TechTalks from event: Technical session talks from ICRA 2012

Conference registration code to access these videos can be accessed by visiting this link: PaperPlaza. Step-by-step to access these videos are here: step-by-step process .
Why some of the videos are missing? If you had provided your consent form for your video to be published and still it is missing, please contact


  • Efficient Data-Driven MCMC Sampling for Vision-Based 6D SLAM Authors: Min, Jihong; Kim, Jungho; Shin, Seunghak; Kweon, In So
    In this paper, we propose a Markov Chain Monte Carlo (MCMC) sampling method with the data-driven proposal distribution for six-degree-of-freedom (6-DoF) SLAM. Recently, visual odometry priors have been widely used as the process model in the SLAM formulation to improve the SLAM performance. However, modeling the uncertainties of incremental motions estimated by visual odometry is especially difficult under challenging conditions, such as erratic motion. For a particle-based model representation, it can represent the uncertainty of the camera motion well under erratic motion compared to the constant velocity model or a Gaussian noise model, but the manner of representing the proposal distribution and sampling the particles is extremely important, as we can maintain only a limited number of particles in the high-dimensional state space. Hence, we propose an effective sampling approach by exploiting MCMC sampling and the data-driven proposal distribution to propagate the particles. We demonstrate the performance of the proposed approach for 6-DoF SLAM using both synthetic and real datasets and compare the performance with those of other sampling methods.
  • Scan Segments Matching for Pairwise 3D Alignment Authors: Douillard, Bertrand; Quadros, Alastair James; Morton, Peter; Underwood, James Patrick; De Deuge, Mark; Hugosson, Simon; Hallström, Manfred; Bailey, Tim
    This paper presents a method for pairwise 3D alignment which solves data association by matching scan segments across scans. Generating accurate segment associations allows to run a modified version of the Iterative Closest Point (ICP) algorithm where the search for point-to-point correspondences is constrained to associated segments. The novelty of the proposed approach is in the segment matching process which takes into account the proximity of segments, their shape, and the consistency of their relative locations in each scan. Scan segmentation is here assumed to be given (recent studies provide various alternatives). The method is tested on seven sequences of Velodyne scans acquired in urban environments. Unlike various other standard versions of ICP, which fail to recover correct alignment when the displacement between scans increases, the proposed method is shown to be robust to displacements of several meters. In addition, it is shown to lead to savings in computational times which are potentially critical in real-time applications.
  • Planar Surface SLAM with 3D and 2D Sensors Authors: Trevor, Alexander J B; Rogers III, John G.; Christensen, Henrik Iskov
    We present an extension to our feature based mapping technique that allows for the use of planar surfaces such as walls, tables, counters, or other planar surfaces as landmarks in our mapper. These planar surfaces are measured both in 3D point clouds, as well as 2D laser scans. These sensing modalities compliment each other well, as they differ significantly in their measurable fields of view and maximum ranges. We present experiments to evaluate the contributions of each type of sensor.
  • Uncertainty Estimation for a 6-DoF Spectral Registration Method As Basis for Sonar-Based Underwater 3D SLAM Authors: Pfingsthorn, Max; Birk, Andreas; Buelow, Heiko
    An uncertainty estimation method for 6 degree of freedom (6-DoF) spectral registration is introduced here. The underlying 6-DoF registration method based on Phase Only Matched Filtering (POMF) is capable of dealing with very noisy sensor data. It is hence well suited for 3D underwater mapping, where relatively inaccurate sonar imaging devices have to be employed. An uncertainty estimation method is required to use this registration method in a Simultaneous Localization and Mapping (SLAM) framework. To our knowledge, the first such method for 6-DoF spectral registration is presented here. This new uncertainty estimation method treats the POMF results as probability mass functions (PMF). Due to the decoupling in the underlying method, yaw is computed by a one-dimensional POMF leading hence to a 1D PMF; roll and pitch are simultaneously computed and hence encoded in a 2D PMF. Furthermore, a 3D PMF is generated for the translation as it is determined by a 3D POMF. A normal distribution is fitted on each of the PMF to get the uncertainty estimate. The method is experimentally evaluated with simulated as well as real world sonar data. It is shown that it indeed can be used for SLAM, which significantly improves the map quality.
  • Interactive Acquisition of Residential Floor Plans Authors: Kim, Young Min; Dolson, Jennifer; Sokolsky, Michael; Koltun, Vladlen; Thrun, Sebastian
    We present a hand-held system for real-time, interactive acquisition of residential floor plans. The system integrates a commodity range camera, a micro-projector, and a button interface for user input and allows the user to freely move through a building to capture its important architectural elements. The system uses the Manhattan world assumption, which posits that wall layouts are rectilinear. This assumption allows generating floor plans in real time, enabling the operator to interactively guide the reconstruction process and to resolve structural ambiguities and errors during the acquisition. The interactive component aids users with no architectural training in acquiring wall layouts for their residences. We show a number of residential floor plans reconstructed with the system.
  • CFastSLAM: A New Jacobian Free Solution to SLAM Problem Authors: Song, Yu; Li, Qingling; Kang, Yifei
    While FastSLAM algorithm is a popular solution to SLAM problem, it suffers from two major drawbacks: one is particle set degeneracy due to lack of observation information in proposal distribution; the other is errors accumulation caused by inaccuracy linearization of the robot motion model and the observation model. To overcome the problems, we propose a new Jacobian free CFastSLAM algorithm. The main contribution of this work lies in the utilization of Cubature Kalman Filter (CKF), which calculate Gaussian Weight Integral based on Cubature Rule, to design an optimal proposal distribution of the particle filter and to estimate the environment feature landmarks. On the basis of Rao-Blackwellized particle filter, proposed algorithm is comprised by two main parts: in the first part, a Cubature Particle Filter (CPF) is derived to localize the robot; in the second part, a set of CKFs is used to estimate the environment landmarks. The performance of the CFastSLAM is investigated and compared with that of FastSLAM2.0 and UFastSLAM in simulations and experiments. Results verify that the CFastSLAM improves SLAM performance.