CrossSafe proposes embodiment-conditioned safety filtering that uses a Hamilton‑Jacobi reachability value function shared across robots while conditioning on each robot’s morphology and kinematics via a morphology‑aware latent representation. The method performs reachability analysis directly in latent space, enabling a single policy trained on multiple bimanual robot embodiments and manipulation tasks to generalize zero‑shot to a held‑out embodiment and reduce collision rates. Experiments on five embodiments and five tasks demonstrate that training with more embodiments improves generalization.
By Ihab Tabbara, Yuxuan Yang, Hussein Sibai
SEVI (Safe Evidential Real-World Reinforcement Learning) is a framework that adds a safety intervention layer to real‑world policy learning. It uses an Evidential Safety Critic to estimate both future constraint‑violation risk and epistemic uncertainty in a single forward pass, and overrides unsafe or poorly supported actions with an offline‑trained recovery policy. Experiments on simulated manipulation tasks and a real‑world USB insertion task show that SEVI improves trajectory‑level safety prediction, task success, and reduces unsafe events by 13.4–57.1% compared to other safe RL baselines.
By Shaekh Mohammad Shithil, Lantao Liu
arXiv:2606. 23754v1 Announce Type: cross Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes these models opaque and difficult to analyze formally, rendering them intractable for existing verification tools.
By Davide Corsi, Kyungmin Kim, Roy Fox
arXiv:2609. 11697v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) and World-Action Models (WAMs) have demonstrated strong capabilities in general-purpose robotic manipulation, yet their generated actions may violate hard physical constraints and therefore be unsafe or infeasible for deployment.
By Jianming Ma, Rongjun Jin, Xiaxi Si, Yang Zhang, Yiheng Li, Yue Gao
The paper introduces an oracle-guided differentiable safeguard for flow-matching robot policies that ensures safety constraints are met without explicit constraint models. By using binary feasibility queries during both forward and backward passes, the method corrects unsafe updates and incorporates local boundary information into learning signals. Experiments on obstacle-aware robotic manipulation show that the approach achieves 100% constraint satisfaction while maintaining task performance.
By Jianming Ma, Rongjun Jin, Yizhi Chen, Yue Gao
arXiv:2607. 12784v1 Announce Type: cross Abstract: Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation.
By Paolo Magliano, Puze Liu, Jan Peters, Davide Tateo, Raffaello Camoriano
The paper introduces Safety to Competence (S2C), a two‑stage reinforcement learning framework that first learns a safety filter and then trains a competitive task policy while embedding the filter. By separating safety synthesis from task learning, S2C reduces training complexity and prevents the policy from being exploited by adversarial attacks. Experiments on simulated touchdown games show that S2C achieves higher win rates, better Elo ratings, and lower exploitability than eight safe‑RL baselines, and hardware tests confirm its competence against a human opponent.
By Ruihan Wu, Rui Yang, Donggeon David Oh, Duy Nguyen, Haimin Hu
arXiv:2606. 05660v1 Announce Type: cross Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments.
By Dabin Kim, Daemin Park, Sangyub Lee, Jinsik Kim, Yeongtak Oh, Jongho Shin, Sungroh Yoon
Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation. However, real-world deployment in open-ended environments requires strong safety guarantees to prevent dangerous or harmful behaviors.
arXiv:2606. 00090v1 Announce Type: cross Abstract: Physical AI systems increasingly map multimodal observations, language instructions, and learned world representations into physically consequential actions.
By Barak Or
arXiv:2608.06481v2 Announce Type: replace-cross
Abstract: Synthesizing safe and robust neural controllers in simulation for reliable sim-to-real deployment remains a critical challenge in robotics. E...
By Riccardo Curcio, Hongpeng Cao, Marco Caccamo
arXiv:2606. 31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics.
By Hongpeng Cao, Liqun Zhao, Yuliang Gu, Naira Hovakimyan, Lui Sha, Marco Caccamo