Traffic Signal Control
IEEE T-ITS · 2026
08HeLoM: Hierarchical Learning for Whole-Body Loco-Manipulation by a Hexapod Robot
Under review · 2026
09HEADER: Hierarchical Robot Exploration via Attention-Based Deep Reinforcement Learning with Expert-Guided Reward
arXiv preprint · 2025
10SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning
Robotics: Science and Systems · 2025
11CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control
IEEE T-ITS · 2025
12HeteroLight: A General and Efficient Learning Approach for Heterogeneous Traffic Signal Control
IEEE/RSJ IROS · 2024
13DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies
IEEE/RSJ IROS · 2024
14Learning-based Hierarchical Control: Emulating the Central Nervous System for Bio-Inspired Legged Robot Locomotion
IEEE/RSJ IROS · 2024
04 / Journey
Research shaped by learning and practice.
Education
Aug 2023 — Jun 2027 (expected)
PhD in Mechanical Engineering
May — Aug 2026
Summer Exchange · Center of X-Mechanics
May — Aug 2025
Summer Exchange · Robotics & Machine Intelligence Lab
2019 — 2023
B.Eng. in Mechanical Engineering
Experience
Aug 2026 — Present
Algorithm Intern
Sep 2025 — Present
Research Assistant
Dec 2025 — Aug 2026
Algorithm Intern
Jan 2024 — Sep 2025
Student Research Assistant
Aug 2024 — May 2025