Unified Overview of Safety Certificate Functions: Techniques from Hamilton--Jacobi Reachability and Control Barrier Functions
Authors: Hao Wang, Max Cohen, Zeyuan Feng, Donggeon David Oh, Oswin So, Songyuan Zhang, Javier Borquez, Chuchu Fan, Jaime Fernández Fisac, Haimin Hu, Jason J. Choi, Somil Bansal
Organizations: University of Southern California · Stanford University · North Carolina State University · Princeton University · Massachusetts Institute of Technology · Universidad de Santiago de Chile · Johns Hopkins University · University of California, Los Angeles
Safety is a central concern in modern autonomous systems. Safety certificates---functions whose existence guarantees that a system meets its safety specification---have long been used as a principled tool for rigorously reasoning about safety. Methods for synthesizing such certificates are scattered across research areas, with little guidance on when to use a particular approach. This tutorial provides a holistic treatment of safety certificate synthesis centered on two widely used families: Hamilton--Jacobi (HJ) reachability analysis and control barrier functions (CBFs). For each family of methods, we first introduce its general formulation, along with classical and learning-based tools for certificate synthesis. Next, we introduce two benchmark problems consisting of vehicle systems of differing complexity to assess the certificate quality of different synthesis methods and their effectiveness in safety-critical control. We use these benchmarks to compare various methods and provide practical guidance for selecting an approach.
Figures & tables
Fig. 1: Overview of the methods for designing safety certificates covered in this tutorial. See Sec. VII for detailed guidance for practitioners. See Sec. II-F for the overview of the methods not covered in this tutorial.
Symbol
Definition
x
State
u
Control
t
Time
k
Time index in discrete time
0
Initial time
T
Final time
TABLE I: Notations used in this tutorial.
Fig. 2: Running example: a 5D kinematic vehicle model that needs to stay within the race track boundary (black) while keeping the velocity bounds. The maximal safe sets computed by the numerical HJ reachability method [ 28 ] are visualized as various slices at different speeds, under θ=ω=0 .
Fig. 3: Applying continuous-time PNCBFs to the running example. (a) Data collection with a centerline-tracking backup controller. Each trajectory, colored by the value of C1 in ( 67 ), is a rollout of a centerline-tracking backup controller. (b) The learned PNCBF can be used as a safety filter with a CBF-QP ( 19 ) to filter an unsafe MPPI reference controller.
Fig. 4: Heat maps and contours of safe set slices for each method in the running example, sliced at [θ,ω,v]=[0,0,1.45] . The contour of the ground-truth maximal safe set is shown as grey dotted lines.
Fig. 5: Error metrics and filtering results for the running example.
Method
False Safe Rate (%) ↓
False Unsafe Rate (%) ↓
Safety Rate (%) ↑
Gates Passed ↑
Ground-Truth Maximal Safe Set
–
–
100.00
80.05
High-Order CBF
25.51
12.88
68.00
38.65
Backstepping CBF
8.52
14.08
86.00
61.45
Backup CBF
2.35
7.22
73.00
86.90
PINN-Based Reachability
0.00±0.00
0.21±0.17
99.60±0.89
88.00±1.27
Neural CBF (PNCBF)
0.00±0.00
36.83±1.27
100.00±0.00
90.46±1.32
TABLE II: Case Study 1 (Running Example) Results—Simplified Car Dynamics
Fig. 6: Heat maps and contours of safe set slices for each method in Case Study 2 (F1Tenth), sliced at [ϕ,v,θ,ω,β]=[0,6,0,0,0] .
Fig. 7: Filtering metrics for case study 2 (F1Tenth).
Method
Observation
Safety Rate (%) ↑
Gates Passed ↑
Calibrated Safe Set Volume ↑
Reduced-Order CBF
State-based
100.00
124.90
–
PINN-Based Reachability
State-based
98.80±2.68
136.00±1.33
0.3845±0.0523
47D Local State
100.00±0.00
131.88±1.02
0.5148±0.0875
Neural CBF (PNCBF)
State-based
100.00±0.00
152.54±1.78
0.2527±0.0009
47D Local State
100.00±0.00
151.12±2.11
0.2530±0.0009
66D Local Observation
100.00±0.00
158.94±0.47
0.2653±0.0003
TABLE III: Case Study 2 Results—F1Tenth Racing
Design Effort
Certificate Quality
Method
Comp. Effort
Analytical Effort
Needs Derivatives
Needs Model
Safety
Conservativeness
Handles Control Bounds
Robustness to Disturbance
Numerical HJ Reachability
High
Moderate
Yes
Yes
Excellent
Excellent
Yes
Worst-case over modeled bounds
High-Order CBF
Negligible
Easy
Yes
Yes
Poor a
Moderate
No
Attractive safe set
Backstepping CBF
Low
Involved
Yes
Yes
Poor b
Moderate b
No
Robust variants available
Backup CBF
Low
Moderate
Yes
Yes
Medium
Good
Yes
Robust variants available
PINN-Based Reachability
Moderate
Moderate
No
Yes
Good
Good
Yes
Robust variants available
TABLE IV: Design Effort Versus Certificate Quality Across Synthesis Methods.
Fig. 8: Applications of Numerical Solutions for HJ reachability: real-time collision avoidance via FPGA-accelerated grid solving [ 146 ] (top), hybrid mode planning for a quadruped navigating slope and ground obstacles [ 148 ] (middle), and observation-conditioned safety filtering using grid-computed value functions as training data [ 151 ] (bottom).
Fig. 9: Applications of CBF backstepping as applied to drones as well as CBFs via reduced-order models applied to quadrupeds, hopping robots, and fixed-wing aircraft. These images are adapted from [ 103 , 102 , 153 , 154 ] .
Fig. 10: Selected applications leveraging the DeepReach family: (Top) two-drone pursuit–evasion game; (Row 2) safe and performant manipulation with payload; (Row 3, Left) spacecraft docking and (Right) autonomous vehicle predictive Forward Reachable Sets; (Bottom) robust safety verification under severe perceptual uncertainty.
Fig. 11: Applications of neural CBFs, including fixed-wing aircraft maneuvering, robust quadcopter obstacle avoidance, rally racing, and multi-agent systems. Images adapted from [ 16 , 164 , 17 , 121 , 18 ] .
Fig. 12: RL-based HJ reachability applied to black-box dynamical systems with high-dimensional observation spaces: robust quadrupedal locomotion with direct torque control (36D), human-in-the-loop car racing (133D), interactive urban driving with a neural predictor (200D), visual manipulation (3 × 128 × 128 RGB observation), and fixed-wing aircraft maneuvering (11D). Images adapted from [ 127 , 124 , 141 , 172 ] .
Hamilton-Jacobi reachability constructs safety certificates for specified dynamics and safety constraints, tying each certificate to the deployment context for which it is synthesized. We ask whether a single certificate can instead represent a family of context-dependent safety problems and be queried across deployment conditions without re-synthesis. We learn a backward reachable tube for an eight-state vehicle model conditioned on local boundary geometry, friction coefficient, and adversarial disturbance scale. Geometry enters through an ego-frame boundary observation that defines the local containment constraint, while friction and disturbance scale enter as explicit operating-condition variables. This allows the same value function to be queried across friction coefficients from 0.4 to 2.0 and on geometries absent from synthesis. On 11 held-out evaluation geometries, the certificate maintains containment across the full tested friction range, including simultaneous geometry and grip shifts, while remaining within 1.2 percentage points in intervention rate and 0.09 m/s in speed of certificates re-synthesized with knowledge of the test geometry. We then deploy the certificate as a sampled discrete-time control barrier function filter on a full-scale vehicle near the handling limit. Lateral containment holds in every hardware session under both adversarial driving and autonomous racing, with 99th-percentile acceleration magnitude reaching 0.99 g. Across three certificates evaluated under a fixed autonomous racing controller, lap time varies by only 3.1%, demonstrating that a context-conditioned reachability certificate can transfer to deployment geometries absent from synthesis with modest performance cost.
Ali Fuat Sahin, Yunus Yazoglu, John Talbot +3
Ecole Polytechnique Fédérale de Lausanne · Stanford University · Toyota Research Institute
Hamilton-Jacobi (HJ) reachability analysis offers formal safety guarantees for control systems, but training accurate neural certificates remains difficult, particularly when unsafe regions are hard to characterize. We propose a verification-guided training framework that addresses this by using probabilistic enumeration of safety constraints to detect forward-invariance violations, i.e., states where the learned certificate incorrectly classifies unsafe behavior. This produces a compact, targeted set of counterexamples that more precisely captures the failure boundary than inputs generated by standard adversarial attack methods. Crucially, using this representation to fine-tune a pretrained HJ value function yields larger certified regions and reduces certification time across all tested benchmarks. We further introduce a shielding mechanism based on the refined certificates to enforce safety constraints at deployment time. We evaluate the proposed safety filter in a realistic, physics-based Isaac Sim environment and through real-world autonomous racing experiments, achieving zero safety constraint violations compared to a nominal controller and a backup policy based on Linear Quadratic Regulation (LQR). These results demonstrate the effectiveness of the proposed shielding mechanism in ensuring safe operation under high-speed, safety-critical conditions.
Dynamical Systems (DS) are reactive motion policies representing vector fields trained with theoretical guarantees of stability and convergence. To ensure safety during deployment in unknown environments they must be locally reshaped, either through modulation or geometric control barrier function strategies. However, depending on the geometry of the obstacles and the complexity of the DS, these local strategies can lead the system to unavoidable collisions or spurious attractors. In this work, we certify safety with a value function drawn from the notion of backward reachability tube, which measures the worst-case safety along a rollout trajectory of the nominal DS. Usually, such a value function is intractable for a controlled system due to curse of dimensionality. We show that in the DS-based learning-from-demonstration setting, the absence of a control input collapses the reachability problem to a deterministic rollout, and the presence of certain stability conditions truncates the infinite horizon to a finite one, resulting in a well-defined value function. We further show that the value function we devised is the maximal forward-invariant subset of the obstaclefree region for the nominal DS flow. The application of this certificate function is validated across five DS constructions - analytical, Neural ODE, diffeomorphic latent space, LPV-DS, SE(3)and validate it on a Franka manipulator. Modulation and geometric CBFs also suffer from saddle point in cases of headon approach towards an unsafe zone. We show that CBF-on-V avoids this pitfall entirely.
Aditya Vats, Tianyi Xia, Nadia Figueroa
The authors are with the University of Pennsylvania, Philadelphia, PA, USA.