Safe Planning with Diffusion Probabilistic Models
-
Updated
Apr 30, 2025 - Python
Safe Planning with Diffusion Probabilistic Models
Safe Pontryagin Differentiable Programming (Safe PDP) is a new theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks.
[ICRA 2025] Code for Conformalized Reachable Sets for Obstacle Avoidance With Spheres
A Single-Outcome Replanner for Computing Strong Cyclic Solutions in Fully Observable Non-Deterministic Domains
A MuJoCo-based simulation framework for studying robot behavior under unexpected failures like hardware shutdown, sensor degradation, or actuator malfunctions.
RTD-RAX: fast, safe trajectory planning for systems under unknown disturbances. Uses mixed-monotone reachability to certify and repair planned trajectories online, extending Reachability-based Trajectory Design with runtime safety assurance that handles real-world uncertainty.
Safety-constrained PDDL planning: physical safety encoded in action preconditions, verified by an independent simulator across 3 domains (numeric crushing, blocks-world, categorical fragility)
To associate your repository with the safe-planning topic, visit your repo's landing page and select "manage topics."