# Differentiable Collision Detection for a Set of Convex Primitives

arXiv: https://arxiv.org/abs/2207.00669 · HTML: https://mlsanity.com/paper/2207.00669/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2022.

## Built on by (most cited first, 5 of 5)

- [Distance and Collision Probability Estimation from Gaussian Surface Models](https://mlsanity.com/paper/2402.00186/) (2024)
- [A Fully First-Order Layer for Differentiable Optimization](https://mlsanity.com/paper/2512.02494/) (2025)
- [Improved Convex Decomposition with Ensembling and Negative Primitives](https://mlsanity.com/paper/2405.19569/) (2024)
- [Learning Agile Gate Traversal via Analytical Optimal Policy Gradient](https://mlsanity.com/paper/2508.21592/) (2025)
- [GLUE: Coordinating Pre-Trained Generative Models for System-Level Design](https://mlsanity.com/paper/2512.19469/) (2025)

## Abstract (arXiv)

Collision detection between objects is critical for simulation, control, and learning for robotic systems. However, existing collision detection routines are inherently non-differentiable, limiting their applications in gradient-based optimization tools. In this work, we propose DCOL: a fast and fully differentiable collision-detection framework that reasons about collisions between a set of composable and highly expressive convex primitive shapes. This is achieved by formulating the collision detection problem as a convex optimization problem that solves for the minimum uniform scaling applied to each primitive before they intersect. The optimization problem is fully differentiable with respect to the configurations of each primitive and is able to return a collision detection metric and contact points on each object, agnostic of interpenetration. We demonstrate the capabilities of DCOL on a range of robotics problems from trajectory optimization and contact physics, and have made an open-source implementation available.