# CoBRA: A Composable Benchmark for Robotics Applications

arXiv: https://arxiv.org/abs/2203.09337 · HTML: https://mlsanity.com/paper/2203.09337/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2022.

## Built on by (most cited first, 2 of 2)

- [Optimizing Modular Robot Composition: A Lexicographic Genetic Algorithm Approach](https://mlsanity.com/paper/2309.08399/) (2023)
- [Holistic Construction Automation with Modular Robots: From High-Level Task Specification to Execution](https://mlsanity.com/paper/2412.20867/) (2024)

## Abstract (arXiv)

Selecting an optimal robot, its base pose, and trajectory for a given task is currently mainly done by human expertise or trial and error. To evaluate automatic approaches to this combined optimization problem, we introduce a benchmark suite encompassing a unified format for robots, environments, and task descriptions. Our benchmark suite is especially useful for modular robots, where the multitude of robots that can be assembled creates a host of additional parameters to optimize. We include tasks such as machine tending and welding in synthetic environments and 3D scans of real-world machine shops. All benchmarks are accessible through https://cobra.cps.cit.tum.de, a platform to conveniently share, reference, and compare tasks, robot models, and solutions.