Keypoint-based Diffusion for Robotic Motion Planning on the NICOL Robot
This addresses runtime inefficiencies in robotic motion planning for applications like the NICOL robot, though it appears incremental as it builds on existing diffusion and learning methods.
The paper tackles robotic motion planning by proposing a diffusion-based action model that learns from a dataset generated by numerical planners, achieving a runtime reduction by an order of magnitude and up to 90% success rate for collision-free solutions.
We propose a novel diffusion-based action model for robotic motion planning. Commonly, established numerical planning approaches are used to solve general motion planning problems, but have significant runtime requirements. By leveraging the power of deep learning, we are able to achieve good results in a much smaller runtime by learning from a dataset generated by these planners. While our initial model uses point cloud embeddings in the input to predict keypoint-based joint sequences in its output, we observed in our ablation study that it remained challenging to condition the network on the point cloud embeddings. We identified some biases in our dataset and refined it, which improved the model's performance. Our model, even without the use of the point cloud encodings, outperforms numerical models by an order of magnitude regarding the runtime, while reaching a success rate of up to 90% of collision free solutions on the test set.