13 papers
PGMT: Perceptive General Motion Tracking for Humanoid Robots
Hongyi Li, Li Peizhuo, Yucheng Tao +9
Humanoid motion trackers can reproduce diverse whole-body motions, but their performance degrades on complex terrain where terrain-agnostic references become physically infeasible.…
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
Peizhuo Li, Hongyi Li, Mingfeng Fan +13
Agile humanoid locomotion across diverse challenging terrain demands both wide perceptual coverage and precise local geometry understanding. Motivated by the way humans selectively…
CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control
Yifeng Zhang, Harsh Goel, Peizhuo Li +3
Adaptive traffic signal control (ATSC) is crucial in alleviating congestion, maximizing throughput and promoting sustainable mobility in ever-expanding cities. Multi-Agent Reinforc…
LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control
Yifeng Zhang, Peizhuo Li, Tingguang Zhou +2
Adaptive Traffic Signal Control (ATSC) aims to optimize traffic flow and minimize delays by adjusting traffic lights in real time. Recent advances in Multi-agent Reinforcement Lear…
GPO: Growing Policy Optimization for Legged Robot Locomotion and Whole-Body Control
Shuhao Liao, Peizhuo Li, Xinrong Yang +7
Training reinforcement learning (RL) policies for legged robots remains challenging due to high-dimensional continuous actions, hardware constraints, and limited exploration. Exist…
FARE: Fast-Slow Agentic Robotic Exploration
Shuhao Liao, Xuxin Lv, Jeric Lew +6
This work advances autonomous robot exploration by integrating agent-level semantic reasoning with fast local control. We introduce FARE, a hierarchical autonomous exploration fram…
HEADER: Hierarchical Robot Exploration via Attention-Based Deep Reinforcement Learning with Expert-Guided Reward
Yuhong Cao, Yizhuo Wang, Jingsong Liang +4
This work pushes the boundaries of learning-based methods in autonomous robot exploration in terms of environmental scale and exploration efficiency. We present HEADER, an attentio…
HeLoM: Hierarchical Learning for Whole-Body Loco-Manipulation by a Hexapod Robot
Xinrong Yang, Peizhuo Li, Hongyi Li +8
In nature, animals often need to move/manipulate objects comparable in weight/size to their own bodies. Compared to grasping and carrying, pushing provides a more straightforward a…
KiVi: Kinesthetic-Visuospatial Integration for Dynamic and Safe Egocentric Legged Locomotion
Peizhuo Li, Hongyi Li, Yuxuan Ma +8
Vision-based locomotion has shown great promise in enabling legged robots to perceive and adapt to complex environments. However, visual information is inherently fragile, being vu…
Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control
Yifeng Zhang, Yilin Liu, Ping Gong +3
Adaptive traffic signal control (ATSC) is crucial in reducing congestion, maximizing throughput, and improving mobility in rapidly growing urban areas. Recent advancements in param…
SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning
Peizhuo Li, Hongyi Li, Ge Sun +7
Despite recent advances in learning-based controllers for legged robots, deployments in human-centric environments remain limited by safety concerns. Most of these approaches use p…
Learning-based Hierarchical Control: Emulating the Central Nervous System for Bio-Inspired Legged Robot Locomotion
Ge Sun, Milad Shafiee, Peizhuo Li +3
Animals possess a remarkable ability to navigate challenging terrains, achieved through the interplay of various pathways between the brain, central pattern generators (CPGs) in th…
DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies
Shivam Sood, Ge Sun, Peizhuo Li +1
Optimal Control for legged robots has gone through a paradigm shift from position-based to torque-based control, owing to the latter's compliant and robust nature. In parallel to t…