Sim2CBF: From Forward Simulations to Implicit Control Barrier Function Safety Filtering without Model Derivatives
Organizations: Department of Robotics, Perception and Learning, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden
Abstract
Failure avoidance in complex robot-environment interactions is challenging because the underlying dynamics are difficult to model accurately, and available predictive models may not provide reliable derivatives. We present Sim2CBF, a failure-avoidance framework that solves the Control Barrier Function (CBF)-Safety Filter (SF) optimization problem using only forward-model evaluations, thereby avoiding differentiation of the predictive model. Specifically, we approximate the CBF constraint using finite differences and local linear interpolation over sampled control inputs while preserving failure-avoidance guarantees. The underlying CBF is implicit and constructed from backup-policy rollouts, enabling the use of expressive predictive models such as physics-based simulators and learned world models. Compared with purely sampling-based SFs, our formulation requires fewer control samples and yields less conservative behavior than direct nominal-backup blending. We evaluate Sim2CBF in simulation, hardware box-toppling, and vision-based control tasks, demonstrating its applicability to contact-rich and learned dynamics, as well as its adaptability to changes in the predictive model.
Figures & tables
| Method | Safe Success Rate | |
|---|---|---|
| Nominal (No SF) | 0.45 | 0.00 0.00 |
| Direct Blending | 0.86 | 0.50 0.80 |
| Interpolation without Blending (Ours) | 0.78 | 0.27 0.52 |
| Interpolation with Blending (Ours) | 0.95 | 0.67 0.79 |
| Sample and Select | 0.82 | 0.49 0.75 |
| Neural CBF + Sample and Select | 1.00 | 0.17 0.52 |
Robot Safety
Robot safety studies how to prevent harmful physical actions while enabling robots to complete tasks around people and in uncertain environments.
See all 254 papers