6 papers
Refining Almost-Safe Value Functions on the Fly
Sander Tonkens, Sosuke Kojima, Chenhao Liu +2
Control Barrier Functions (CBFs) are a powerful tool for ensuring robotic safety, but designing or learning valid CBFs for complex systems is a significant challenge. While Hamilto…
Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations
William Sharpless, Dylan Hirsch, Sander Tonkens +2
Hard constraints in reinforcement learning (RL) often degrade policy performance. Lagrangian methods offer a way to blend objectives with constraints, but require intricate reward…
MADR: MPC-guided Adversarial DeepReach
Ryan Teoh, Sander Tonkens, William Sharpless +4
Hamilton-Jacobi (HJ) Reachability offers a framework for generating safe value functions and policies in the face of adversarial disturbance, but is limited by the curse of dimensi…
From Space to Time: Enabling Adaptive Safety with Learned Value Functions via Disturbance Recasting
Sander Tonkens, Nikhil Uday Shinde, Azra BegzadiÄ +3
The widespread deployment of autonomous systems in safety-critical environments such as urban air mobility hinges on ensuring reliable, performant, and safe operation under varying…
Back to Base: Towards Hands-Off Learning via Safe Resets with Reach-Avoid Safety Filters
Azra BegzadiÄ, Nikhil Uday Shinde, Sander Tonkens +5
Designing controllers that accomplish tasks while guaranteeing safety constraints remains a significant challenge. We often want an agent to perform well in a nominal task, such as…
Reachability Barrier Networks: Learning Hamilton-Jacobi Solutions for Smooth and Flexible Control Barrier Functions
Matthew Kim, William Sharpless, Hyun Joe Jeong +3
Recent developments in autonomous driving and robotics underscore the necessity of safety-critical controllers. Control barrier functions (CBFs) are a popular method for appending…