2026

1. [C119] Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure
   Yiyuan Pan, Hanjiang Hu, Shangtao Li, Xusheng Luo and Changliu Liu
   Conference on Robot Learning, 2026
   

   Preprint Abstract Cite

   Citation Formats: BibTeX Plain Text

   Abstract:
   

   A central challenge in deploying learned robot policies is inference-time behavior steering: redirecting a policy at test time to satisfy user preferences not anticipated during training, without retraining. Existing methods fail in two modes: end-to-end methods require fine-tuning or expert-level guidance, while neuro-symbolic methods rely on predefined symbols whose edits can result in logically reasonable but physically infeasible plans. To address this challenge, we propose ReStruct, which builds upon a neural automaton policy that decomposes a visuomotor policy into a high-level state-machine skeleton capturing task structure and a low-level continuous controller represented as a residual policy. Specifically, ReStruct adopts the automaton to represent the preference and incorporates it into the skeleton through a synchronous product, thereby reconfiguring the task structure. With the controller kept frozen, the action priors provided by the skeleton are updated accordingly to enable physically-aware control under a modified task structure. Extensive experiments from simulation and real-world show that ReStruct steers a wide range of preferences, from object-centric specifications to temporal-logic constraints, and after steering surpasses existing methods, exceeding VLA models in both task success and preference-following by up to 25%.

2. [C115] Learning Safe-Stoppability Monitors for Humanoid Robots
   Yifan Sun, Yiyuan Pan, Shangtao Li, Caiwu Ding, Tao Cui, Lingyun Wang and Changliu Liu
   IEEE/RSJ International Conference on Intelligent Robots and Systems, 2026
   

   Preprint Page Video Abstract Cite

   Citation Formats: BibTeX Plain Text

   Abstract:
   

   Emergency stop (E-stop) mechanisms are the de facto standard for robot safety. However, for humanoid robots, abruptly cutting power can itself cause catastrophic failures; instead, an emergency stop must execute a predefined fallback controller that preserves balance and drives the robot toward a minimum-risk condition. This raises a critical question: from which states can a humanoid robot safely execute such a stop? In this work, we formalize emergency stopping for humanoids as a policy-dependent safe-stoppability problem and use data-driven approaches to characterize the safe-stoppable envelope. We introduce PRISM (Proactive Refinement of Importance-sampled Stoppability Monitor), a simulation-driven framework that learns a neural predictor for state-level stoppability. PRISM iteratively refines the decision boundary using importance sampling, enabling targeted exploration of rare but safety-critical states. This targeted exploration significantly improves data efficiency while reducing false-safe predictions under a fixed simulation budget. We further demonstrate sim-to-real transfer by deploying the pretrained monitor on a real humanoid platform. Results show that modeling safety as policy-dependent stoppability enables proactive safety monitoring and supports scalable certification of fail-safe behaviors for humanoid robots.

   Video:
   
3. [C112] Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
   Yiyuan Pan, Xusheng Luo, Hanjiang Hu, Peiqi Yu and Changliu Liu
   Robotics: Science and Systems, 2026
   

   Preprint Page Cite

   Citation Formats: BibTeX Plain Text

1. [U] VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring
   Hanjiang Hu, Yiyuan Pan, Jiaxing Li, Xusheng Luo, Alexander Robey, Na Li, Yebin Wang and Changliu Liu
   arXiv: 2606.03954, 2026
   

   Preprint Code Abstract Cite

   Citation Formats: BibTeX Plain Text

   Abstract:
   

   As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount – physical actions carry immediate and irreversible consequences that digital errors do not. We introduce the Vision-Language Embodied Safety Agent (VLESA), a framework that monitors human activities from egocentric video and triggers real-time safety interventions when dangerous actions are predicted. VLESA addresses intent-dependent safety where identical actions can be safe or dangerous depending on context. A dataset pairing egocentric frames with goal-conditioned safety annotations is introduced, enabling a goal-conditioned safety Q-filter trained via GRPO that evaluates actions with respect to inferred intent without retraining. On top of that, an intent-action prediction agent is proposed to jointly infer goals and predict future actions from video. On the ASIMOV-2.0 benchmark, VLESA achieves higher intervention accuracy at the exact ground-truth frame compared to baselines, while the GRPO-trained Q-filter improves action safety by over 41 percentage points through goal-conditioned constrained decoding.