We extend the Iterative Closest Point (ICP) algorithm to obtain a method for continuous-time trajectory estimation (CICP) suitable for SLAM from actuated lidar. Traditional solutions to SLAM from actuated lidar rely heavily on the accuracy of an auxiliary pose sensor to form rigid frames. These frames are then used with ICP to obtain accurate pose estimates. However, since lidar records a single range sample at time, any error in inter-sample sensor motion must be accounted for. This is not possible if the frame is treated as a rigid point cloud. In this work, instead of ICP we estimate a continuous-time trajectory that takes into account inter-sample pose errors. The trajectory is represented as a linear combination of basis functions and formulated as a solution to a (sparse) linear system without restrictive assumptions on sensor motion. We evaluate the algorithm on synthetic and real data and show improved accuracy in open-loop SLAM in comparison to state-of-the-art rigid registration methods.

This paper describes the application of Distributional Clustering [20] to document classification. This approach clusters words into groups based on the distribution of class labels associated with each word. Thus, unlike some other unsupervised dimensionalityreduction techniques, such as Latent Semantic Indexing, we are able to compress the feature space much more aggressively, while still maintaining high document classification accuracy. Experimental results obtained on three real-world data sets show that we can reduce the feature dimensionality by three orders of magnitude and lose only 2% accuracy---significantly better than Latent Semantic Indexing [6], class-based clustering [1], feature selection by mutual information [23], or Markov-blanket-based feature selection [13]. We also show that less aggressive clustering sometimes results in improved classification accuracy over classification without clustering. 1 Introduction The popularity of the Internet has caused an exponent...