Non-Myopic Safety Filtering with Learned Intervention Cost-to-Go
Authors: Johannes Autenrieb, Mark Spiller, Daniel Silvestre, Namhoon Cho, Jason J. Choi
Organizations: German Aerospace Center (DLR) · NOVA School of Science and Technology · Seoul National University · University of California, Los Angeles
Control barrier function (CBF) safety filters minimize instantaneous deviation from a nominal control command, but a sequence of pointwise-minimal interventions need not minimize cumulative intervention effort. This paper proposes a discrete-time non-myopic safety filter using a learned approximation of the optimal intervention cost-to-go over CBF-admissible policies. The approximation enters through a relaxed Bellman-residual constraint, while the original barrier condition remains hard. Feasibility is equivalent to that of the conventional CBF filter, and forward invariance remains independent of approximation accuracy under the stated assumptions. We derive a trajectory-wise performance certificate that requires neither the optimal value function nor an approximation-error bound. Under additional approximation and horizon assumptions, a suboptimality bound contains an explicit endpoint approximation-error term together with accumulated tolerance and relaxation terms. Numerical results for a collision-avoidance problem show an approximately 50% reduction in mean cumulative intervention effort relative to conventional CBF filtering over 100 initial conditions not used during training or parameter selection. The improvement is consistent across three independently trained networks, while maintaining the prescribed safety constraints and requiring less online computation than the tested predictive filter.
Figures & tables
Figure 1: Controller trajectories and offline optimal solution.
Method
JN (Fig. 1 )
Mean JN
Saving vs. CBF
Time [ms]
CBF
218.0
200.5
–
0.31
H-CBF-QP
209.8
188.8
11.7 (5.8%)
0.50
MPC-CBF ( H=15 )
85.5
83.8
116.7 (58.2%)
24.97
NMF
93.6
101.3
99.2 (49.5%)
3.31
Offline optimal solution
74.4
–
–
–
Table 1: Intervention costs, savings relative to CBF, and mean online time over 100 test cases.
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 2: Orthogonal projections of the trajectories in Fig. 1 .
Figure 3: Stage intervention cost and sampled obstacle clearance.
Figure 4: Cumulative intervention cost and NMF slack.
Figure 5: Cumulative intervention costs and mean computation times over 100 test cases.
Safety filters are an effective tool for enforcing constraints in safety-critical systems, but most existing methods assume perfect state information, which is rarely available in practice. Recent work has begun to close this gap by developing filtering mechanisms that are robust to state estimation error, but these methods can still exhibit safety violations or overly conservative behavior as estimation error grows. Focusing on obstacle avoidance, we develop two new control barrier function (CBF) formulations: drift-measurement-robust (DMR)-CBFs and neural measurement-robust (NMR)-CBFs. The DMR-CBF augments the standard CBF condition with an inner optimization over the worst-case uncertainty in the drift dynamics, improving robustness to estimation error. This DMR-CBF then supervises a pretraining phase for the NMR-CBF, which replaces the inner optimization with a learned term. The NMR-CBF is subsequently finetuned through differentiable trajectory rollouts, yielding a filter that achieves empirical safety comparable to the DMR-CBF while reducing both conservativeness and computational cost. We provide theoretical analysis of the DMR-CBF along with numerical results on a planar double integrator and a 12D quadrotor, where both proposed approaches prevent collisions while other robust methods either fail or are overly conservative. Finally, we deployed the NMR-CBF on a Unitree Go2, enabling successful navigation of an obstacle field under odometry errors that caused a standard CBF to collide.
Safety filters provide a practical approach for enforcing safety constraints in autonomous systems. While learning-based tools scale to high-dimensional systems, their performance depends on informative data that includes states likely to lead to constraint violation, which can be difficult to efficiently sample in complex, high-dimensional systems. In this work, we characterize trajectories that barely avoid safety violations using the Pontryagin Maximum Principle. These boundary trajectories are used to guide data collection for learned Hamilton-Jacobi Reachability, concentrating learning efforts near safety-critical states to improve efficiency. The learned Control Barrier Value Function is then used directly for safety filtering. Simulations and experimental validation on a shared-control automotive racing application demonstrate PMP sampling improves learning efficiency, yielding faster convergence, reduced failure rates, and improved safe set reconstruction, with wall times around 3ms.
James Dallas, Thomas Lew, John Talbot +3
Toyota Research Institute, Los Altos, CA 94022, USA. · Department of Aeronautics and Astronautics, Stanford University, Stanford, CA 94305, USA.
Safety filters have been shown to be effective tools to ensure the safety of control systems with unsafe nominal policies. To address scalability challenges in traditional synthesis methods, learning-based approaches have been proposed for designing safety filters for systems with high-dimensional state and control spaces. However, the inevitable errors in the decisions of these models raise concerns about their reliability and the safety guarantees they offer. This paper presents Adaptive Conformal Filtering (ACoFi), a method that combines learned Hamilton-Jacobi reachability-based safety filters with adaptive conformal inference. Under ACoFi, the filter dynamically adjusts its switching criteria based on the observed errors in its predictions of the safety of actions. The range of possible safety values of the nominal policy's output is used to quantify uncertainty in safety assessment. The filter switches from the nominal policy to the learned safe one when that range suggests it might be unsafe. We show that ACoFi guarantees that the rate of incorrectly quantifying uncertainty in the predicted safety of the nominal policy is asymptotically upper bounded by a user-defined parameter. This gives a soft safety guarantee rather than a hard safety guarantee. We evaluate ACoFi in a Dubins car simulation and a Safety Gymnasium environment, empirically demonstrating that it significantly outperforms the baseline method that uses a fixed switching threshold by achieving higher learned safety values and fewer safety violations, especially in out-of-distribution scenarios.
Sacha Huriot, Ihab Tabbara, Hussein Sibai
Computer Science & Engineering Washington University in St. Louis