Xuetao Li

Covariance Volume Maximization for Embodied Latent Exploration in Deep Reinforcement Learning

Efficient exploration remains a key challenge in deep reinforcement learning, especially for embodied agents operating in realistic environments with high-dimensional observations and complex dynamics. Recent latent exploration methods define bonuses in a learned latent space, but often struggle in …

E^2DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation

In reinforcement learning (RL) for robotic manipulation, the Decision Transformer (DT) has emerged as an effective framework for addressing long-horizon tasks. However, DT’s performance depends heavily on the coverage of collected experiences. Without an active exploration mechanism, standard DT rel…

Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics

近年来，视觉-语言-行动（VLA）模型通过无缝整合视觉感知、语言理解和动作生成，在端到端的学习框架中彻底革新了机器人作。然而，由于这些模型设计为直接与物理世界和人类交互，其安全性至关重要，即使是小漏洞也可能导致灾难性故障。在本研究中，我们提出了通用对抗对象，这是一种表面纹理优化的球体，当置于机器人视野内时，任务成功率会显著降低。具体来说，我们的方法引入了一个多层次攻击框架，能够共同干扰轨迹规划、任务执行和动作控制。我们在模拟和现实机器人环境中验证了我们的方法。实验结果表明，对抗对象在两种代表性VLA模型（Pi0和RDT&#

RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation

Humanoid robots exhibit significant potential in executing diverse human-level skills. However, current research predominantly relies on data-driven approaches that necessitate extensive training datasets to achieve robust multimodal decision-making capabilities and generalizable visuomotor control.

When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual Tokens