Pith. sign in

REVIEW 3 cited by

Neural Certificates for Safe Control Policies

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.08465 v1 pith:TN5NSIGA submitted 2020-06-15 eess.SY cs.LGcs.SY

Neural Certificates for Safe Control Policies

Wanxin Jin , Zhaoran Wang , Zhuoran Yang , Shaoshuai Mou This is my paper
classification eess.SY cs.LGcs.SY
keywords goal-reachingsafepolicysystemfunctionlearnneuralpolicies
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper develops an approach to learn a policy of a dynamical system that is guaranteed to be both provably safe and goal-reaching. Here, the safety means that a policy must not drive the state of the system to any unsafe region, while the goal-reaching requires the trajectory of the controlled system asymptotically converges to a goal region (a generalization of stability). We obtain the safe and goal-reaching policy by jointly learning two additional certificate functions: a barrier function that guarantees the safety and a developed Lyapunov-like function to fulfill the goal-reaching requirement, both of which are represented by neural networks. We show the effectiveness of the method to learn both safe and goal-reaching policies on various systems, including pendulums, cart-poles, and UAVs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control

    cs.LG 2024-11 unverdicted novelty 7.0

    CT-BaB integrates branch-and-bound during training to tighten certified Lyapunov bounds, yielding neural controllers with 164X larger verifiable ROA and 11X faster verification than CEGIS on a 2D quadrotor.

  2. Verification Framework for the Union of Control Barrier Functions

    math.OC 2026-06 unverdicted novelty 6.0

    Develops sufficient conditions and sum-of-squares verification algorithms for union of control barrier functions under two switching strategies to ensure finite switches and forward invariance.

  3. Data-Driven Formal Methods for Complex Dynamical Systems: A Survey

    eess.SY 2026-07 accept novelty 2.0

    A taxonomy and survey of data-driven formal verification and controller synthesis, organized around abstraction-based, functional-certificate, and compositional methods with PAC, Lipschitz, and structural-property guarantees.