6 papers
LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
Chenxu Wang, Yongkun Yang, Boyuan Du +2
Deliberation plays a crucial role in collaboration; when humans work together, they naturally engage in communication to align information and reach an agreement. In this paper, we…
Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration
Nan Sun, Bo Mao, Yongchang Li +3
Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a singl…
CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human
Nan Sun, Yongchang Li, Chenxu Wang +2
In this work, we present CollabVLA, a self-reflective vision-language-action framework that transforms a standard visuomotor policy into a collaborative assistant. CollabVLA tackle…
Towards Robust Deep Reinforcement Learning against Environmental State Perturbation
Chenxu Wang, Huaping Liu
Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations,…
A VLM-based Method for Visual Anomaly Detection in Robotic Scientific Laboratories
Shiwei Lin, Chenxu Wang, Xiaozhen Ding +5
In robot scientific laboratories, visual anomaly detection is important for the timely identification and resolution of potential faults or deviations. It has become a key factor i…
Trajectory Entropy Reinforcement Learning for Predictable and Robust Control
Bang You, Chenxu Wang, Huaping Liu
Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learnin…