The paper combines DeepG pixel bounds with CROWN bound propagation to compute outer approximations of reachable sets for vision-based controllers under entity-specific geometric perturbations.
A Reachability Method for Verifying Dynamical Systems with Deep Neural Network Controllers
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Deep neural networks can be trained to be efficient and effective controllers for dynamical systems; however, the mechanics of deep neural networks are complex and difficult to guarantee. This work presents a general approach for providing guarantees for deep neural network controllers over multiple time steps using a combination of reachability methods and open source neural network verification tools. By bounding the system dynamics and neural network outputs, the set of reachable states can be over-approximated to provide a guarantee that the system will never reach states outside the set. The method is demonstrated on the mountain car problem as well as an aircraft collision avoidance problem. Results show that this approach can provide neural network guarantees given a bounded dynamic model.
citation-role summary
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Verification of Visual Controllers via Compositional Geometric Transformations
The paper combines DeepG pixel bounds with CROWN bound propagation to compute outer approximations of reachable sets for vision-based controllers under entity-specific geometric perturbations.