Probabilistic Collision Detection between Noisy Point Clouds using Robust Classification
We use appropriate techniques from machine learning to compute the collision probability for each point in the input data and accelerate the computation using stochastic traversal of bounding volume hierarchies. We highlight the performance of our algorithm on point clouds captured using PR2 sensors as well as synthetic data sets, and show that our approach provides a fast and robust solution for handling uncertainty in contact computations.
International Symposium on Robotics Research (ISRR), 2011
RGB-D: Advanced Reasoning with Depth Cameras (RSS workshop), 2011