SynPick: A Dataset for Dynamic Bin Picking Scene Understanding
This provides a dataset for researchers in robotics and computer vision working on industrial bin-picking, but it is incremental as it builds on existing formats and applications.
The authors introduced SynPick, a synthetic dataset for dynamic scene understanding in bin-picking, based on the Amazon Robotics Challenge, and showed that tracking poses during manipulation improves performance over single-shot estimation.
We present SynPick, a synthetic dataset for dynamic scene understanding in bin-picking scenarios. In contrast to existing datasets, our dataset is both situated in a realistic industrial application domain -- inspired by the well-known Amazon Robotics Challenge (ARC) -- and features dynamic scenes with authentic picking actions as chosen by our picking heuristic developed for the ARC 2017. The dataset is compatible with the popular BOP dataset format. We describe the dataset generation process in detail, including object arrangement generation and manipulation simulation using the NVIDIA PhysX physics engine. To cover a large action space, we perform untargeted and targeted picking actions, as well as random moving actions. To establish a baseline for object perception, a state-of-the-art pose estimation approach is evaluated on the dataset. We demonstrate the usefulness of tracking poses during manipulation instead of single-shot estimation even with a naive filtering approach. The generator source code and dataset are publicly available.