13 papers
Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure
Yiyuan Pan, Hanjiang Hu, Shangtao Li +2
A central challenge in deploying robot policies is inference-time policy steering: redirecting a policy to satisfy natural-language preferences unseen in training, without retraini…
VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring
Hanjiang Hu, Yiyuan Pan, Jiaxing Li +5
As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible consequences that digital errors…
Verified Task-Space Motion Planning Under Joint-Space Constraints
Hanjiang Hu, Changliu Liu, Yebin Wang
Reactive task-space planners such as Bug2 operate with fixed Cartesian step sizes and are unaware of the manipulator's joint-angle limits. When the Jacobian is poorly conditioned,…
Online Safety Filter for Deformable Object Manipulation with Horizon Agnostic Neural Operators
Jiaxing Li, Hanjiang Hu, Zhuoyuan Wang +2
Safety critical control of robotic manipulation tasks involving deformable media such as fluids, cloth, and soft objects remains challenging because existing learning based approac…
Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
Yiyuan Pan, Xusheng Luo, Hanjiang Hu +2
Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for effective long-term reasoning, tr…
Training Task Reasoning LLM Agents for Multi-turn Task Planning via Single-turn Reinforcement Learning
Hanjiang Hu, Changliu Liu, Na Li +1
Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge acquisition, reasoning, and tool use, making them promising candidates for autonomous agent appl…
Verifiable Safety Q-Filters via Hamilton-Jacobi Reachability and Multiplicative Q-Networks
Jiaxing Li, Hanjiang Hu, Yujie Yang +1
Recent learning-based safety filters have outperformed conventional methods, such as hand-crafted Control Barrier Functions (CBFs), by effectively adapting to complex constraints.…
Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Hanjiang Hu, Alexander Robey, Changliu Liu
Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectiv…
Safe PDE Boundary Control with Neural Operators
Hanjiang Hu, Changliu Liu
The physical world dynamics are generally governed by underlying partial differential equations (PDEs) with unknown analytical forms in science and engineering problems. Neural net…
Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation
Hanjiang Hu, Yujie Yang, Tianhao Wei +1
Control barrier functions (CBFs) are important in safety-critical systems and robot control applications. Neural networks have been used to parameterize and synthesize CBFs with bo…
Robust Tracking Control with Neural Network Dynamic Models under Input Perturbations
Huixuan Cheng, Hanjiang Hu, Changliu Liu
Robust control problems have significant practical implications since external disturbances can significantly impact the performance of control methods. Existing robust control met…
ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks
Tianhao Wei, Hanjiang Hu, Luca Marzari +4
Deep Neural Networks (DNN) are crucial in approximating nonlinear functions across diverse applications, ranging from image classification to control. Verifying specific input-outp…
Improving Policy Optimization via -Retrain
Luca Marzari, Priya L. Donti, Changliu Liu +1
We present -retrain, an exploration strategy encouraging a behavioral preference while optimizing policies with monotonic improvement guarantees. To this end, we intro…