Particle Filter Localization on Continuous Occupancy Maps
Occupancy grid maps have been widely used for robot localization. Despite the popularity, this representation has some limitations, such as requirement of discretization of the environment, assumption of independence between grid cells and necessity of dense sensor data. Suppressing these limitations can improve the localization performance, but requires a different representation of the environment. Gaussian process occupancy map (GPOM) is a novel representation based on Gaussian Process that enables the construction of continuous maps (i.e. without discretization) using few laser measurements. This paper addresses a new localization method that uses GPOM to estimate the robot pose in areas not directly observed during mapping and generally provides higher accuracy compared to occupancy grid maps localization. Specifically, we devised a novel likelihood model based on the multivariate normal probability density function and adapted the particle filter localization method to work with GPOM. Experiments showed localization errors more than three times lower in comparison with particle filter localization using occupancy grid maps.
KeywordsGaussian Process Occupancy Maps Gaussian Process Particle Filter Localization Occupancy Grid Map Sparse laser sensor data
The authors acknowledge the grant provided by FAPESP (2012/02354-1; 2014/09096-3), the ACFR and LRM groups for their support.
- 2.Ferris, B., Fox, D., Lawrence, N.: WiFi-SLAM using gaussian process latent variable models. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, IJCAI 2007, San Francisco, CA, USA, pp. 2480–2485 (2007)Google Scholar
- 3.Kim, S., Kim, J.: Building occupancy maps with a mixture of Gaussian processes. In: 2012 IEEE International Conference on Robotics and Automation (ICRA), pp. 4756–4761, May 2012Google Scholar
- 4.Ko, J., Fox, D.: Gp-bayesfilters: Bayesian filtering using gaussian process prediction and observation models. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2008, pp. 3471–3476, September 2008Google Scholar
- 7.Plagemann, C., Kersting, K., Pfaff, P., Burgard, W.: Gaussian beam processes: a nonparametric bayesian measurement model for range finders. In: Proceedings of Robotics: Science and Systems, RSS (2007)Google Scholar
- 8.Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). The MIT Press (2005). ISBN:026218253XGoogle Scholar
- 9.Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark forthe evaluation of RGB-D SLAM systems. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 573–580, October 2012Google Scholar
- 10.Yang, S.W., Wang, C.C.: Feasibility grids for localization and mapping in crowded urban scenes. In: 2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 2322–2328, May 2011Google Scholar