You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
title: "Two papers accepted at <strong>ICRA</strong> 2026"
4
+
date: 2026-01-31
5
+
---
6
+
7
+
Our paper ["Beyond Collision Cones: Dynamic Obstacle Avoidance for Nonholonomic Robots via Dynamic Parabolic Control Barrier Functions"](/papers/2026-dpcbf.md) and ["Safe Model Predictive Diffusion with Shielding"](/papers/2026-safe_mpd.md) have been accepted to IEEE ICRA 2026!
title: "Paper accepted at <strong>L4DC</strong> 2026"
4
+
date: 2026-01-23
5
+
---
6
+
7
+
Our paper ["Provably Safe Stein Variational Clarity-Aware Informative Planning"](/papers/2026_stein_clarity_L4DC.md) has been accepted at the Learning for Dynamics & Control Conference (L4DC 2026)!
abstract: "This letter investigates the problem of composing multiple control barrier functions (CBFs)—and matrix control barrier functions (MCBFs)—through logical and combinatorial operations. Standard CBF formulations naturally enable conjunctive (AND) combinations, but disjunctive (OR) and more general logical structures introduce nonsmoothness and possibly a combinatorial blow-up in the number of logical combinations. We introduce the framework of combinatorial CBFs that addresses p-choose-r safety specifications and their nested composition. The proposed framework ensures safety for the exact safe set in a scalable way, using the original number of primitive constraints. We establish theoretical guarantees on safety under these compositions, and we demonstrate their use on a patrolling problem in a multi-agent system."
30
+
# bib entry (optional). the |- is used to allow for multiline entry."
title: "Safe Model Predictive Diffusion with Shielding"
4
-
date: 2026-01-02
4
+
date: 2026-01-31
5
5
image: /images/2026-safe_mpd.gif
6
-
venue: "under review"
6
+
venue: "IEEE ICRA 2026"
7
7
authors:
8
8
- taekyungkim
9
9
- Keyvan Majd
@@ -12,8 +12,8 @@ authors:
12
12
- dimitrapanagou
13
13
- Georgios Fainekos
14
14
projectpage: https://www.taekyung.me/safe-mpd
15
-
arxiv:
16
-
code:
15
+
arxiv: https://arxiv.org/abs/2512.06261
16
+
code: https://github.com/cps-atlas/safe-mpd
17
17
video: https://youtu.be/DQBeybU7EYI
18
18
abstract: "Generating safe, kinodynamically feasible, and optimal trajectories for complex robotic systems is a central challenge in robotics. This paper presents Safe Model Predictive Diffusion (Safe MPD), a training-free diffusion planner that unifies a model-based diffusion framework with a safety shield to generate trajectories that are both kinodynamically feasible and safe by construction. By enforcing feasibility and safety on all samples during the denoising process, our method avoids the common pitfalls of post-processing corrections, such as computational intractability and loss of feasibility. We validate our approach on challenging non-convex planning problems, including kinematic and acceleration-controlled tractor-trailer systems. The results show that it substantially outperforms existing safety strategies in success rate and safety, while achieving sub-second computation times. "
0 commit comments