PerAct²: Benchmarking and Learning for
Robotic Bimanual Manipulation Tasks

The table below provides links to each task within the dataset. Please be aware that these files are quite large and may require significant download time. If you need alternative download options, please contact the authors directly. To ensure the integrity of the downloaded files, it is recommended to verify the checksums using SHA256 (Download 128x128, Download 256x256) or SHA512 (Download 128x128, Download 256x256) . Here are the instructions for checking the checksum and unpacking the squashfs files:

1. Download the file and its corresponding checksum file.
2. Run the following command to check the SHA256 checksum:

   sha256sum -c SHA256SUMS

3. To work with the squashfs file, you will need unsquashfs. If you don't have it installed, you can install it on Linux using:

   sudo apt install squashfs-tools

4. You can mount the squashfs file without unpacking it once unsquashfs is installed. To do this, create a mount point and then mount the file:

   sudo mkdir /mnt/rlbench_data
   mount filename.squashfs /mnt/rlbench_data -t squashfs -o loop

5. Alternatively, run the following command to unpack the file:

   unsquashfs filename.squashfs

6. The contents will be extracted to a directory named squashfs-root by default. You can specify a different directory using the -d option:

   unsquashfs -d /mnt/rlbench_data filename.squashfs

If you encounter any discrepancies or have questions, please do not hesitate to reach out to the authors for assistance.

To benchmark, we extend RLBench to the complex bimanual case by adding functionality and tasks for bimanual manipulation RLBench is a robot learning benchmark suite consisting of more than 100 tasks to facilitate robot learning, which is widely used in the community. Among task diversity other key properties include reproducibility or the ability to adapt to different learning strategies. We extend RLBench to bimanual manipulation, while keeping the functionality and its key properties. This allows us to quantify the success of our method and to compare it against other baselines. Compared to unimanual manipulation, bimanual manipulation is more challenging as it requires different kinds of coordination and orchestration of the two arms. For the implementation side this makes it much more complex since synchronization is required when controlling both arms at the same time.
The following table classifies the tasks according to the bimanual taxonomy of Krebs et al.. Here, key distinguishing factors are the coupling as well as the required coordination between the two arms. We extended the classification in that we also distinguish between physical coupling, i.e., if one arm exerts a force that could be measured by the other arm.