12 papers
ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching Policies
Jianming Ma, Rongjun Jin, Xiaxi Si +3
Vision-Language-Action (VLA) and World-Action Models (WAMs) have demonstrated strong capabilities in general-purpose robotic manipulation, yet their generated actions may violate h…
P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning
Liyun Yan, Jianming Ma, Yang Zhang +5
Variational Autoencoders are widely used to encode high-dimensional and noisy observations in robotics. However, their stochastic latent creates a mismatch with Proximal Policy Opt…
PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Update
Jianming Ma, Qiyue Yang, Yang Zhang +4
While flow-based generative models have demonstrated strong performance across a wide range of domains, deploying them in safety-critical physical systems remains challenging due t…
HierKick: Hierarchical Reinforcement Learning for Vision-Guided Soccer Robot Control
Yizhi Chen, Zheng Zhang, Zhanxiang Cao +7
Controlling soccer robots involves multi-time-scale decision-making, which requires balancing long-term tactical planning and short-term motion execution. Traditional end-to-end re…
HiWET: Hierarchical World-Frame End-Effector Tracking for Long-Horizon Humanoid Loco-Manipulation
Zhanxiang Cao, Liyun Yan, Yang Zhang +7
Humanoid loco-manipulation requires executing precise manipulation tasks while maintaining dynamic stability amid base motion and impacts. Existing approaches typically formulate c…
FocusNav: Spatial Selective Attention with Waypoint Guidance for Humanoid Local Navigation
Yang Zhang, Jianming Ma, Liyun Yan +4
Robust local navigation in unstructured and dynamic environments remains a significant challenge for humanoid robots, requiring a delicate balance between long-range navigation tar…
Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy
Buqing Nie, Yang Zhang, Rongjun Jin +4
The human nervous system exhibits bilateral symmetry, enabling coordinated and balanced movements. However, existing Deep Reinforcement Learning (DRL) methods for humanoid robots n…
Keep on Going: Learning Robust Humanoid Motion Skills via Selective Adversarial Training
Yang Zhang, Zhanxiang Cao, Buqing Nie +6
Humanoid robots are expected to operate reliably over long horizons while executing versatile whole-body skills. Yet Reinforcement Learning (RL) motion policies typically lose stab…
Learning Motion Skills with Adaptive Assistive Curriculum Force in Humanoid Robots
Zhanxiang Cao, Yang Zhang, Buqing Nie +3
Learning policies for complex humanoid tasks remains both challenging and compelling. Inspired by how infants and athletes rely on external support--such as parental walkers or coa…
Minimizing Acoustic Noise: Enhancing Quiet Locomotion for Quadruped Robots in Indoor Applications
Zhanxiang Cao, Buqing Nie, Yang Zhang +1
Recent advancements in quadruped robot research have significantly improved their ability to traverse complex and unstructured outdoor environments. However, the issue of noise gen…
Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots
Yang Zhang, Buqing Nie, Zhanxiang Cao +2
Reinforcement Learning (RL)-based methods have significantly improved the locomotion performance of legged robots. However, these motion policies face significant challenges when d…
Ask1: Development and Reinforcement Learning-Based Control of a Custom Quadruped Robot
Yang Zhang, Yuxing Lu, Guiyang Xin +4
In this work, we present the design, development, and experimental validation of a custom-built quadruped robot, Ask1. The Ask1 robot shares similar morphology with the Unitree Go1…