Score: 1

Learning Verifiable Control Policies Using Relaxed Verification

Published: April 23, 2025 | arXiv ID: 2504.16879v1

By: Puja Chaudhury, Alexander Estornell, Michael Everett

Potential Business Impact:

Makes robots safer by checking them while learning.

Business Areas:
Autonomous Vehicles Transportation

To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism in the verification algorithm, establishing these guarantees may not be possible. Instead, this work proposes to perform verification throughout training to ultimately aim for policies whose properties can be evaluated throughout runtime with lightweight, relaxed verification algorithms. The approach is to use differentiable reachability analysis and incorporate new components into the loss function. Numerical experiments on a quadrotor model and unicycle model highlight the ability of this approach to lead to learned control policies that satisfy desired reach-avoid and invariance specifications.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
7 pages

Category
Electrical Engineering and Systems Science:
Systems and Control