Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Nullspace MPC: A novel multi-objective control framework for explicitly handling task priorities, implemented in ROS Noetic for a Swerve Drive Robot.
| Date | Stars |
|---|---|
| 2026-07-24 | 269 |
| 2026-07-25 | 269 |
| 2026-07-28 | 270 |
| 2026-07-30 | 270 |
| 2026-08-06 | 270 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Nullspace MPC
Nullspace MPC is a novel multi-objective control framework for explicitly handling task priorities.
It demonstrates agile and smooth navigation through a narrow environment with a swerve drive vehicle.
<div align="center">
[](https://wiki.ros.org/noetic)
[](https://www.docker.com/)
[](https://opensource.org/licenses/MIT)
<!-- eyecatch movie -->
</div>
## Setup
### [Option 1] Native Environment
Note: This is the recommended setup for optimal performance.
<details>
<summary>Click here to expand</summary>
1. Prerequisites
- [Ubuntu 20.04](https://releases.ubuntu.com/focal/)
- [ROS Noetic](https://wiki.ros.org/noetic)
2. Clone the repository.
```bash
cd <path-to-your-workspace>
git clone https://github.com/MizuhoAOKI/nullspace_mpc
```
3. Install packages not handled by rosdep.
```bash
cd <path-to-your-workspace>/nullspace_mpc
sudo make install_deps
```
4. Initialize rosdep, update it, and install ROS dependencies.
```bash
cd <path-to-your-workspace>/nullspace_mpc
sudo rosdep init # Skip if already initialized
rosdep update --rosdistro noetic
rosdep install -y --from-paths src --ignore-src --rosdistro noetic
```
5. Build the project.
```bash
cd <path-to-your-workspace>/nullspace_mpc
make build
```
</details>
### [Option 2] Docker Environment
#### GPU Accelerated Environment
<details>
<summary>Click here to expand</summary>
1. Prerequisites
- [Docker](https://docs.docker.com/engine/install/ubuntu/)
- For Ubuntu users, you can use the convenience script:
```bash
curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh
```
- [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
- This is required to allow Docker containers to access the host's GPU.
- NVIDIA GPU & Driver
- An NVIDIA GPU and a compatible driver for the base image (nvidia/cuda:12.4.1-devel-ubuntu20.04) are required.
2. Clone the repository.
```bash
cd <path-to-your-workspace>
git clone https://github.com/MizuhoAOKI/nullspace_mpc
```
3. Build the Docker image (first-time setup).
```bash
cd <path-to-your-workspace>/nullspace_mpc
make setup_docker_gpu
```
4. Run the Docker container and start a bash session inside.
```bash
cd <path-to-your-workspace>/nullspace_mpc
make run_docker_gpu
```
5. [Inside the docker container] Build the project.
```bash
cd ~/nullspace_mpc
make build
```
</details>
#### CPU-Only Environment
<details>
<summary>Click here to expand</summary>
Warning: This setup runs entirely on the CPU. Performance is significantly lower, and on my test system it was not sufficient for stable control. Use GPU or native setup whenever possible.
1. Prerequisites
- [Docker](https://docs.docker.com/engine/install/ubuntu/)
- For Ubuntu users:
```bash
curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh
```
2. Clone the repository.
```bash
cd <path-to-your-workspace>
git clone https://github.com/MizuhoAOKI/nullspace_mpc
```
3. Build the Docker image (first-time setup).
```bash
cd <path-to-your-workspace>/nullspace_mpc
make setup_docker_cpu
```
4. Run the Docker container and start a bash session inside.
```bash
cd <path-to-your-workspace>/nullspace_mpc
make run_docker_cpu
```
5. [Inside the docker container] Build the project.
```bash
cd ~/nullspace_mpc
make build
```
</details>
## Usage
This packExcerpt of 7,157 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f823e035a0f20f94, topic:robotics, topic:ros, topic:autonomous-driving