Nosan Kwak

A new compensation technique based on analysis of resampling process in fastslam

The state-of-the-art FastSLAM algorithm has been shown to cause a particle depletion problem while performing simultaneous localization and mapping for mobile robots. As a result, it always produces over-confident estimates of uncertainty as time progresses. This particle depletion problem is mainly due to the resampling process in FastSLAM, which tends to eliminate particles with low weights. Therefore, the number of particles to conduct loop-closure decreases, which makes the performance of FastSLAM degenerate. The resampling process has not been thoroughly analyzed even though it is the main reason for the particle depletion problem. In this paper, standard resampling algorithms (systematic residual and partial resampling), a rank-based resampling adopting genetic algorithms are analyzed using computer simulations. Several performance measures such as the effective sample size, the number of distinct particles, estimation errors, and complexity are used for the thorough analysis of the resampling algorithms. Moreover, a new compensation technique is proposed instead of resampling to resolve the particle depletion problem in FastSLAM. In estimation errors, the compensation technique outperformed other resampling algorithms though its run-time was longer than those of others. The most appropriate time to instigate compensation to reduce the run-time was also analyzed with the diminishing number of particles.

Improved particle fusing geometric relation between particles in fastslam

FastSLAM is a framework for simultaneous localization and mapping using a Rao-Blackwellized particle filter (RBPF). But, FastSLAM is known to degenerate over time due to the loss of particle diversity, mainly caused by the particle depletion problem in resampling phase. In this work, improved particle filter using geometric relation between particles is proposed to restrain particle depletion and to reduce estimation errors and error variances. It uses a KD tree (k-dimensional tree) to derive geometric relation among particles and filters particles with importance weight conditions for resampling. Compared to the original particle filter used in FastSLAM, this technique showed less estimation error with lower error standard deviation in computer simulations.

Analysis of Resampling Process for the Particle Depletion Problem in FastSLAM

The state-of-the-art FastSLAM has been shown to cause a particle depletion problem while performing simultaneous localization and mapping for mobile robots. As a result, it always produces over-confident estimates of uncertainty as time progresses. This particle depletion problem is mainly due to the resampling process in FastSLAM, which tends to eliminate particles with low weights. Therefore, the number of particles to perform loop-closure decreases, which makes the performance of FastSLAM degenerate. The resampling process has not been thoroughly analyzed even though it is the main reason for the particle depletion problem. In this paper, standard resampling algorithms (systematic residual and partial resampling), and a rank-based resampling applying genetic algorithms are analyzed using computer simulations. For the thorough analysis, several performance measures are used such as effective sample size, the number of distinct particles, root mean square (RMS) errors, and complexity. According to the simulation results, all resampling algorithms could not resolve the particle depletion problem.

Adaptive prior boosting technique for the efficient sample size in fastSLAM

FastSLAM has been shown to degenerate over time due to sample impoverishment, that is, poor samples are generated during the sampling process. One of major culprits of the sample impoverishment problem is lack of the number of particles estimating the pose of the robot and the environment. In this work, an adaptive prior boosting technique is proposed for the efficient sample size according to the uncertainty of each situation in performing FastSLAM. It uses a back-propagation neural network, learned in various environments, in order to decide the required sample size. This adaptive approach generates a small number of particles when the uncertainty is low while performing FastSLAM, and it generates a large number of particles when the uncertainty is high. This technique efficiently generates the sample size in computer simulations and real environmental experiments, which significantly reduces the RMS feature and position errors.

A Mobile Robot Exploration Strategy with Low Cost Sonar and Tungsten-Halogen Structured Light

Autonomous environment mapping is an essential part of efficiently carrying out complex missions in unknown indoor environments. In this paper, a low cost mapping system composed of a web camera with structured light and sonar sensors is presented. We propose a novel exploration strategy based on the frontier concept using the low cost mapping system. Based on the complementary characteristics of a web camera with structured light and sonar sensors, two different sensors are fused to make a mobile robot explore an unknown environment with efficient mapping. Sonar sensors are used to roughly find obstacles, and the structured light vision system is used to increase the occupancy probability of obstacles or walls detected by sonar sensors. To overcome the inaccuracy of the frontier-based exploration, we propose an exploration strategy that would both define obstacles and reveal new regions using the mapping system. Since the processing cost of the vision module is high, we resolve the vision sensing placement problem to minimize the number of vision sensing in analyzing the geometry of the proposed sonar and vision probability models. Through simulations and indoor experiments, the efficiency of the proposed exploration strategy is proved and compared to other exploration strategies.

Result representation of Rao-Blackwellized particle filtering for SLAM

Recently, particle filters have been applying to many robotic problems including the simultaneous localization and mapping (SLAM). Specifically, SLAM approaches employing Rao-Blackwellized particle filter (RBPF) have shown good results. However, no research is conducted to analyze representation of the results of particle filtering. After finishing the particle filtering, the results such as a map and a path are stored in the separate particles. In most cases, the result of the particle that has the highest importance weight is represented as the result. However, this approach does not give the best result all the time. Thus, We provide the analysis of final representation of particle filtering. In this paper, we compares several methods to derive the final representation of the result after finishing RBPF-SLAM. According to the result, combining data of each particle provides the better result with high probability than using just data of a particle such as the highest weighted particle representation.

A KNOWLEDGE BASE FOR DYNAMIC PATH PLANNING OF MULTI-AGENTS

Abstract A fuzzy rule base is proposed to navigate multi-agents from initial positions to target positions in unknown environments. The proposed fuzzy rule base determines the highest priority of nine possible heading directions. The fuzzy rule base has been developed employing genetic algorithms as an approach to dynamic path planning of autonomous multi-agents in unknown environments. Paths which satisfy some optimization criteria with respect to moving distance, smoothness, and clearance of obstacles was obtained from the fuzzy rule base. The fuzzy rule base was obtained from off-line navigation with precise sensor modeling and applied to various simulated on-line navigation. The performance of the fuzzy rule base in different unknown environments is acceptable and shown in simulation results.

Low cost active range sensing using halogen sheet-of-light for occupancy grid map building

We propose a low cost, accurate and safe active range sensor with a halogen sheet-of-light and a USB camera. We also propose an algorithm suitable for building a local map using the probabilistic sensor model. In this paper, the inexpensive structured light source that uses tungsten-halogen lamp is used, and an efficient method of detecting the sheet-of-light by the camera is proposed. A local map is built using the spatial occupancy technique which is inputs values in an occupancy grid that reflect the probability of occupancy for each cell. In addition, a suitable probabilistic sensor model is employed to build the local map. The experimental results show the validity of the proposed range sensor and the algorithm to build a map using the probabilistic sensor model.

Improved particle filter using geometric relation between particles in fastslam – erratum

This work was supported in part by MIC & IITA through IT Leading R&D Support Project, the Seoul R&BD Program (10689M92991), the MOCIE Industrial Technology Development Program, Korea Science and Engineering Foundation (KOSEF) NRL Program grant funded by Korean government (MEST) (No. R0A-2008-000-20004-0), Growth Engine Technology Development Program funded by Ministry of Knowledge Economy, the ASRI, and the Brain Korea 21 Project.