More Like this

1. Robots that Suggest Safe Alternatives

   Jeong, Hyun Joe; Chen, Rosy; Bajcsy, Andrea (October 2025, IEEE International Conference on Intelligent Robots and Systems)

   Goal-conditioned policies, such as those learned via imitation learning, provide an easy way for humans to influence what tasks robots accomplish. However, these robot policies are not guaranteed to execute safely or to succeed when faced with out-of-distribution goal requests. In this work, we enable robots to know when they can confidently execute a user’s desired goal, and automatically suggest safe alternatives when they cannot. Our approach is inspired by control-theoretic safety filtering, wherein a safety filter minimally adjusts a robot’s candidate action to be safe. Our key idea is to pose alternative suggestion as a safe control problem in goal space, rather than in action space. Offline, we use reachability analysis to compute a goal-parameterized reach-avoid value network which quantifies the safety and liveness of the robot’s pre- trained policy. Online, our robot uses the reach-avoid value network as a safety filter, monitoring the human’s given goal and actively suggesting alternatives that are similar but meet the safety specification. We demonstrate our Safe ALTernatives (SALT) framework in simulation experiments with indoor navigation and Franka Panda tabletop manipulation, and with both discrete and continuous goal representations. We find that SALT is able to learn to predict successful and failed closed-loop executions, is a less pessimistic monitor than open- loop uncertainty quantification, and proposes alternatives that consistently align with those that people find acceptable. 

   more » « less
2. Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning

   Guo, Zijian; Zhou, Weichao; Wang, Shengao; Li, Wenchao (March 2025, The Thirteenth International Conference on Learning Representations)

   Offline safe reinforcement learning (OSRL) aims to learn policies with high rewards while satisfying safety constraints solely from data collected offline. However, the learned policies often struggle to handle states and actions that are not present or out-of-distribution (OOD) from the offline dataset, which can result in violation of the safety constraints or overly conservative behaviors during their online deployment. Moreover, many existing methods are unable to learn policies that can adapt to varying constraint thresholds. To address these challenges, we propose constraint-conditioned actor-critic (CCAC), a novel OSRL method that models the relationship between state-action distributions and safety constraints, and leverages this relationship to regularize critics and policy learning. CCAC learns policies that can effectively handle OOD data and adapt to varying constraint thresholds. Empirical evaluations on the benchmarks show that CCAC significantly outperforms existing methods for learning adaptive, safe, and high-reward policies. 

   more » « less
3. Learning Off-policy for Online Planning

   Sikchi, Harshit; Zhou, Wenxuan; Held, David (January 2021, Conference on Robot Learning (CoRL))

   Reinforcement learning (RL) in low-data and risk-sensitive domains requires performant and flexible deployment policies that can readily incorporate constraints during deployment. One such class of policies are the semi-parametric H-step lookahead policies, which select actions using trajectory optimization over a dynamics model for a fixed horizon with a terminal value function. In this work, we investigate a novel instantiation of H-step lookahead with a learned model and a terminal value function learned by a model-free off-policy algorithm, named Learning Off-Policy with Online Planning (LOOP). We provide a theoretical analysis of this method, suggesting a tradeoff between model errors and value function errors and empirically demonstrate this tradeoff to be beneficial in deep reinforcement learning. Furthermore, we identify the "Actor Divergence" issue in this framework and propose Actor Regularized Control (ARC), a modified trajectory optimization procedure. We evaluate our method on a set of robotic tasks for Offline and Online RL and demonstrate improved performance. We also show the flexibility of LOOP to incorporate safety constraints during deployment with a set of navigation environments. We demonstrate that LOOP is a desirable framework for robotics applications based on its strong performance in various important RL settings. 

   more » « less
4. Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning

   Banerjee, Arko; Rahmani, Kia; Biswas, Joydeep; Dillig, Isil (December 2024, Neurips 2024)

   Among approaches for provably safe reinforcement learning, Model Predictive Shielding (MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces, by leveraging a backup policy to ensure safety when the learned policy attempts to take risky actions. However, while MPS can ensure safety both during and after training, it often hinders task progress due to the conservative and task-oblivious nature of backup policies. This paper introduces Dynamic Model Predictive Shielding (DMPS), which optimizes reinforcement learning objectives while maintaining provable safety. DMPS employs a local planner to dynamically select safe recovery actions that maximize both short-term progress as well as long-term rewards. Crucially, the planner and the neural policy play a synergistic role in DMPS. When planning recovery actions for ensuring safety, the planner utilizes the neural policy to estimate long-term rewards, allowing it to observe beyond its short-term planning horizon. Conversely, the neural policy under training learns from the recovery plans proposed by the planner, converging to policies that are both high-performing and safe in practice. This approach guarantees safety during and after training, with bounded recovery regret that decreases exponentially with planning horizon depth. Experimental results demonstrate that DMPS converges to policies that rarely require shield interventions after training and achieve higher rewards compared to several state-of-the-art baselines 

   more » « less
5. Demo: Vulnerability Analysis for STL-Guided Safe Reinforcement Learning in Cyber-Physical Systems

   Jiang, Shixiong; Liu, Mengyu; Kong, Fanxin (May 2024, IEEE Real-Time and Embedded Technology and Applications Symposium)

   Cyber-Physical Systems(CPS) are the integration of sensing, control, computation, and networking with physical components and infrastructure connected by the internet. The autonomy and reliability are enhanced by the recent development of safe reinforcement learning (safe RL). However, the vulnerability of safe RL to adversarial conditions has received minimal exploration. In order to truly ensure safety in physical world applications, it is crucial to understand and address these potential safety weaknesses in learned control policies. In this work, we demonstrate a novel attack to violate safety that induces unsafe behaviors by adversarial models trained using reversed safety constraints. The experiment results show that the proposed method is more effective than existing works. 

   more » « less